#867 by GitHub stars
rampstackco/claude-skills
Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
dist/codex/.agents/skills/accessibility-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/ads-creative-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/ads-performance-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/after-action-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/ai-content-collaboration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/analytics-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/art-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/backup-and-disaster-recovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/beta-program-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-archetype-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-ideation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-identity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-style-guide/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/brand-voice/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/calculator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/chatbot-flow-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/code-review-web/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/comparison-tool-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/competitor-experience-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-and-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-brief-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-distribution/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-migration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-refresh-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-repurposing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/content-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/cost-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/creative-brief/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/creative-brief-selector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/creative-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/cro-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/data-warehouse-experimentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/dependency-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/design-standards/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/design-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/discovery-research-synthesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/dispatch-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/documentation-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/domain-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/editorial-qa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/email-deliverability/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/email-sequences/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/evidence-based-reviews/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/experiment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/experimentation-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/experimentation-platform-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/feature-flagging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/feature-launch-playbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/form-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/frontend-component-build/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/funnel-flow-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/incident-response/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/information-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/integration-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/interactive-product-tour/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/internationalization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/journey-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/jtbd-framing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/landing-page-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/launch-runbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/lead-magnet-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/logo-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/long-form-content-frameworks/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/media-asset-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/monitoring-and-alerting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/multi-step-form-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/okr-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/onboarding-wizard-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/oss-contribution-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/paid-media-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/performance-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/pillar-content-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/pm-spec-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/product-analytics-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/product-configurator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/programmatic-seo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/qa-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/quiz-and-assessment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/roadmap-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/scheduler-and-booking-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/security-baseline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-aeo-geo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-audit-orchestration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-backlink-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-competitor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-content-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-content-gap-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-keyword/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-keyword-gap-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-offpage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-onpage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-rank-tracking/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-site-health-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-technical/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/seo-traffic-diagnosis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/skill-creation-walkthrough/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/sprint-operations/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/stakeholder-communication/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/team-onboarding-playbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/ticket-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/upgrade-flow-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/usability-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/user-feedback-aggregation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/ux-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/vendor-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/codex/.agents/skills/vertical-site-conventions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/accessibility-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/ads-creative-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/ads-performance-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/after-action-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/ai-content-collaboration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/analytics-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/art-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/backup-and-disaster-recovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/beta-program-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-archetype-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-ideation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-identity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-style-guide/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/brand-voice/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/calculator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/chatbot-flow-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/code-review-web/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/comparison-tool-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/competitor-experience-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-and-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-brief-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-distribution/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-migration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-refresh-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-repurposing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/content-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/cost-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/creative-brief/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/creative-brief-selector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/creative-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/cro-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/data-warehouse-experimentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/dependency-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/design-standards/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/design-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/discovery-research-synthesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/dispatch-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/documentation-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/domain-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/editorial-qa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/email-deliverability/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/email-sequences/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/evidence-based-reviews/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/experiment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/experimentation-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/experimentation-platform-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/feature-flagging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/feature-launch-playbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/form-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/frontend-component-build/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/funnel-flow-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/incident-response/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/information-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/integration-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/interactive-product-tour/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/internationalization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/journey-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/jtbd-framing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/landing-page-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/launch-runbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/lead-magnet-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/logo-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/long-form-content-frameworks/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/media-asset-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/monitoring-and-alerting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/multi-step-form-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/okr-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/onboarding-wizard-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/oss-contribution-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/paid-media-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/performance-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/pillar-content-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/pm-spec-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/product-analytics-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/product-configurator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/programmatic-seo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/qa-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/quiz-and-assessment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/roadmap-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/scheduler-and-booking-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/security-baseline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-aeo-geo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-audit-orchestration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-backlink-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-competitor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-content-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-content-gap-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-keyword/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-keyword-gap-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-offpage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-onpage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-rank-tracking/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-site-health-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-technical/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/seo-traffic-diagnosis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/skill-creation-walkthrough/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/sprint-operations/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/stakeholder-communication/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/team-onboarding-playbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/ticket-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/upgrade-flow-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/usability-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/user-feedback-aggregation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/ux-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/vendor-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
dist/pi/.agents/skills/vertical-site-conventions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/accessibility-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/ads-creative-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/ads-performance-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/after-action-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/ai-content-collaboration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/analytics-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/art-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/backup-and-disaster-recovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/beta-program-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-archetype-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-ideation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-identity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-style-guide/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/brand-voice/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/calculator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/chatbot-flow-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/code-review-web/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/comparison-tool-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/competitor-experience-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-and-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-brief-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-distribution/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-migration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-refresh-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-repurposing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/content-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/cost-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/creative-brief/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/creative-brief-selector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/creative-direction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/cro-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/data-warehouse-experimentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/dependency-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/design-standards/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/design-system/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/discovery-research-synthesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/dispatch-authoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/documentation-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/domain-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/editorial-qa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/email-deliverability/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/email-sequences/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/evidence-based-reviews/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/experiment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/experimentation-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/experimentation-platform-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/feature-flagging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/feature-launch-playbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/form-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/frontend-component-build/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/funnel-flow-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/incident-response/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/information-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/integration-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/interactive-product-tour/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/internationalization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/journey-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/jtbd-framing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/landing-page-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/launch-runbook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/lead-magnet-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/logo-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/long-form-content-frameworks/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/media-asset-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/monitoring-and-alerting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/multi-step-form-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/okr-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/onboarding-wizard-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/oss-contribution-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/paid-media-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/performance-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/pillar-content-architecture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/pm-spec-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/product-analytics-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/product-configurator-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/programmatic-seo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/qa-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/quiz-and-assessment-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/roadmap-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/scheduler-and-booking-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/security-baseline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/seo-aeo-geo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/seo-audit-orchestration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/seo-backlink-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
skills/seo-competitor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9b90db257f73 → 9b90db257f73
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9b90db257f73
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 9b90db257f7395fab76ff9bfcb808456709f6af3
git clone --filter=blob:none --no-checkout https://github.com/rampstackco/claude-skills.git .hotskills/rampstackco-claude-skills && git -C .hotskills/rampstackco-claude-skills checkout --detach 9b90db257f7395fab76ff9bfcb808456709f6af3
# Copy each selected skill directory from .hotskills/rampstackco-claude-skills into .claude/skills/<skill-name>/1kGitHub stars
27stars in 7 days
321skills in this repository
5commits in 30 days
Heat
6.4- Star growth, last 7 daysAhead of 93% of tracked repositories
- Star growth, last 24 hoursAhead of 70% of tracked repositories
- Rank movement, last 7 daysAhead of 38% of tracked repositories
- Commits, last 30 daysAhead of 70% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- accessibility-audit
dist/codex/.agents/skills/accessibility-audit - ads-creative-development
dist/codex/.agents/skills/ads-creative-development - ads-performance-analytics
dist/codex/.agents/skills/ads-performance-analytics - after-action-report
dist/codex/.agents/skills/after-action-report - ai-content-collaboration
dist/codex/.agents/skills/ai-content-collaboration - analytics-strategy
dist/codex/.agents/skills/analytics-strategy - art-direction
dist/codex/.agents/skills/art-direction - backup-and-disaster-recovery
dist/codex/.agents/skills/backup-and-disaster-recovery - beta-program-management
dist/codex/.agents/skills/beta-program-management - brand-archetype-system
dist/codex/.agents/skills/brand-archetype-system - brand-discovery
dist/codex/.agents/skills/brand-discovery - brand-ideation
dist/codex/.agents/skills/brand-ideation - brand-identity
dist/codex/.agents/skills/brand-identity - brand-style-guide
dist/codex/.agents/skills/brand-style-guide - brand-voice
dist/codex/.agents/skills/brand-voice - calculator-design
dist/codex/.agents/skills/calculator-design - chatbot-flow-design
dist/codex/.agents/skills/chatbot-flow-design - code-review-web
dist/codex/.agents/skills/code-review-web - comparison-tool-design
dist/codex/.agents/skills/comparison-tool-design - competitor-experience-audit
dist/codex/.agents/skills/competitor-experience-audit - content-and-copy
dist/codex/.agents/skills/content-and-copy - content-brief-authoring
dist/codex/.agents/skills/content-brief-authoring - content-distribution
dist/codex/.agents/skills/content-distribution - content-migration
dist/codex/.agents/skills/content-migration - content-refresh-system
dist/codex/.agents/skills/content-refresh-system - content-repurposing
dist/codex/.agents/skills/content-repurposing - content-strategy
dist/codex/.agents/skills/content-strategy - cost-optimization
dist/codex/.agents/skills/cost-optimization - creative-brief
dist/codex/.agents/skills/creative-brief - creative-brief-selector
dist/codex/.agents/skills/creative-brief-selector - creative-direction
dist/codex/.agents/skills/creative-direction - cro-optimization
dist/codex/.agents/skills/cro-optimization - data-warehouse-experimentation
dist/codex/.agents/skills/data-warehouse-experimentation - dependency-management
dist/codex/.agents/skills/dependency-management - design-standards
dist/codex/.agents/skills/design-standards - design-system
dist/codex/.agents/skills/design-system - discovery-research-synthesis
dist/codex/.agents/skills/discovery-research-synthesis - dispatch-authoring
dist/codex/.agents/skills/dispatch-authoring - documentation-strategy
dist/codex/.agents/skills/documentation-strategy - domain-strategy
dist/codex/.agents/skills/domain-strategy - editorial-qa
dist/codex/.agents/skills/editorial-qa - email-deliverability
dist/codex/.agents/skills/email-deliverability - email-sequences
dist/codex/.agents/skills/email-sequences - evidence-based-reviews
dist/codex/.agents/skills/evidence-based-reviews - experiment-design
dist/codex/.agents/skills/experiment-design - experimentation-analytics
dist/codex/.agents/skills/experimentation-analytics - experimentation-platform-orchestrator
dist/codex/.agents/skills/experimentation-platform-orchestrator - feature-flagging
dist/codex/.agents/skills/feature-flagging - feature-launch-playbook
dist/codex/.agents/skills/feature-launch-playbook - form-strategy
dist/codex/.agents/skills/form-strategy - frontend-component-build
dist/codex/.agents/skills/frontend-component-build - funnel-flow-architecture
dist/codex/.agents/skills/funnel-flow-architecture - incident-response
dist/codex/.agents/skills/incident-response - information-architecture
dist/codex/.agents/skills/information-architecture - integration-orchestrator
dist/codex/.agents/skills/integration-orchestrator - interactive-product-tour
dist/codex/.agents/skills/interactive-product-tour - internationalization
dist/codex/.agents/skills/internationalization - journey-mapping
dist/codex/.agents/skills/journey-mapping - jtbd-framing
dist/codex/.agents/skills/jtbd-framing - landing-page-copy
dist/codex/.agents/skills/landing-page-copy - launch-runbook
dist/codex/.agents/skills/launch-runbook - lead-magnet-design
dist/codex/.agents/skills/lead-magnet-design - logo-design
dist/codex/.agents/skills/logo-design - long-form-content-frameworks
dist/codex/.agents/skills/long-form-content-frameworks - media-asset-management
dist/codex/.agents/skills/media-asset-management - monitoring-and-alerting
dist/codex/.agents/skills/monitoring-and-alerting - multi-step-form-design
dist/codex/.agents/skills/multi-step-form-design - okr-design
dist/codex/.agents/skills/okr-design - onboarding-wizard-design
dist/codex/.agents/skills/onboarding-wizard-design - oss-contribution-research
dist/codex/.agents/skills/oss-contribution-research - paid-media-strategy
dist/codex/.agents/skills/paid-media-strategy - performance-optimization
dist/codex/.agents/skills/performance-optimization - pillar-content-architecture
dist/codex/.agents/skills/pillar-content-architecture - pm-spec-writing
dist/codex/.agents/skills/pm-spec-writing - product-analytics-setup
dist/codex/.agents/skills/product-analytics-setup - product-configurator-design
dist/codex/.agents/skills/product-configurator-design - programmatic-seo
dist/codex/.agents/skills/programmatic-seo - qa-testing
dist/codex/.agents/skills/qa-testing - quiz-and-assessment-design
dist/codex/.agents/skills/quiz-and-assessment-design - roadmap-planning
dist/codex/.agents/skills/roadmap-planning - scheduler-and-booking-design
dist/codex/.agents/skills/scheduler-and-booking-design - security-baseline
dist/codex/.agents/skills/security-baseline - seo-aeo-geo
dist/codex/.agents/skills/seo-aeo-geo - seo-audit-orchestration
dist/codex/.agents/skills/seo-audit-orchestration - seo-backlink-audit
dist/codex/.agents/skills/seo-backlink-audit - seo-competitor
dist/codex/.agents/skills/seo-competitor - seo-content-audit
dist/codex/.agents/skills/seo-content-audit - seo-content-gap-audit
dist/codex/.agents/skills/seo-content-gap-audit - seo-keyword
dist/codex/.agents/skills/seo-keyword - seo-keyword-gap-audit
dist/codex/.agents/skills/seo-keyword-gap-audit - seo-offpage
dist/codex/.agents/skills/seo-offpage - seo-onpage
dist/codex/.agents/skills/seo-onpage - seo-rank-tracking
dist/codex/.agents/skills/seo-rank-tracking - seo-site-health-audit
dist/codex/.agents/skills/seo-site-health-audit - seo-technical
dist/codex/.agents/skills/seo-technical - seo-traffic-diagnosis
dist/codex/.agents/skills/seo-traffic-diagnosis - skill-creation-walkthrough
dist/codex/.agents/skills/skill-creation-walkthrough - sprint-operations
dist/codex/.agents/skills/sprint-operations - stakeholder-communication
dist/codex/.agents/skills/stakeholder-communication - team-onboarding-playbook
dist/codex/.agents/skills/team-onboarding-playbook - ticket-authoring
dist/codex/.agents/skills/ticket-authoring - upgrade-flow-design
dist/codex/.agents/skills/upgrade-flow-design - usability-testing
dist/codex/.agents/skills/usability-testing - user-feedback-aggregation
dist/codex/.agents/skills/user-feedback-aggregation - ux-research
dist/codex/.agents/skills/ux-research - vendor-evaluation
dist/codex/.agents/skills/vendor-evaluation - vertical-site-conventions
dist/codex/.agents/skills/vertical-site-conventions - accessibility-audit
dist/pi/.agents/skills/accessibility-audit - ads-creative-development
dist/pi/.agents/skills/ads-creative-development - ads-performance-analytics
dist/pi/.agents/skills/ads-performance-analytics - after-action-report
dist/pi/.agents/skills/after-action-report - ai-content-collaboration
dist/pi/.agents/skills/ai-content-collaboration - analytics-strategy
dist/pi/.agents/skills/analytics-strategy - art-direction
dist/pi/.agents/skills/art-direction - backup-and-disaster-recovery
dist/pi/.agents/skills/backup-and-disaster-recovery - beta-program-management
dist/pi/.agents/skills/beta-program-management - brand-archetype-system
dist/pi/.agents/skills/brand-archetype-system - brand-discovery
dist/pi/.agents/skills/brand-discovery - brand-ideation
dist/pi/.agents/skills/brand-ideation - brand-identity
dist/pi/.agents/skills/brand-identity - brand-style-guide
dist/pi/.agents/skills/brand-style-guide - brand-voice
dist/pi/.agents/skills/brand-voice - calculator-design
dist/pi/.agents/skills/calculator-design - chatbot-flow-design
dist/pi/.agents/skills/chatbot-flow-design - code-review-web
dist/pi/.agents/skills/code-review-web - comparison-tool-design
dist/pi/.agents/skills/comparison-tool-design - competitor-experience-audit
dist/pi/.agents/skills/competitor-experience-audit - content-and-copy
dist/pi/.agents/skills/content-and-copy - content-brief-authoring
dist/pi/.agents/skills/content-brief-authoring - content-distribution
dist/pi/.agents/skills/content-distribution - content-migration
dist/pi/.agents/skills/content-migration - content-refresh-system
dist/pi/.agents/skills/content-refresh-system - content-repurposing
dist/pi/.agents/skills/content-repurposing - content-strategy
dist/pi/.agents/skills/content-strategy - cost-optimization
dist/pi/.agents/skills/cost-optimization - creative-brief
dist/pi/.agents/skills/creative-brief - creative-brief-selector
dist/pi/.agents/skills/creative-brief-selector - creative-direction
dist/pi/.agents/skills/creative-direction - cro-optimization
dist/pi/.agents/skills/cro-optimization - data-warehouse-experimentation
dist/pi/.agents/skills/data-warehouse-experimentation - dependency-management
dist/pi/.agents/skills/dependency-management - design-standards
dist/pi/.agents/skills/design-standards - design-system
dist/pi/.agents/skills/design-system - discovery-research-synthesis
dist/pi/.agents/skills/discovery-research-synthesis - dispatch-authoring
dist/pi/.agents/skills/dispatch-authoring - documentation-strategy
dist/pi/.agents/skills/documentation-strategy - domain-strategy
dist/pi/.agents/skills/domain-strategy - editorial-qa
dist/pi/.agents/skills/editorial-qa - email-deliverability
dist/pi/.agents/skills/email-deliverability - email-sequences
dist/pi/.agents/skills/email-sequences - evidence-based-reviews
dist/pi/.agents/skills/evidence-based-reviews - experiment-design
dist/pi/.agents/skills/experiment-design - experimentation-analytics
dist/pi/.agents/skills/experimentation-analytics - experimentation-platform-orchestrator
dist/pi/.agents/skills/experimentation-platform-orchestrator - feature-flagging
dist/pi/.agents/skills/feature-flagging - feature-launch-playbook
dist/pi/.agents/skills/feature-launch-playbook - form-strategy
dist/pi/.agents/skills/form-strategy - frontend-component-build
dist/pi/.agents/skills/frontend-component-build - funnel-flow-architecture
dist/pi/.agents/skills/funnel-flow-architecture - incident-response
dist/pi/.agents/skills/incident-response - information-architecture
dist/pi/.agents/skills/information-architecture - integration-orchestrator
dist/pi/.agents/skills/integration-orchestrator - interactive-product-tour
dist/pi/.agents/skills/interactive-product-tour - internationalization
dist/pi/.agents/skills/internationalization - journey-mapping
dist/pi/.agents/skills/journey-mapping - jtbd-framing
dist/pi/.agents/skills/jtbd-framing - landing-page-copy
dist/pi/.agents/skills/landing-page-copy - launch-runbook
dist/pi/.agents/skills/launch-runbook - lead-magnet-design
dist/pi/.agents/skills/lead-magnet-design - logo-design
dist/pi/.agents/skills/logo-design - long-form-content-frameworks
dist/pi/.agents/skills/long-form-content-frameworks - media-asset-management
dist/pi/.agents/skills/media-asset-management - monitoring-and-alerting
dist/pi/.agents/skills/monitoring-and-alerting - multi-step-form-design
dist/pi/.agents/skills/multi-step-form-design - okr-design
dist/pi/.agents/skills/okr-design - onboarding-wizard-design
dist/pi/.agents/skills/onboarding-wizard-design - oss-contribution-research
dist/pi/.agents/skills/oss-contribution-research - paid-media-strategy
dist/pi/.agents/skills/paid-media-strategy - performance-optimization
dist/pi/.agents/skills/performance-optimization - pillar-content-architecture
dist/pi/.agents/skills/pillar-content-architecture - pm-spec-writing
dist/pi/.agents/skills/pm-spec-writing - product-analytics-setup
dist/pi/.agents/skills/product-analytics-setup - product-configurator-design
dist/pi/.agents/skills/product-configurator-design - programmatic-seo
dist/pi/.agents/skills/programmatic-seo - qa-testing
dist/pi/.agents/skills/qa-testing - quiz-and-assessment-design
dist/pi/.agents/skills/quiz-and-assessment-design - roadmap-planning
dist/pi/.agents/skills/roadmap-planning - scheduler-and-booking-design
dist/pi/.agents/skills/scheduler-and-booking-design - security-baseline
dist/pi/.agents/skills/security-baseline - seo-aeo-geo
dist/pi/.agents/skills/seo-aeo-geo - seo-audit-orchestration
dist/pi/.agents/skills/seo-audit-orchestration - seo-backlink-audit
dist/pi/.agents/skills/seo-backlink-audit - seo-competitor
dist/pi/.agents/skills/seo-competitor - seo-content-audit
dist/pi/.agents/skills/seo-content-audit - seo-content-gap-audit
dist/pi/.agents/skills/seo-content-gap-audit - seo-keyword
dist/pi/.agents/skills/seo-keyword - seo-keyword-gap-audit
dist/pi/.agents/skills/seo-keyword-gap-audit - seo-offpage
dist/pi/.agents/skills/seo-offpage - seo-onpage
dist/pi/.agents/skills/seo-onpage - seo-rank-tracking
dist/pi/.agents/skills/seo-rank-tracking - seo-site-health-audit
dist/pi/.agents/skills/seo-site-health-audit - seo-technical
dist/pi/.agents/skills/seo-technical - seo-traffic-diagnosis
dist/pi/.agents/skills/seo-traffic-diagnosis - skill-creation-walkthrough
dist/pi/.agents/skills/skill-creation-walkthrough - sprint-operations
dist/pi/.agents/skills/sprint-operations - stakeholder-communication
dist/pi/.agents/skills/stakeholder-communication - team-onboarding-playbook
dist/pi/.agents/skills/team-onboarding-playbook - ticket-authoring
dist/pi/.agents/skills/ticket-authoring - upgrade-flow-design
dist/pi/.agents/skills/upgrade-flow-design - usability-testing
dist/pi/.agents/skills/usability-testing - user-feedback-aggregation
dist/pi/.agents/skills/user-feedback-aggregation - ux-research
dist/pi/.agents/skills/ux-research - vendor-evaluation
dist/pi/.agents/skills/vendor-evaluation - vertical-site-conventions
dist/pi/.agents/skills/vertical-site-conventions - accessibility-audit
skills/accessibility-audit - ads-creative-development
skills/ads-creative-development - ads-performance-analytics
skills/ads-performance-analytics - after-action-report
skills/after-action-report - ai-content-collaboration
skills/ai-content-collaboration - analytics-strategy
skills/analytics-strategy - art-direction
skills/art-direction - backup-and-disaster-recovery
skills/backup-and-disaster-recovery - beta-program-management
skills/beta-program-management - brand-archetype-system
skills/brand-archetype-system - brand-discovery
skills/brand-discovery - brand-ideation
skills/brand-ideation - brand-identity
skills/brand-identity - brand-style-guide
skills/brand-style-guide - brand-voice
skills/brand-voice - calculator-design
skills/calculator-design - chatbot-flow-design
skills/chatbot-flow-design - code-review-web
skills/code-review-web - comparison-tool-design
skills/comparison-tool-design - competitor-experience-audit
skills/competitor-experience-audit - content-and-copy
skills/content-and-copy - content-brief-authoring
skills/content-brief-authoring - content-distribution
skills/content-distribution - content-migration
skills/content-migration - content-refresh-system
skills/content-refresh-system - content-repurposing
skills/content-repurposing - content-strategy
skills/content-strategy - cost-optimization
skills/cost-optimization - creative-brief
skills/creative-brief - creative-brief-selector
skills/creative-brief-selector - creative-direction
skills/creative-direction - cro-optimization
skills/cro-optimization - data-warehouse-experimentation
skills/data-warehouse-experimentation - dependency-management
skills/dependency-management - design-standards
skills/design-standards - design-system
skills/design-system - discovery-research-synthesis
skills/discovery-research-synthesis - dispatch-authoring
skills/dispatch-authoring - documentation-strategy
skills/documentation-strategy - domain-strategy
skills/domain-strategy - editorial-qa
skills/editorial-qa - email-deliverability
skills/email-deliverability - email-sequences
skills/email-sequences - evidence-based-reviews
skills/evidence-based-reviews - experiment-design
skills/experiment-design - experimentation-analytics
skills/experimentation-analytics - experimentation-platform-orchestrator
skills/experimentation-platform-orchestrator - feature-flagging
skills/feature-flagging - feature-launch-playbook
skills/feature-launch-playbook - form-strategy
skills/form-strategy - frontend-component-build
skills/frontend-component-build - funnel-flow-architecture
skills/funnel-flow-architecture - incident-response
skills/incident-response - information-architecture
skills/information-architecture - integration-orchestrator
skills/integration-orchestrator - interactive-product-tour
skills/interactive-product-tour - internationalization
skills/internationalization - journey-mapping
skills/journey-mapping - jtbd-framing
skills/jtbd-framing - landing-page-copy
skills/landing-page-copy - launch-runbook
skills/launch-runbook - lead-magnet-design
skills/lead-magnet-design - logo-design
skills/logo-design - long-form-content-frameworks
skills/long-form-content-frameworks - media-asset-management
skills/media-asset-management - monitoring-and-alerting
skills/monitoring-and-alerting - multi-step-form-design
skills/multi-step-form-design - okr-design
skills/okr-design - onboarding-wizard-design
skills/onboarding-wizard-design - oss-contribution-research
skills/oss-contribution-research - paid-media-strategy
skills/paid-media-strategy - performance-optimization
skills/performance-optimization - pillar-content-architecture
skills/pillar-content-architecture - pm-spec-writing
skills/pm-spec-writing - product-analytics-setup
skills/product-analytics-setup - product-configurator-design
skills/product-configurator-design - programmatic-seo
skills/programmatic-seo - qa-testing
skills/qa-testing - quiz-and-assessment-design
skills/quiz-and-assessment-design - roadmap-planning
skills/roadmap-planning - scheduler-and-booking-design
skills/scheduler-and-booking-design - security-baseline
skills/security-baseline - seo-aeo-geo
skills/seo-aeo-geo - seo-audit-orchestration
skills/seo-audit-orchestration - seo-backlink-audit
skills/seo-backlink-audit - seo-competitor
skills/seo-competitor - seo-content-audit
skills/seo-content-audit - seo-content-gap-audit
skills/seo-content-gap-audit - seo-keyword
skills/seo-keyword - seo-keyword-gap-audit
skills/seo-keyword-gap-audit - seo-offpage
skills/seo-offpage - seo-onpage
skills/seo-onpage - seo-rank-tracking
skills/seo-rank-tracking - seo-site-health-audit
skills/seo-site-health-audit - seo-technical
skills/seo-technical - seo-traffic-diagnosis
skills/seo-traffic-diagnosis - skill-creation-walkthrough
skills/skill-creation-walkthrough - sprint-operations
skills/sprint-operations - stakeholder-communication
skills/stakeholder-communication - team-onboarding-playbook
skills/team-onboarding-playbook - ticket-authoring
skills/ticket-authoring - upgrade-flow-design
skills/upgrade-flow-design - usability-testing
skills/usability-testing - user-feedback-aggregation
skills/user-feedback-aggregation - ux-research
skills/ux-research - vendor-evaluation
skills/vendor-evaluation - vertical-site-conventions
skills/vertical-site-conventions
How it works
accessibility-audit
When your agent uses it
Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
2,419 tokensWhen the skill is activated
Reference documents
8,000 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: WCAG's 4 principles
- Audit methodology
- Workflow
- Severity classification
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
../../../../../.claude-plugin/marketplace.jsonasset1,680 bytes../../../../../.claude-plugin/plugin.jsonasset433 bytesSKILL.mdcore11,354 bytesSKILL.mdcore11,354 bytesSKILL.mdcore11,354 bytesreferences/_claude-frontmatter-extras.yamlasset381 bytesreferences/aria-patterns.mddoc18,175 bytesreferences/audit-report-template.mddoc5,175 bytesreferences/wcag-quick-reference.mddoc8,655 bytes
Read SKILL.md
# Accessibility Audit
Run a thorough accessibility audit and produce a remediation plan. Stack-agnostic. Anchored to WCAG 2.1 AA, with notes on AAA where relevant.
This skill goes deeper than the accessibility checks in `qa-testing` and `design-standards`. Use this when accessibility itself is the goal.
---
## When to use
- Pre-launch accessibility verification
- Compliance preparation (ADA, EN 301 549, AODA, Section 508)
- Remediation after an audit finding or complaint
- Annual or quarterly accessibility health checkads-creative-development
When your agent uses it
How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
4,483 tokensWhen the skill is activated
Reference documents
9,865 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Performance vs brand creative
- Hook patterns: the first 3 seconds
- Format selection
- Video pacing
- Variation systems
- Sequential testing methodology
- Creative fatigue detection
- Brand-voice alignment without conversion dilution
- Platform-specific creative norms
- Common failures
- The framework: 10 considerations for sustainable creative production
- Reference files
- Closing: the hook is the whole game
Files
SKILL.mdcore21,107 bytesreferences/_claude-frontmatter-extras.yamlasset518 bytesreferences/brand-voice-performance-balance.mddoc7,397 bytesreferences/creative-variation-templates.mddoc5,621 bytesreferences/fatigue-detection-checklist.mddoc6,431 bytesreferences/format-decision-matrix.mddoc4,791 bytesreferences/hook-pattern-library.mddoc7,100 bytesreferences/platform-creative-norms.mddoc6,827 bytesreferences/testing-cadence-playbook.mddoc6,034 bytes
Read SKILL.md
# Ads Creative Development
A senior creative strategist's playbook for producing ad creative that performs.
Performance creative is a different discipline from brand creative. Brand work optimizes for memorability, emotional resonance, and distinctive identity. Performance creative optimizes for stopping the scroll, communicating value in three seconds, and producing a click. Both matter. Mixing them up costs money. Brand creative running as performance ads bleeds budget; performance creative running as brand ads erodes equity.
This skill is the discipline that produces performance creative without diluting brand. It assumes you know your audience and offer (see `paid-media-strategy`). It assumes you have brand-voice guidance (see `brand-voice`). The hard part is the systematic production of variations that test cleanly and ship without manual approval bottlenecks, and that is what is here.
When to use this skill: producing ad creative for paid campaigns, planning a creative testing cycle, diagnosing creative fatigue, or auditing why creative is not converting.
---
## What this skill is for
ads-performance-analytics
When your agent uses it
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
5,078 tokensWhen the skill is activated
Reference documents
11,524 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every paid media platform should expose
- Platform-reported vs reality
- Attribution models in practice
- Multi-platform reconciliation
- ROAS vs LTV: the time horizon trap
- Cohort analysis vs daily metrics
- Statistical noise in performance metrics
- Incrementality testing
- Geo experiments and holdouts
- Platform self-attribution bias
- Common interpretation failures
- The framework: 12 considerations for trustworthy paid media interpretation
- If required data is unavailable
- Reference files
- Closing: the courage to call it incremental zero
Files
SKILL.mdcore24,481 bytesSKILL.mdcore24,481 bytesSKILL.mdcore24,481 bytesSKILL.mdcore24,481 bytesreferences/_claude-frontmatter-extras.yamlasset574 bytesreferences/attribution-model-comparison.mddoc7,456 bytesreferences/cohort-analysis-templates.mddoc6,603 bytesreferences/common-interpretation-failures.mddoc9,164 bytesreferences/dashboard-reconciliation-patterns.mddoc6,692 bytesreferences/incrementality-testing-playbook.mddoc7,127 bytesreferences/metric-definitions-glossary.mddoc6,677 bytesreferences/platform-reporting-quirks.mddoc8,963 bytes
Read SKILL.md
# Ads Performance Analytics
A data-team-mentor's playbook for interpreting paid media dashboards without fooling yourself.
The dashboard is the moment of truth for paid media decisions. The numbers on it determine whether you scale, hold, or kill. They also expose every platform's self-attribution bias, every modeled-conversion shortcut, every cross-platform double-count. Most "scale this campaign" decisions trace back to misreading the dashboard.
This skill is the discipline that prevents misreading. It assumes the campaign was strategically sound (see `paid-media-strategy`). It assumes the creative was tested properly (see `ads-creative-development`). The hard part is knowing what each number actually means, what it does not, and how to reconcile platform-reported metrics with the truth in your warehouse.
When to use this skill: any time you are about to scale, kill, or rebudget a campaign based on platform metrics; reconciling platform reports with revenue data; evaluating an agency's reporting; or building a paid media dashboard that will not lie to you.
---
## What this skill is for
after-action-report
When your agent uses it
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
2,206 tokensWhen the skill is activated
Reference documents
2,122 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: blameless analysis
- The framework: 6 sections
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesreferences/_claude-frontmatter-extras.yamlasset382 bytesreferences/aar-template.mddoc8,344 bytes
Read SKILL.md
# After-Action Report
Run a structured retrospective on a launch, incident, or completed project. Produce actionable lessons, not just a document.
This skill is for after-the-fact analysis. For active incident response, use `incident-response`. For planning launches, use `launch-runbook`.
---
## When to use
- After any incident (any severity)
- After every major launch
- At the end of a project (sprint retro, quarterly retro, project closeout)
- When a recurring issue has happened enough times to demand investigationai-content-collaboration
When your agent uses it
How humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
4,584 tokensWhen the skill is activated
Reference documents
16,129 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Humans own, AI accelerates
- Where AI legitimately participates
- Where humans must own
- Hybrid workflow patterns
- Voice ownership preservation
- The AI slop problem
- Disclosure and transparency
- Team training and calibration
- Ethics: training data, attribution, intellectual honesty
- Common failure modes
- The framework: 12 considerations for AI content collaboration
- Reference files
- Closing: collaboration, not replacement
Files
SKILL.mdcore22,307 bytesSKILL.mdcore22,307 bytesSKILL.mdcore22,307 bytesreferences/_claude-frontmatter-extras.yamlasset562 bytesreferences/ai-participation-boundaries.mddoc7,481 bytesreferences/ai-slop-detection-and-avoidance.mddoc8,587 bytesreferences/common-collaboration-failures.mddoc10,479 bytesreferences/disclosure-and-transparency-patterns.mddoc9,437 bytesreferences/ethics-and-intellectual-honesty.mddoc10,412 bytesreferences/hybrid-workflow-patterns.mddoc8,302 bytesreferences/quality-calibration-with-ai-in-loop.mddoc9,077 bytesreferences/team-training-and-calibration.mddoc8,499 bytesreferences/voice-ownership-preservation.mddoc8,373 bytes
Read SKILL.md
# AI Content Collaboration
A senior editorial leader's playbook for how humans and AI compose in content workflows. Pragmatic, tool-agnostic, honest about both what AI in the loop enables and what it threatens.
Most content programs in 2026 use AI somewhere in the workflow. Pretending otherwise is dishonest; treating AI as a magic content factory is the failure mode this skill exists to prevent. The discipline is in between: knowing where AI legitimately accelerates, where humans must own, what hybrid patterns produce work that earns reader trust, and what crosses the line into AI slop or intellectual dishonesty.
This skill is the WORKFLOW layer that composes with every other content skill. Briefs can be AI-assisted; hub architectures can be AI-assisted; programmatic SEO is almost always AI-involved; editorial QA now includes AI-content audit by necessity. The collaboration discipline applies to all production stages, not to a single artifact type.
The voice is pragmatic and tool-agnostic deliberately. The methodology applies whether the AI in your loop is one of the major commercial models, an open-source model, or whatever ships next quarter. What stays constant is the workflow shape, the participation boundaries, the voice ownership question, and the ethical frame. What changes is which specific tool you reach for, which is implementation work that varies by team and budget.
When to use this skill: building or refining an AI-content workflow, calibrating a team on consistent AI usage, addressing the "we use AI but our work feels generic" problem, designing disclosure policies, or working through the ethics of AI-assisted content production for a regulated or trust-sensitive context.
---
analytics-strategy
When your agent uses it
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement. Triggers on analytics strategy, measurement plan, event taxonomy, tracking plan, KPI framework, dashboard design, north star metric, attribution model, conversion tracking, GA4 setup, Mixpanel setup, analytics audit. Also triggers when the user has data but no clear way to use it, or wants to make decisions but doesn't know what to track.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
2,010 tokensWhen the skill is activated
Reference documents
2,292 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- The tracking plan document
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,360 bytesreferences/_claude-frontmatter-extras.yamlasset388 bytesreferences/event-taxonomy-template.mddoc9,896 bytes
Read SKILL.md
# Analytics Strategy
Design measurement frameworks that produce decisions, not just dashboards. Stack-agnostic. Tool-agnostic.
This skill is for measurement planning. For conversion optimization, use `cro-optimization`. For SEO measurement specifically, use `seo-onpage` and adjacent SEO skills.
---
## When to use
- Setting up analytics on a new product or site
- Auditing existing analytics setup
- Designing dashboards for a team or business
- Defining KPIs and a north star metricart-direction
When your agent uses it
Direct visual and creative work for campaigns, photography, illustration, video, and branded experiences. Use this skill whenever the user wants to brief a photographer, direct illustrators, plan a creative campaign, develop visual concepts, or evaluate creative work for fit. Triggers on art direction, photo brief, photography brief, illustration brief, campaign concept, creative concept, visual direction, mood board, look and feel, visual treatment, video direction. Also triggers when the user has approved brand identity but needs to extend it into specific creative deliverables. Use `creative-direction` instead when the ask is the project-wide aesthetic brief that this skill consumes as input.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
2,035 tokensWhen the skill is activated
Reference documents
5,011 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,496 bytesreferences/_claude-frontmatter-extras.yamlasset388 bytesreferences/creative-brief-template.mddoc6,077 bytesreferences/illustration-brief.mddoc7,946 bytesreferences/photo-shoot-brief.mddoc6,424 bytes
Read SKILL.md
# Art Direction
Direct creative work that extends the brand into specific deliverables. Photography, illustration, video, motion, campaigns, environmental design.
This skill assumes brand identity is approved (`brand-identity` complete). Art direction is about applying and extending it, not defining it.
---
## When to use
- Briefing photographers, illustrators, videographers
- Developing campaign creative concepts
- Directing in-house creative teams
- Writing creative direction documents for vendorsbackup-and-disaster-recovery
When your agent uses it
Plan and run backups, set recovery objectives, and run disaster recovery drills. Use this skill when defining RPO/RTO targets, designing backup architecture, deciding what to back up and how often, planning for full-region or platform outages, or running a restoration drill. Triggers on backup, restore, RPO, RTO, disaster recovery, DR, business continuity, what if the database is gone, what if our hosting goes down, recovery drill, ransomware planning. Also triggers when an incident reveals a gap in restoration capability.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
2,380 tokensWhen the skill is activated
Reference documents
1,338 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 questions
- Workflow
- Special topics
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,760 bytesSKILL.mdcore10,760 bytesreferences/_claude-frontmatter-extras.yamlasset398 bytesreferences/restore-runbook-template.mddoc5,525 bytes
Read SKILL.md
# Backup and Disaster Recovery
Plan for the worst case: the database is gone, the host is down for a week, the deploy was poisoned, ransomware encrypted everything. The skill is in advance preparation, not reaction.
---
## When to use
- Setting up backups for a new system
- Reviewing and validating backup architecture
- Defining RPO (recovery point objective) and RTO (recovery time objective)
- Running a disaster recovery drill
- Diagnosing gaps after an incident
- Planning for ransomware, data corruption, or insider threatsbeta-program-management
When your agent uses it
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria). Triggers on beta program, alpha test, beta cohort, beta participant, beta feedback, beta to GA decision, design partner, early access program, closed beta, open beta, RC release. Also triggers when a feature is approaching launch and the team needs structured pre-GA validation, when prior betas produced noise rather than signal, or when the team has soft-launched before but wants more structured feedback this time.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
4,878 tokensWhen the skill is activated
Reference documents
18,246 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Soft-launch vs kitchen-sink vs structured-beta
- Beta type decisions
- Participant selection criteria
- Beta cohort sizing
- Onboarding beta participants
- Feedback collection patterns
- Mid-beta triage and iteration
- Beta-to-GA decision criteria
- Beta wind-down and participant communication
- Common failure modes
- The framework: 12 considerations for beta program management
- If required data is unavailable
- Reference files
- Closing: betas earn their keep with structure
Files
SKILL.mdcore24,147 bytesSKILL.mdcore24,147 bytesreferences/_claude-frontmatter-extras.yamlasset590 bytesreferences/beta-onboarding-templates.mddoc10,602 bytesreferences/beta-to-ga-graduation-criteria.mddoc11,663 bytesreferences/beta-type-decisions.mddoc10,326 bytesreferences/beta-wind-down-communication.mddoc9,512 bytesreferences/cohort-sizing-patterns.mddoc8,928 bytesreferences/common-beta-failures.mddoc10,373 bytesreferences/feedback-collection-patterns.mddoc10,916 bytesreferences/mid-beta-triage-and-iteration.mddoc9,669 bytesreferences/participant-selection-criteria.mddoc10,154 bytes
Read SKILL.md
# Beta Program Management
A senior product leader's playbook for running betas that produce real signal. Closed and open betas, alpha programs, design partner programs, early access. Participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria).
Most betas underperform. Teams ship a beta because they think they should run a beta; participants are recruited loosely or open-flooded; feedback is collected ad-hoc through whatever channels exist; the decision to graduate to GA happens on calendar rather than on signal. The beta produced activity but not learning; the team launches with the same uncertainty they had before the beta.
This skill is the discipline that turns betas into decision input. Calibrated cohorts who match the post-launch user profile. Structured feedback that captures what the team needs to know. Mid-beta triage that uses what is being learned. Graduation criteria that distinguish "ready" from "we are tired of running the beta." The discipline is not bureaucratic; it is the difference between a beta that informs the GA launch and a beta that produces noise.
The voice is the senior product leader who has run betas with real signal and watched plenty of betas produce nothing. Concrete, opinionated about what produces signal, willing to call out where beta programs slide into ceremony.
When to use this skill: planning a beta for an upcoming launch, auditing why prior betas have not produced actionable signal, designing the beta participant experience, or deciding whether a feature is ready to graduate from beta to GA.
---
brand-archetype-system
When your agent uses it
Apply pre-composed aesthetic archetype defaults to jumpstart brand design work covering color, typography, layout, voice, and imagery direction. Use this skill whenever the user wants a starting point for brand visual and verbal direction, references a brand they want to design near (for example 'something like Stripe' or 'editorial like Linear'), needs to converge faster from many directions to one, or wants known-good defaults for a specific industry vertical. Triggers on archetype, design archetype, brand archetype, near to (brand), in the style of, similar aesthetic, design starting point, brand template, vertical-typical, industry-typical. Also triggers when the user has a brief and wants to map it to a known aesthetic family rather than design from first principles.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
1,659 tokensWhen the skill is activated
Reference documents
32,712 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: 12 core archetypes plus 18 vertical applications
- The 12 core archetypes
- The 18 vertical applications
- Trademark and attribution
- The four creative-direction axes (reference)
- Reference files
Files
SKILL.mdcore7,532 bytesreferences/00-archetype-system-overview.mddoc3,231 bytesreferences/01-how-to-apply-an-archetype.mddoc3,898 bytesreferences/_claude-frontmatter-extras.yamlasset414 bytesreferences/by-vertical/01-b2b-saas-developer-tools.mddoc3,609 bytesreferences/by-vertical/02-b2b-saas-business-productivity.mddoc3,547 bytesreferences/by-vertical/03-b2b-saas-marketing-sales.mddoc3,408 bytesreferences/by-vertical/04-b2b-saas-data-analytics.mddoc3,255 bytesreferences/by-vertical/05-fintech-consumer.mddoc3,264 bytesreferences/by-vertical/06-fintech-enterprise.mddoc3,438 bytesreferences/by-vertical/07-dtc-fashion.mddoc3,520 bytesreferences/by-vertical/08-dtc-beauty.mddoc3,447 bytesreferences/by-vertical/09-dtc-home-lifestyle.mddoc3,493 bytesreferences/by-vertical/10-dtc-food-beverage.mddoc3,513 bytesreferences/by-vertical/11-consumer-health-wellness.mddoc3,502 bytesreferences/by-vertical/12-hospitality-travel.mddoc3,308 bytesreferences/by-vertical/13-media-publishing.mddoc3,279 bytesreferences/by-vertical/14-edtech.mddoc3,608 bytesreferences/by-vertical/15-gaming-entertainment.mddoc3,438 bytesreferences/by-vertical/16-marketplace.mddoc3,474 bytesreferences/by-vertical/17-crypto-web3.mddoc3,443 bytesreferences/by-vertical/18-real-estate-proptech.mddoc3,648 bytesreferences/core-archetypes/01-editorial-restrained.mddoc6,292 bytesreferences/core-archetypes/02-technical-precise.mddoc6,632 bytesreferences/core-archetypes/03-warm-conversational.mddoc6,988 bytesreferences/core-archetypes/04-bold-confident.mddoc6,347 bytesreferences/core-archetypes/05-playful-energetic.mddoc6,623 bytesreferences/core-archetypes/06-luxe-considered.mddoc6,956 bytesreferences/core-archetypes/07-clinical-trustworthy.mddoc7,397 bytesreferences/core-archetypes/08-rugged-utilitarian.mddoc6,933 bytesreferences/core-archetypes/09-retro-nostalgic.mddoc7,336 bytesreferences/core-archetypes/10-minimal-essentialist.mddoc6,995 bytesreferences/core-archetypes/11-vibrant-saturated.mddoc6,758 bytesreferences/core-archetypes/12-documentary-honest.mddoc7,119 bytes
Read SKILL.md
# Brand Archetype System
Pre-composed aesthetic archetype defaults that jumpstart brand design work. Each archetype bundles color tendencies, type pairings, layout patterns, voice samples, and imagery direction for a recognizable aesthetic family. Stack-agnostic. Tool-agnostic.
This is a starting-point library, not a methodology library. The agent applies archetype defaults to a specific brief; the archetypes themselves provide anchor points, not endpoints.
---
## When to use
- The user wants a starting point rather than designing from first principles
- The user references a brand or aesthetic family they want to design near
- Need to converge faster from many directions to one
- The user wants vertical-typical defaults (for example fintech consumer, B2B developer tools)brand-discovery
When your agent uses it
Run upstream brand discovery covering audience research, competitive landscape, category dynamics, problem space, and positioning territory exploration. Use this skill at the very start of a brand or website project when the user needs to understand who they're for, who they compete with, what the audience actually needs, and where the brand could plausibly stand. Triggers on brand discovery, audience research, market research, competitive scan, category research, customer research, who is this for, who are we, positioning research, intake, kickoff. Also triggers when a creative brief is requested but the upstream inputs (audience, competitors, problem space) are not yet clear.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
2,061 tokensWhen the skill is activated
Reference documents
2,544 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,562 bytesSKILL.mdcore9,562 bytesreferences/_claude-frontmatter-extras.yamlasset415 bytesreferences/discovery-report-template.mddoc4,597 bytesreferences/interview-guide.mddoc6,923 bytes
Read SKILL.md
# Brand Discovery
Upstream of every brief, identity, and content plan. Discovery answers four questions: who the brand is for, what they need, who else is competing for that need, and where the brand could plausibly stand that competitors do not.
---
## When to use
- The very first phase of a new brand or website project
- Understanding an audience before any creative work begins
- Mapping competitors and category dynamics
- Surfacing the problem space the brand will operate in
- Generating positioning territories before brief or ideation
- When a creative brief was requested but the inputs are missingbrand-ideation
When your agent uses it
Generate, evaluate, and narrow brand concepts during early ideation including positioning territories, naming candidates, mood directions, and narrative angles. Use this skill whenever the user is in the early phase of brand creation, exploring brand directions, brainstorming names, building moodboards, generating positioning options, or trying to choose between multiple brand directions. Triggers on brand ideation, brand concept, naming, brand name, name candidates, positioning, brand positioning, mood board, brand directions, exploring brands, early brand work, brand exploration, brand brainstorm, brand options. Also triggers when the user has multiple half-formed brand ideas and needs help converging on one, even if they do not say 'ideation' explicitly.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
2,180 tokensWhen the skill is activated
Reference documents
2,735 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,493 bytesSKILL.mdcore9,493 bytesreferences/_claude-frontmatter-extras.yamlasset393 bytesreferences/ideation-output-template.mddoc4,755 bytesreferences/naming-evaluation-rubric.mddoc6,497 bytes
Read SKILL.md
# Brand Ideation
Generate and converge on brand directions before committing to identity work. This is upstream of `brand-identity` (the visual system) and `brand-style-guide` (the documentation). It is the divergent-then-convergent thinking phase where ideas are cheap and direction matters more than polish.
---
## When to use
- Generating naming options for a new brand or product
- Exploring positioning territories before committing
- Building moodboards and visual direction options
- Drafting narrative or origin-story angles
- Helping the user converge from many half-ideas to one direction
- Stress-testing an existing brand idea before investing in identity workbrand-identity
When your agent uses it
Design or evaluate a brand visual identity system covering logo, color, typography, imagery direction, iconography, and motion principles. Use this skill whenever the user wants to design a logo, build a visual identity, define brand colors, choose brand typography, develop iconography, plan brand imagery, or evaluate an existing identity for cohesion. Triggers on logo design, brand identity, visual identity, brand mark, wordmark, monogram, color palette, brand colors, brand typography, type system, iconography, brand imagery, motion design, brand system, identity system. Also triggers when the user has a brand direction approved and now needs the visual artifacts that express it.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,365 tokensWhen the skill is activated
Reference documents
3,411 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 elements
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,519 bytesSKILL.mdcore10,519 bytesSKILL.mdcore10,519 bytesreferences/_claude-frontmatter-extras.yamlasset387 bytesreferences/contrast-and-accessibility.mddoc6,761 bytesreferences/identity-system-spec.mddoc6,266 bytes
Read SKILL.md
# Brand Identity
Design or evaluate the visual artifacts that express a brand: logo system, color, typography, imagery, iconography, and motion. Stack-agnostic. Tool-agnostic.
This skill assumes a brand direction is already approved (positioning, mood, name). If not, run `brand-ideation` first.
---
## When to use
- Designing a logo system
- Defining a brand color palette
- Choosing brand typography
- Developing iconography or illustration stylebrand-style-guide
When your agent uses it
Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style guide for completeness, or produce the artifact that other teams will reference for years. Triggers on style guide, brand guidelines, brand book, brand standards, brand manual, style sheet, brand documentation, brand reference. Also triggers when the brand identity is finished and needs to be documented for handoff to designers, developers, vendors, or future team members.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
1,842 tokensWhen the skill is activated
Reference documents
3,893 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 8 sections
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,330 bytesSKILL.mdcore8,330 bytesSKILL.mdcore8,330 bytesSKILL.mdcore8,330 bytesreferences/_claude-frontmatter-extras.yamlasset388 bytesreferences/maintenance-playbook.mddoc7,873 bytesreferences/style-guide-template.mddoc7,669 bytes
Read SKILL.md
# Brand Style Guide
Document the brand system so other people can use it without ambiguity. This is the artifact that lives longest. Designers, developers, agencies, and vendors will reference it for years. Build it like a reference manual, not a presentation.
This skill assumes the brand identity is designed (run `brand-identity` first if not). The output of this skill is the canonical reference document.
---
## When to use
- Creating brand guidelines for a finished identity
- Documenting an existing brand that has no formal guide
- Auditing an existing style guide for gaps or inconsistencies
- Building a brand book to hand to vendors, partners, or new team membersbrand-voice
When your agent uses it
Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
1,967 tokensWhen the skill is activated
Reference documents
3,243 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,786 bytesreferences/_claude-frontmatter-extras.yamlasset389 bytesreferences/voice-document-template.mddoc5,656 bytesreferences/voice-frameworks.mddoc7,630 bytes
Read SKILL.md
# Brand Voice
Define how a brand sounds in writing. Document it in a way that anyone (writer, designer, founder, AI assistant) can apply it consistently.
This skill produces a standalone voice document that can either live in the brand style guide or feed into it.
---
## When to use
- Defining brand voice for the first time
- Auditing existing copy for voice consistency
- Training a team, freelancer, or AI assistant on the brand voice
- Refining a voice that exists but is inconsistent across applicationscalculator-design
When your agent uses it
Designing interactive calculators (ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments) that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. Honest about vanity-calculator (no real value), lead-trap (hides the answer behind email), and transparent-decision-tool (gives the result and earns the email through tiered value) patterns. Triggers on calculator, ROI calculator, pricing estimator, savings calculator, custom calculator, interactive tool, decision tool, financial calculator. Also triggers when an audience needs a calculation-driven lead magnet, when a vanity calculator is producing leads but no qualified ones, or when a calculator is being scoped for the first time.
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
4,721 tokensWhen the skill is activated
Reference documents
19,463 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The calculator decision: when calculators earn investment
- Vanity-calculator vs lead-trap vs transparent-decision-tool
- Input design
- Calculation logic transparency
- Result presentation
- Email-capture decision
- Tiered-value structures
- Calculator anti-patterns
- Common failure modes
- The framework: 12 considerations for calculator design
- If required data is unavailable
- Reference files
- Closing: calculators earn the email when they would have been worth paying for
Files
SKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesSKILL.mdcore23,458 bytesreferences/_claude-frontmatter-extras.yamlasset601 bytesreferences/calculation-logic-transparency.mddoc11,693 bytesreferences/calculator-anti-patterns.mddoc10,366 bytesreferences/calculator-investment-criteria.mddoc10,002 bytesreferences/common-calculator-failures.mddoc9,313 bytesreferences/email-capture-decision-tree.mddoc10,868 bytesreferences/input-design-patterns.mddoc10,986 bytesreferences/methodology-disclosure-templates.mddoc10,700 bytesreferences/result-presentation-patterns.mddoc10,900 bytesreferences/tiered-value-structures.mddoc10,560 bytes
Read SKILL.md
# Calculator Design
A senior growth practitioner's playbook for designing interactive calculators that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments. The discipline of building a tool the audience actually trusts.
Most calculators on the web are bait. Random multipliers behind official-looking math; an "Industry Average" number that does not cite a source; the result hidden behind a contact-sales form. The calculator captures emails because the format implies calculation; the leads are unqualified because the calculator did not actually help anyone decide anything.
The calculators that work as compounding assets do something different. They give the audience a result they can defend to a stakeholder. They show the methodology so the result is interrogatable. They capture leads through value (a PDF report, a save-and-compare account, a custom analysis) rather than through manipulation.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the calculator-specific methodology (calculation transparency, tiered value, methodology disclosure) lives here.
The voice is the senior growth practitioner who has watched calculators earn long-term credibility and watched them burn it within weeks of launch. Practical, opinionated about transparency, willing to say when a calculator is the wrong investment for the goal.
When to use this skill: scoping a calculator for the first time, auditing a calculator that converts but does not qualify, designing the methodology disclosure that earns audience trust, or deciding which features warrant the email gate.
chatbot-flow-design
When your agent uses it
Designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. Honest about scripted-bot (rigid trees, fail edge cases), hallucinating-bot (LLM without structure, makes things up), and structured-guided-conversation (LLM-powered with intent architecture and fallback discipline) patterns. Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION (engineering and platform work). Triggers on chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding. Also triggers when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time.
What it loads into context
Frontmatter
161 tokensAlways available to the agent
SKILL.md
4,088 tokensWhen the skill is activated
Reference documents
17,487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The chatbot decision: when chatbots earn deployment
- Scripted-bot vs hallucinating-bot vs structured-guided-conversation
- Intent architecture
- Knowledge-base grounding
- Branching and conditional logic
- Fallback patterns
- Escalation to human
- Conversation analytics
- Common failure modes
- The framework: 12 considerations for chatbot flow design
- Reference files
- Closing: chatbots earn deployment when they know what they don't know
Files
SKILL.mdcore20,269 bytesSKILL.mdcore20,269 bytesreferences/_claude-frontmatter-extras.yamlasset632 bytesreferences/branching-and-conditional-logic.mddoc9,490 bytesreferences/chatbot-anti-patterns.mddoc9,772 bytesreferences/chatbot-decision-criteria.mddoc9,562 bytesreferences/common-chatbot-failures.mddoc8,438 bytesreferences/conversation-analytics-patterns.mddoc10,047 bytesreferences/escalation-to-human-patterns.mddoc9,193 bytesreferences/fallback-pattern-design.mddoc9,859 bytesreferences/intent-architecture-patterns.mddoc10,376 bytesreferences/knowledge-base-grounding-patterns.mddoc10,778 bytes
Read SKILL.md
# Chatbot Flow Design
A senior growth practitioner's playbook for designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. The discipline of building a bot that knows what it knows and routes appropriately when it does not.
Most chatbots on the web fail in one of two ways. Scripted bots break the moment a user phrases something the script did not anticipate; the user gets pushed through a decision tree that does not fit their situation. LLM-powered bots without structure hallucinate; they confidently answer questions about pricing, policy, or capabilities and frequently make up answers, creating support burden and trust damage.
The chatbots that work do something different. They have an intent architecture that defines what the bot can and cannot handle. They ground their responses in a knowledge base so they do not invent facts. They have explicit fallback paths for unclear or out-of-scope intents. They escalate to humans cleanly when the bot's job is done. The audience trusts the bot because the bot is honest about its scope.
The voice is the senior growth practitioner who has watched chatbots become trusted brand surfaces and watched them become liability risks. Practical, opinionated about the architecture that distinguishes the two outcomes, willing to call out when a chatbot is the wrong investment or when an existing chatbot needs to be redesigned rather than tuned.
When to use this skill: scoping a chatbot for the first time, auditing a chatbot that hallucinates or fails edge cases, designing the intent architecture and fallback patterns, or deciding when to escalate to humans.
---
code-review-web
When your agent uses it
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,296 tokensWhen the skill is activated
Reference documents
4,786 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 review dimensions
- Common bug patterns (stack-agnostic)
- Workflow
- Failure patterns
- Debugging workflow
- Output format
- Reference files
Files
SKILL.mdcore10,583 bytesreferences/_claude-frontmatter-extras.yamlasset395 bytesreferences/nextjs-patterns.mddoc8,960 bytesreferences/review-template.mddoc3,090 bytesreferences/wordpress-headless-patterns.mddoc8,259 bytes
Read SKILL.md
# Code Review for Web
Review and debug web application code with a focus on the patterns that actually break production. Stack-agnostic principles in SKILL.md. Stack-specific patterns in references.
---
## When to use
- Reviewing a pull request before merging
- Debugging a production issue
- Investigating a build failure
- Auditing security or performance of existing code
- Investigating environment variable or configuration issues
- Triaging a "the site is broken" reportcomparison-tool-design
When your agent uses it
Designing side-by-side comparison tools (plan-compare, product-compare, alternative-compare) that help users decide rather than just listing features. Axis selection, default-comparison logic, recommendation discipline. Honest about feature-list-dump (every feature in a row, no decision support), hidden-recommendation (biased comparison pretending to be neutral), and honest-comparison-with-guidance (genuine comparison plus opinionated recommendation) patterns. Triggers on comparison tool, plan compare, product compare, alternative compare, vs page, decision support tool. Also triggers when conversion through comparison stages is poor, when users are abandoning at the comparison step, or when a comparison tool is being scoped for the first time.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
3,283 tokensWhen the skill is activated
Reference documents
10,173 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The comparison-tool decision: when comparison tools earn investment
- Feature-list-dump vs hidden-recommendation vs honest-comparison-with-guidance
- Axis selection: which dimensions matter, which are noise
- Default-comparison logic
- Recommendation engine design
- Filter and toggle UX
- Comparison-fatigue patterns
- Common failure modes
- The framework: 12 considerations for comparison tool design
- If required data is unavailable
- Reference files
- Closing: comparison tools earn the choice when they earn the user's trust
Files
SKILL.mdcore16,440 bytesSKILL.mdcore16,440 bytesreferences/_claude-frontmatter-extras.yamlasset635 bytesreferences/axis-selection-patterns.mddoc4,706 bytesreferences/common-comparison-failures.mddoc5,720 bytesreferences/comparison-anti-patterns.mddoc5,991 bytesreferences/comparison-fatigue-patterns.mddoc5,906 bytesreferences/comparison-tool-decision-criteria.mddoc4,643 bytesreferences/default-comparison-logic.mddoc5,752 bytesreferences/filter-and-toggle-patterns.mddoc6,237 bytesreferences/honest-recommendation-discipline.mddoc6,823 bytesreferences/recommendation-engine-design.mddoc5,157 bytes
Read SKILL.md
# Comparison Tool Design
A senior product marketing director's playbook for designing side-by-side comparison tools that help users decide rather than just listing features. Plan-compare, product-compare, alternative-compare. Axis selection, default-comparison logic, recommendation discipline. The discipline of building a comparison tool that earns the user's trust.
Most comparison tools fail in one of two ways. They dump every feature into a giant grid (4 options × 40 features = 160 cells) and ask the user to weigh everything against everything. The user leaves without choosing. Or they pretend to be neutral comparisons but are actually sales pitches with biased defaults and weighted framing; the user catches the bias and trust collapses.
The comparison tools that work do something different. Genuine like-for-like comparison plus an explicit opinionated recommendation. "For X audience, choose Y." The recommendation is visible, defended, and not the only path; users can override. The tool helps the user decide rather than asking them to decide alone.
The voice is the senior product marketing director who has watched comparison tools double conversion when redesigned with honest recommendations and watched them collapse when feature grids grew without decision support. Practical, opinionated about which axes matter, willing to call out when the comparison is decoration.
When to use this skill: scoping a comparison tool for the first time, auditing a feature-grid comparison that produces no conversion lift, designing recommendation logic that is honest about the recommendation, or deciding which axes earn placement in a comparison tool.
---
competitor-experience-audit
When your agent uses it
Audit the brand, UX, and site design of the leading sites in a vertical as a set of observable cross-site patterns, producing the experience bar a new build must meet or beat. Use this skill whenever the user wants to assess the competitive design field, capture vertical conventions, identify the design and UX bar of a category, or set the experience standard before a build. Triggers on competitor experience audit, UX audit, site design audit, brand audit, design conventions, what makes these sites good, vertical conventions, storefront patterns, merchandising patterns, layout density, primary task, design bar, category conventions, retail vs marketing register, what does the field do. Also triggers when an audit of the competitive field has captured technical signals (SEO, accessibility) but never named the brand, UX, or design conventions, and the build downstream will read as off-vertical without that bar.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
3,028 tokensWhen the skill is activated
Reference documents
2,684 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 experience dimensions
- The honesty guardrail (load-bearing)
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore14,324 bytesreferences/_claude-frontmatter-extras.yamlasset400 bytesreferences/audit-template.mddoc4,750 bytesreferences/experience-dimensions-checklist.mddoc7,203 bytes
Read SKILL.md
# Competitor Experience Audit
Capture the brand, UX, and site design that the leading sites in a vertical observably share, and where they fall short. The output is the experience bar a new build must meet or beat, grounded in cross-site patterns rather than aesthetic opinion.
Stack-agnostic. Works on any SiteShape (ecommerce-catalog, inventory-listing, hospitality-food, b2b-manufacturer, and so on). Auto-parts catalogs are the first test case, not the only target.
This skill is the brand / UX / design counterpart to a technical audit like `seo-onpage` or `accessibility-audit`. Technical findings are objective (a missing canonical is missing). Design is more subjective, so this skill is deliberately written to make the subjective assessable: every dimension is judged by observable questions about what the leading sites actually do, reported as patterns and gaps, and marked `not_assessable` whenever the evidence does not support a judgment.
---
## When to use
- Setting the experience bar for a new build in a vertical you have not built in before
- Capturing the design and UX conventions a credible site in the category is expected to carrycontent-and-copy
When your agent uses it
Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog post, draft an article, write copy for, edit this, rewrite this, write content, write a guide, draft a how-to, write web copy. Also triggers when content has been outlined and now needs to be written, or when existing content needs voice or clarity edits.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,868 tokensWhen the skill is activated
Reference documents
3,535 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,124 bytesreferences/_claude-frontmatter-extras.yamlasset388 bytesreferences/content-brief-template.mddoc7,426 bytesreferences/content-edit-checklist.mddoc7,284 bytes
Read SKILL.md
# Content and Copy
Write or edit content that serves a specific reader and goal. Stack-agnostic. This skill is for general content production. Specialized skills exist for landing pages (`landing-page-copy`) and email (`email-sequences`).
---
## When to use
- Writing a blog post or article
- Drafting website copy (homepage sections, about, services)
- Editing existing content for voice or clarity
- Writing how-to guides, listicles, or explainers
- Producing knowledge base or help center articles
- Adapting brand voice to a specific piececontent-brief-authoring
When your agent uses it
How to author a content brief that actually guides a writer (human or AI) to produce a piece that ranks, converts, or both. Per-piece editorial brief: target keyword and cluster, search intent, audience and JTBD, heading structure, entity coverage for AEO/GEO, internal linking strategy, success criteria. The middle path between thin briefs (a keyword and a deadline) and thick briefs (a 4-page document nobody reads). Triggers on content brief, brief the writer, brief the article, brief authoring, content brief template, brief audit, per-piece brief, editorial brief, target keyword brief, search intent brief. Also triggers when briefing a human writer or an AI agent on a single content piece.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
4,837 tokensWhen the skill is activated
Reference documents
11,075 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Thin vs thick vs effective briefs
- The 12 fields of an effective brief
- Search intent classification
- Heading structure design
- Entity coverage for AEO and GEO
- Internal linking strategy
- Brief templates by content type
- The brief-to-writer handoff
- Brief governance
- Common failure modes
- The framework: 12 considerations for brief authoring
- If required data is unavailable
- Reference files
- Closing: the brief is the contract
Files
SKILL.mdcore22,294 bytesSKILL.mdcore22,294 bytesSKILL.mdcore22,294 bytesSKILL.mdcore22,294 bytesreferences/_claude-frontmatter-extras.yamlasset523 bytesreferences/brief-governance-patterns.mddoc6,083 bytesreferences/brief-templates.mddoc7,826 bytesreferences/common-brief-failures.mddoc7,803 bytesreferences/entity-coverage-checklist.mddoc5,700 bytesreferences/heading-structure-patterns.mddoc5,438 bytesreferences/internal-linking-strategy.mddoc5,650 bytesreferences/search-intent-classification.mddoc4,799 bytesreferences/writer-handoff-protocols.mddoc6,094 bytes
Read SKILL.md
# Content Brief Authoring
A senior content strategist's playbook for authoring per-piece content briefs that actually guide writers to produce content worth publishing.
Most content briefs are some flavor of broken. The thin version is a keyword, a word count, and a deadline; the writer fills in everything else from scratch and the output is generic. The thick version is a 4-page document nobody reads, that the writer skims for the headline and the outline and ignores the rest. Either way, the brief failed at its job: making the writer's work easier and the output more predictable.
This skill is the middle path. It defines the 12 fields that earn their keep in a content brief, the fields that bloat without helping, and the discipline of writing briefs that route a writer (human or AI) toward a content piece that ranks for its target keyword, gets cited by AI engines, converts the right reader, or whatever the success criteria say. It assumes you have decided what to write (see `content-strategy` for program-level decisions) and now you are briefing each piece. The piece itself gets written separately (see `content-and-copy`).
When to use this skill: briefing a writer (human or AI) on an individual content piece, auditing existing briefs that are not producing good content, building a brief template for a content program, or running a brief-generation pipeline through Frase, AirOps, or another tool.
---
## What this skill is for
content-distribution
When your agent uses it
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel matching, distribution cadence. Triggers on content distribution, channel strategy for content, owned earned paid channels, content amplification, content promotion, audience-channel matching, content-channel matching, distribution cadence, syndication strategy, organic distribution. Also triggers when content is publishing but reach is low, when the team is distributing on every channel without strategy, or when the content program needs a distribution discipline rather than just publication.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
4,979 tokensWhen the skill is activated
Reference documents
18,908 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hope-and-pray vs spam-everywhere vs channel-fit
- Channel taxonomy
- Audience-channel matching
- Content-channel matching
- Distribution cadence
- Owned-channel discipline
- Earned-channel work
- Paid promotion of organic content
- Distribution measurement
- Common failure modes
- The framework: 12 considerations for content distribution
- If required data is unavailable
- Reference files
- Closing: distribution is half the work
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesreferences/_claude-frontmatter-extras.yamlasset546 bytesreferences/audience-channel-matching.mddoc10,402 bytesreferences/channel-taxonomy.mddoc13,084 bytesreferences/common-distribution-failures.mddoc11,960 bytesreferences/content-channel-matching.mddoc9,399 bytesreferences/distribution-cadence-patterns.mddoc10,644 bytesreferences/distribution-measurement.mddoc11,013 bytesreferences/earned-channel-work.mddoc11,074 bytesreferences/owned-channel-discipline.mddoc11,261 bytesreferences/paid-promotion-patterns.mddoc11,630 bytes
Read SKILL.md
# Content Distribution
A senior editorial leader's playbook for content distribution as a discipline. Owned, earned, and paid channels matched to audience and content type, with the channel-fit decisions that distinguish strategic distribution from spam-everywhere or hope-and-pray.
Content distribution is half the work and gets a fraction of the attention. Most programs spend 90% of capacity on production and 10% on distribution; the resulting ratio of effort-to-reach is consistently poor. The teams producing content that reaches audiences are the ones who treat distribution as a real discipline: channels chosen for fit, cadence calibrated to audience attention, owned-earned-paid balance set by program strategy, and effectiveness measured per channel.
This skill is the channel discipline. Different from `content-repurposing` (which turns one piece into many formats), this skill is about getting content TO audiences via the right channels. The two skills compose: repurpose first, then distribute the right format on the right channel.
The voice is the senior editorial leader who has watched programs underperform because distribution was treated as posting-after-publishing rather than as the equal half of the work.
When to use this skill: building a distribution discipline for a content program, auditing why content publishes consistently but reach is low, calibrating owned-earned-paid balance, designing channel-fit decisions for a multi-format program.
---
content-migration
When your agent uses it
Move content between platforms, domains, or URL structures while preserving SEO equity, user bookmarks, and integrations. Use this skill when planning a CMS migration, replatforming, consolidating sites, changing URL structures, or merging content from multiple sources. Triggers on content migration, replatform, CMS migration, domain migration, URL restructure, redirect map, site merge, content consolidation, migration plan, post-migration drop. Also triggers when planning a launch that involves moving existing content.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,424 tokensWhen the skill is activated
Reference documents
2,209 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesSKILL.mdcore10,742 bytesreferences/_claude-frontmatter-extras.yamlasset386 bytesreferences/migration-runbook.mddoc9,515 bytes
Read SKILL.md
# Content Migration
Move content from one platform, domain, or URL structure to another without breaking SEO, user bookmarks, or downstream integrations. Stack-agnostic.
---
## When to use
- Migrating from one CMS to another (e.g., WordPress to a headless setup)
- Consolidating multiple sites into one
- Splitting one site into multiple
- Changing URL structures
- Domain migration (one brand to another, mergers, rebrands)
- Migrating from a custom build to a platform (or vice versa)content-refresh-system
When your agent uses it
Systematic content refresh discipline. Quarterly audits, refresh prioritization (which pieces, when, how deep), refresh-vs-merge-vs-delete decisions, the lifecycle that distinguishes intentional refresh from set-and-forget decay. Builds on the refresh sections of pillar-content-architecture and editorial-qa with a program-level discipline. Triggers on content refresh, content decay, content audit, refresh prioritization, content lifecycle, refresh strategy, traffic decay, ranking drop, content freshness, evergreen content, content maintenance. Also triggers when traffic is eroding silently across an aging content library, when teams cannot decide which pieces to refresh, or when refresh work is happening but the impact is unclear.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
5,160 tokensWhen the skill is activated
Reference documents
19,150 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Refresh-everything vs refresh-nothing vs triaged-refresh
- Refresh signals
- The audit cadence
- Refresh prioritization
- Refresh depth options
- Refresh vs merge vs delete decisions
- Refresh execution patterns
- Re-promotion after refresh
- Refresh tracking and effectiveness measurement
- Common failure modes
- The framework: 12 considerations for content refresh
- If required data is unavailable
- Reference files
- Closing: refresh is content's immune system
Files
SKILL.mdcore25,653 bytesSKILL.mdcore25,653 bytesreferences/_claude-frontmatter-extras.yamlasset536 bytesreferences/audit-cadence-patterns.mddoc10,396 bytesreferences/common-refresh-failures.mddoc11,774 bytesreferences/effectiveness-measurement.mddoc11,055 bytesreferences/re-promotion-after-refresh.mddoc10,690 bytesreferences/refresh-depth-decision.mddoc10,655 bytesreferences/refresh-execution-patterns.mddoc10,036 bytesreferences/refresh-prioritization-matrix.mddoc11,361 bytesreferences/refresh-signals-checklist.mddoc10,605 bytesreferences/refresh-vs-merge-vs-delete.mddoc10,295 bytes
Read SKILL.md
# Content Refresh System
A senior editorial leader's playbook for systematic content refresh. The discipline that distinguishes intentional refresh programs from set-and-forget decay, and the prioritization framework that prevents both over-refresh (refresh-everything-on-calendar) and under-refresh (refresh-nothing-until-traffic-collapses).
Content decays. Search behavior shifts; SERP intent reshapes; facts go stale; competitors publish stronger pieces; the brand's own positioning evolves past what older pieces represent. Programs that ignore this reality watch traffic erode silently across the library. Programs that overreact (rewriting everything on calendar) burn editorial capacity that should be producing new flagship work. The discipline is in the middle: refresh what matters when signals say so, and document the decisions so the program is auditable.
This skill is the program-level refresh discipline across the whole content library. It builds on `pillar-content-architecture`'s hub-level refresh consideration (refresh as ONE consideration in hub design) and `editorial-qa`'s pre-publish quality gate (this skill is post-publish lifecycle, not pre-publish QA). Together those skills cover content quality at the moments quality decisions get made; this skill covers the moments between, when content is in the field and decaying or holding.
The voice is the senior editorial leader who has watched refresh programs fail in both directions and who has shipped the systems that produced durable refresh discipline.
When to use this skill: building a refresh program from scratch, auditing why refresh work is happening but traffic is not responding, designing the prioritization that keeps refresh tractable across a 200-piece or 2,000-piece library, or fixing a refresh program that is eating editorial capacity without clear results.
---
content-repurposing
When your agent uses it
Cross-format content adaptation. Turning one substantial piece into many derivative formats (blog series, email sequences, social posts, webinars, podcasts, video shorts) without losing the original's value or producing AI-slop variants. The discipline of adaptation per medium rather than mass-blast distribution. Triggers on content repurposing, content adaptation, cross-format content, content atomization, content multiplication, content distribution across formats, source-piece-to-derivative, video shorts from blog, email from whitepaper, podcast from article, blog series from research. Also triggers when a flagship piece is shipping but the team has not planned how to extend it across formats, when repurposing is happening but the derivatives feel mass-produced, or when AI-assisted repurposing is producing slop variants of strong source pieces.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
4,877 tokensWhen the skill is activated
Reference documents
20,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- One-and-done vs mass-blast vs adapt-by-format
- Source-piece selection
- Format adaptation patterns
- Per-format constraints
- Voice consistency across formats
- Sequencing and cadence
- Cross-promotion across derivatives
- Repurposing for AI search visibility
- Common failure modes
- The framework: 12 considerations for content repurposing
- If required data is unavailable
- Reference files
- Closing: adaptation is craft, not duplication
Files
SKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesSKILL.mdcore24,037 bytesreferences/_claude-frontmatter-extras.yamlasset526 bytesreferences/aeo-extraction-patterns.mddoc10,691 bytesreferences/common-repurposing-failures.mddoc10,731 bytesreferences/cross-promotion-patterns.mddoc9,690 bytesreferences/format-adaptation-patterns.mddoc13,696 bytesreferences/per-format-constraints.mddoc10,774 bytesreferences/repurposing-pipeline-templates.mddoc11,655 bytesreferences/sequencing-and-cadence-patterns.mddoc11,444 bytesreferences/source-piece-selection-criteria.mddoc11,167 bytesreferences/voice-consistency-across-formats.mddoc10,950 bytes
Read SKILL.md
# Content Repurposing
A senior editorial leader's playbook for cross-format content adaptation. The discipline of turning one substantial piece into many derivative formats without losing the original's value or producing slop variants.
Most content programs underspend on repurposing. A flagship piece costs 40-80 hours to produce; the program publishes it once, shares it on three channels, and moves on. The same piece could have produced a blog series, an email sequence, a webinar, a podcast episode, a dozen social posts, video shorts, and FAQ extractions for AI search visibility. The work to extend the source piece across formats is small relative to the value extracted; programs that skip repurposing leave most of the value unrealized.
The failure mode in the other direction is mass-blast: the same content reposted across channels without adaptation. A blog post pasted into LinkedIn as a long-text post; the email newsletter is the blog's first three paragraphs with "read more" tacked on; the YouTube video is a slideshow of the article text read aloud. Mass-blast respects neither the medium nor the audience. AI-assisted repurposing has made mass-blast cheap; the result is a wave of derivative content that performs poorly across every channel because it was adapted to none of them.
This skill is the discipline of adaptation per medium. Each format has constraints, conventions, and reader expectations the source piece does not have. Repurposing that respects those constraints produces work that earns engagement on the new format; repurposing that ignores them produces filler.
When to use this skill: planning the extension of a flagship piece across formats, auditing a repurposing pipeline that is producing low-engagement derivatives, calibrating an AI-assisted repurposing workflow that is producing slop, or designing the cross-format adaptation conventions for a content program.
---
content-strategy
When your agent uses it
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align content production with broader brand and SEO goals. Triggers on content strategy, content plan, editorial strategy, content pillars, content calendar, editorial calendar, topical authority, topic clusters, content governance, content roadmap, content production. Also triggers when the user is about to start producing content without a strategic plan.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
2,274 tokensWhen the skill is activated
Reference documents
3,489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,396 bytesSKILL.mdcore10,396 bytesreferences/_claude-frontmatter-extras.yamlasset410 bytesreferences/content-strategy-template.mddoc6,745 bytesreferences/editorial-calendar-template.mddoc7,906 bytes
Read SKILL.md
# Content Strategy
Plan what content to produce, why, when, and how. Stack-agnostic. Works for blogs, knowledge bases, marketing sites, newsletters, and product content surfaces.
This skill is the strategic layer. Tactical execution sits in `content-and-copy`, `landing-page-copy`, and `email-sequences`. SEO-driven content planning sits in `seo-keyword`. This skill stitches those together into a coherent program.
---
## When to use
- Planning a new content program or relaunching an existing one
- Defining editorial positioning and content pillars
- Building an editorial calendar
- Structuring topic clusters and content hubscost-optimization
When your agent uses it
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
2,632 tokensWhen the skill is activated
Reference documents
1,995 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 levers
- Workflow
- Common opportunities by category
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,094 bytesSKILL.mdcore12,094 bytesSKILL.mdcore12,094 bytesSKILL.mdcore12,094 bytesreferences/_claude-frontmatter-extras.yamlasset400 bytesreferences/cloud-audit-checklist.mddoc8,556 bytes
Read SKILL.md
# Cost Optimization
Audit cloud, SaaS, and infrastructure spend. Cut what's not earning its keep. Rightsize what's oversized. Negotiate what's negotiable. Without breaking what works.
---
## When to use
- Quarterly or annual cost review
- Finance flags rising spend
- Vendor contract renewal coming up
- Budget cut required
- New leadership wants the numbers
- Migrating between providers (cost is part of the case)creative-brief
When your agent uses it
Create or refine a creative brief that bridges discovery and execution. Use this skill whenever the user is starting a new project, kicking off a website, beginning a brand build or redesign, briefing a designer or developer or AI agent, or trying to align a team before building. Triggers on creative brief, design brief, brand brief, project kickoff, kicking off, briefing the team, project intake, design direction, brief the designer, brief the dev, where do we start, how do we start, write a brief, project overview, scope this project, align on direction. Also triggers when the user has a vague idea and needs to make it concrete enough to hand off, even if they do not say 'brief' explicitly.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
1,871 tokensWhen the skill is activated
Reference documents
4,585 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: brief structure
- Eliciting missing info
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,166 bytesreferences/_claude-frontmatter-extras.yamlasset401 bytesreferences/creative-brief-template.mddoc3,956 bytesreferences/example-brief.mddoc7,985 bytesreferences/voice-and-tone-guide.mddoc6,978 bytes
Read SKILL.md
# Creative Brief
Bridges discovery and execution. Translates "we want a website" into a brief a designer, developer, or AI agent can actually run with.
---
## When to use
- Starting a new project (website, app, brand, campaign)
- Kicking off a redesign or rebrand
- Handing work to a designer, developer, or AI agent
- Aligning a team that has drifted off course
- Turning a vague idea into something buildable
creative-brief-selector
When your agent uses it
Produce a creative brief grounded in live reference sites and deliberately distinct from existing demos, for any new brand build. Composes with brand-archetype-system and creative-direction. Use this skill at the start of any brand or microsite build when the result needs to land in a specific aesthetic position and not drift into a default house style. Triggers on creative brief, design brief, build brief, brand direction, where should this brand sit, what should this site look like, reference sites for, archetype for, distinct from our other brands, divergence from prior, not the same as. Also triggers when prior builds have come out as siblings and a systematic divergence approach is needed.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,110 tokensWhen the skill is activated
Reference documents
22,901 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: five steps, three rules, one hybrid bank
- The hybrid references model
- The divergence schema
- Trademark and attribution
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,909 bytesSKILL.mdcore9,909 bytesreferences/00-overview.mddoc5,349 bytesreferences/01-process.mddoc9,538 bytesreferences/02-brief-template.mddoc8,976 bytesreferences/03-divergence-check.mddoc12,675 bytesreferences/04-shipped-demos-signatures-example.mddoc8,664 bytesreferences/05-section-shapes-vocabulary.mddoc10,893 bytesreferences/_claude-frontmatter-extras.yamlasset418 bytesreferences/reference-bank/README.mddoc7,350 bytesreferences/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.mddoc3,849 bytesreferences/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.mddoc4,837 bytesreferences/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.mddoc3,196 bytesreferences/reference-bank/editorial-restrained-literary-quarterly.mddoc3,606 bytesreferences/reference-bank/heritage-local-service-barbershop.mddoc1,888 bytesreferences/reference-bank/hospitality-experience-balloon-ride.mddoc1,891 bytesreferences/reference-bank/luxe-considered-curated-stays-directory.mddoc6,244 bytesreferences/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.mddoc3,636 bytesreferences/reference-bank/minimal-essentialist-documentary-honest-trades-directory.mddoc6,645 bytesreferences/reference-bank/premium-dtc-maker-western-boots.mddoc1,889 bytesreferences/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.mddoc3,427 bytes
Read SKILL.md
# Creative Brief Selector
A starting-point selector for brand and microsite builds. Given a business spec (name, vertical, shape, one-line vibe, optional list of shipped demos), produces a creative brief grounded in three things:
1. An archetype position from `brand-archetype-system`, picked or composed to be deliberately distinct from the shipped demos.
2. A small set of live reference sites for that archetype-and-vertical combination, drawn from a curated bank plus optional per-build discovery.
3. A divergence check against the shipped demos that flags palette, voice, structural pattern, and section-shape overlap before the brief is handed off.
The brief output is concrete tokens, not abstract families, including explicit section-shape choices (hero shape and footer shape) as first-class outputs alongside palette and voice. It is meant to be loaded by downstream build skills as the single creative artifact for the build.
---
## When to use
creative-direction
When your agent uses it
Walk the user through four directional axes (tone register, aesthetic philosophy, audience relationship, sensory ambition) and produce a structured aesthetic brief that downstream content, copy, design, and art-direction skills consume as required input. The aesthetic depth layer, distinct from `creative-brief` (operational kickoff: scope, audience, deliverables, constraints). Use when a project needs aesthetic coherence across many small decisions and the user has only a vague feeling, or when multiple downstream aesthetic-producing skills need a shared brief. Triggers on creative direction, aesthetic direction, set the aesthetic, define the visual direction, what's the vibe, what's the tone, the four axes. Does NOT fire for a general kickoff brief (use `creative-brief`), tactical single-piece work, already-documented direction, purely functional output, or locked production-stage work.
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
2,312 tokensWhen the skill is activated
Reference documents
4,285 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 directional axes
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,478 bytesreferences/_claude-frontmatter-extras.yamlasset445 bytesreferences/axes-explained.mddoc12,970 bytesreferences/brief-template.mddoc2,049 bytesreferences/example-aesthetic-brief.mddoc6,306 bytes
Read SKILL.md
# Creative Direction
Frameworks produce competent output. Coherent output requires a brief.
This skill turns vague creative intent into a structured brief that downstream skills can reference. It does not generate taste. It captures direction, so the dozens of small decisions a project requires (word choice, image selection, white space, sequencing, what to leave out) all answer to the same question.
---
> Worked examples for each axis position can be assembled from any reference brand library that documents tone, aesthetic, audience relationship, and sensory ambition consistently. The framework below describes the four axes; the user's own reference set positions each example along the axes during the brief workflow.
---
## When to use
cro-optimization
When your agent uses it
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze test results. Triggers on conversion optimization, CRO, A/B test, split test, multivariate test, hypothesis, conversion funnel, funnel audit, experiment design, statistical significance, lift, optimization. Also triggers when the user has a conversion problem and isn't sure where to start, or when test results are ambiguous and need interpretation.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,389 tokensWhen the skill is activated
Reference documents
2,132 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Statistical foundations
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,827 bytesSKILL.mdcore10,827 bytesreferences/_claude-frontmatter-extras.yamlasset380 bytesreferences/hypothesis-library.mddoc10,380 bytes
Read SKILL.md
# CRO Optimization
Run conversion rate optimization as a structured discipline: audit → hypothesize → test → decide. Stack-agnostic. Tool-agnostic.
This skill is for running tests against existing pages and flows. For writing landing page copy from scratch, use `landing-page-copy`. For setting up the analytics that make CRO possible, use `analytics-strategy`.
---
## When to use
- Converting traffic at lower rate than expected
- Specific funnel step has high drop-off
- Pages with high traffic that could move the needle if optimized
- A/B testing infrastructure exists (or can be set up)data-warehouse-experimentation
When your agent uses it
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like Statsig and Optimizely. Triggers on warehouse-native experimentation, run experiments in BigQuery, run experiments in Snowflake, dbt experiments, SQL t-test, CUPED variance reduction, exposure log, sample ratio mismatch, sequential testing, mSPRT, doubly robust estimation, build vs buy experimentation. Also triggers when the team is choosing between platform and warehouse, building warehouse-native experiment infrastructure, auditing one, or running an experiment with a custom metric the platform cannot handle.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
6,031 tokensWhen the skill is activated
Reference documents
15,259 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When warehouse-native is the right call
- The architecture
- Assignment patterns
- The exposure log
- Metric definitions in dbt models
- Statistical analysis in SQL
- Statistical analysis in Python
- Variance reduction: CUPED and beyond
- Pre-experiment power analysis
- Sequential testing patterns
- Common pitfalls
- The framework: 12 considerations for warehouse-native experimentation
- If required data is unavailable
- Reference files
- Closing: the build-vs-buy decision is real
Files
SKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesSKILL.mdcore28,760 bytesreferences/_claude-frontmatter-extras.yamlasset553 bytesreferences/assignment-and-exposure-patterns.mddoc8,125 bytesreferences/common-pitfalls.mddoc10,052 bytesreferences/metric-definitions-in-dbt.mddoc8,099 bytesreferences/power-analysis-calculations.mddoc8,161 bytesreferences/sequential-testing-patterns.mddoc7,762 bytesreferences/statistical-analysis-templates.mddoc7,627 bytesreferences/variance-reduction-techniques.mddoc9,091 bytesreferences/warehouse-vs-platform-decision.mddoc7,976 bytes
Read SKILL.md
# Data Warehouse Experimentation
A senior data scientist's playbook for running experiments natively out of BigQuery, Snowflake, or any modern data warehouse, with metric definitions in dbt and statistical analysis in SQL or Python.
Most companies that run experiments at scale use a dedicated platform. Statsig, Optimizely, LaunchDarkly with experimentation, PostHog, Amplitude Experiment. The platforms are good. They handle assignment, instrumentation, and analysis in one product, and the SQL-savvy data team does not have to reinvent the variance reduction wheel.
There is a different operational model that mature data teams increasingly choose: warehouse-native experimentation. Assignment happens in code or via feature flags. Exposure events fire to the warehouse like any other event. Metrics are defined as dbt models. Statistical analysis runs as SQL or in a Python notebook against warehouse data. The "experiment platform" is just your existing data stack.
This skill covers when warehouse-native is the right call, the architecture, and the specific techniques that make it work: assignment patterns, exposure logging discipline, metric definitions in dbt, t-tests and CUPED in SQL, sequential testing, and the pitfalls that take down homegrown setups.
When to use this skill: deciding between platform vs warehouse-native, building a warehouse-native experiment infrastructure, auditing an existing one, or running a specific experiment when the platform of record cannot handle a custom metric or segmentation.
---
dependency-management
When your agent uses it
Manage third-party libraries, runtimes, and SaaS dependencies. Use this skill when setting an update cadence, responding to security advisories, dealing with deprecated dependencies, evaluating new dependencies, auditing what's installed, or unblocking a dependency upgrade. Triggers on dependency, package update, security patch, lockfile, deprecated, breaking change, supply chain, dependency audit, npm audit, dependabot, renovate. Also triggers when a build breaks after an update or when an advisory is published for a used package.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
2,375 tokensWhen the skill is activated
Reference documents
1,915 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of dependency
- The framework: 5 risk dimensions
- Workflow
- New dependency evaluation
- Dependency removal
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesSKILL.mdcore10,892 bytesreferences/_claude-frontmatter-extras.yamlasset393 bytesreferences/upgrade-checklist.mddoc8,457 bytes
Read SKILL.md
# Dependency Management
Decide what to depend on, keep dependencies current, respond to advisories, and reduce supply chain risk. Stack-agnostic principles; specifics vary by package manager.
---
## When to use
- Setting up dependency hygiene for a new or existing project
- Responding to a security advisory
- Major version upgrade of a key dependency
- Adding a new dependency (evaluation, decision)
- Removing a dependency (cleanup)
- Audit of what's installed and what's actually useddesign-standards
When your agent uses it
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card, CTA, layout, review the UI, fix the design, design system, design tokens, spacing, typography scale, button standards, mobile design. Also triggers for any production design decision where contrast, accessibility, spacing, or visual hierarchy matters.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
2,156 tokensWhen the skill is activated
Reference documents
6,137 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 standards
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,491 bytesSKILL.mdcore9,491 bytesreferences/_claude-frontmatter-extras.yamlasset382 bytesreferences/design-tokens-template.mddoc7,347 bytesreferences/preship-checklist.mddoc5,862 bytesreferences/tailwind-patterns.mddoc8,867 bytes
Read SKILL.md
# Design Standards
Production design standards for any web project. Stack-agnostic. Tool-agnostic. Covers tokens, contrast, hierarchy, spacing, mobile rules, and the pre-ship checklist.
This skill complements `brand-identity` (which defines the visual system) and `brand-style-guide` (which documents it). This skill is for the day-to-day work of applying those standards in real components and pages.
---
## When to use
- Building a new page, section, or component
- Reviewing UI for quality, accessibility, or consistency
- Setting up design tokens for a new project
- Fixing layout, contrast, or hierarchy issuesdesign-system
When your agent uses it
Build or audit a design system including component library, design tokens, naming conventions, contribution model, and documentation. Use this skill whenever the user wants to build a design system, audit an existing system, define design tokens at the system level, structure a component library, or set up design system governance. Triggers on design system, component library, design tokens, atomic design, atoms, molecules, organisms, design system documentation, Storybook, Figma library, system governance, design contribution model. Also triggers when teams are inconsistent across products and a system is the answer.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
2,064 tokensWhen the skill is activated
Reference documents
5,782 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,656 bytesSKILL.mdcore9,656 bytesSKILL.mdcore9,656 bytesreferences/_claude-frontmatter-extras.yamlasset388 bytesreferences/governance-playbook.mddoc8,423 bytesreferences/system-architecture.mddoc10,153 bytesreferences/system-audit-template.mddoc7,412 bytes
Read SKILL.md
# Design System
Build, evolve, or audit a design system. Stack-agnostic in principle. Implementation is stack-specific (Figma, Storybook, code library, etc.) but the structure and governance principles transfer.
This skill is for building the system. For applying a system to specific pages or components, use `design-standards`. For brand visual identity, use `brand-identity`.
---
## When to use
- Building a design system from scratch
- Auditing an existing system for gaps or fragmentation
- Defining design tokens at the system level
- Structuring a component librarydiscovery-research-synthesis
When your agent uses it
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis. Also triggers when a team has done research but cannot turn it into decisions, when synthesis is producing pretty decks but no roadmap movement, or when an upcoming PM decision needs to be grounded in research already conducted.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
4,870 tokensWhen the skill is activated
Reference documents
18,581 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Data-dump vs insight-theater vs actionable-synthesis
- Discovery research types
- The synthesis sequence
- Tagging and clustering discipline
- Pattern naming
- From pattern to product implication
- Writing for decisions, not deck performance
- The synthesis review and validation loop
- When to halt and gather more data
- Common failure modes
- The framework: 12 considerations for discovery synthesis
- Reference files
- Closing: synthesis is where research earns its keep
Files
SKILL.mdcore24,895 bytesreferences/_claude-frontmatter-extras.yamlasset579 bytesreferences/common-discovery-synthesis-failures.mddoc11,581 bytesreferences/from-pattern-to-product-implication.mddoc10,038 bytesreferences/pattern-naming-patterns.mddoc9,029 bytesreferences/research-types-and-when-each-fits.mddoc10,694 bytesreferences/synthesis-review-and-validation.mddoc10,987 bytesreferences/synthesis-sequence-walkthrough.mddoc11,419 bytesreferences/tagging-and-clustering-discipline.mddoc9,507 bytesreferences/when-to-gather-more-data.mddoc11,254 bytesreferences/writing-for-decisions-not-decks.mddoc10,630 bytes
Read SKILL.md
# Discovery Research Synthesis
A senior PM's playbook for turning research artifacts into decisions. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the product direction they are meant to inform.
Most discovery research never produces decisions. The team conducts interviews; the transcripts pile up; a researcher hands product the raw artifacts (data-dump) or builds a polished readout deck (insight-theater); the deck gets a 30-minute review meeting and is never referenced again. Two months later the team is making the same product decisions that the research was supposed to inform, with the same gut-feel inputs the research was supposed to displace.
The discipline is in the synthesis. Synthesis is where research earns its keep: where transcripts become tagged observations, observations cluster into patterns, patterns get named, named patterns surface product implications, and implications drive specific decisions. Without that sequence, research is performance art.
This skill covers one-off discovery research projects: a 12-week customer development sprint, a sales-call review for an onboarding redesign, a support-ticket audit informing a roadmap quarter. Different from `user-feedback-aggregation`, which covers ongoing feedback streams; different from `jtbd-framing`, which is a specific framing technique often applied within synthesis but narrower in scope.
The voice is the senior PM or staff product researcher who has run synthesis well and seen plenty of teams fail at it. Honest about where polish becomes performance and where pattern-naming slides into pattern-fabrication.
When to use this skill: synthesizing a recent batch of customer interviews, auditing why prior research has not produced product decisions, designing the synthesis output for a multi-week discovery sprint, or establishing the synthesis discipline a team currently lacks.
dispatch-authoring
When your agent uses it
Write the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope, specification, verification, delivery rules, and stop conditions, so the agent can execute unattended and return a reviewable draft PR. Use this skill whenever the user wants to hand work to an agent, write an agent brief, write instructions for Claude Code, Codex, or a Cursor agent, queue work to run overnight, or turn a plan into something an AI coder can execute without asking questions. Triggers on dispatch, hand off to an agent, agent brief, agent handoff, task brief for an AI coder, instructions for Claude Code, Codex task, Cursor agent, background agent, run this overnight, give this to an agent, unattended run. Also triggers when the user has a plan or a spec and asks how to get an agent to build it, even if they never say dispatch.
What it loads into context
Frontmatter
197 tokensAlways available to the agent
SKILL.md
1,803 tokensWhen the skill is activated
Reference documents
3,293 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 parts of a dispatch
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,043 bytesSKILL.mdcore8,043 bytesreferences/_claude-frontmatter-extras.yamlasset430 bytesreferences/dispatch-template.mddoc3,831 bytesreferences/example-dispatch-new-skill.mddoc5,615 bytesreferences/gate-zero-checklist.mddoc3,146 bytesreferences/pr-body-template.mddoc1,802 bytes
Read SKILL.md
# Dispatch Authoring
Write the handoff that lets a coding agent execute a plan unattended and come back with something a human can review. Agent-agnostic: works for Claude Code, Codex, or your coding agent of choice.
---
## When to use
- Handing a planned change to a coding agent to run without supervision
- Queueing work to run overnight or in the background
- Turning a spec or a ticket set into an executable brief for an agent
- Standardizing handoffs so agent runs are comparable and measurable
- Reviewing a draft dispatch before it goes out
documentation-strategy
When your agent uses it
Design and run a documentation system for a team or product. Use this skill when planning what to document, choosing a documentation tool, organizing existing docs, fixing stale documentation, designing a maintenance cadence, or scoping technical writing work. Triggers on documentation, docs, tech writing, knowledge base, wiki, runbook, README, internal docs, doc audit, doc maintenance, stale docs, where do we document. Also triggers when the team is repeatedly answering the same questions or when onboarding takes too long.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
2,912 tokensWhen the skill is activated
Reference documents
2,418 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of documentation
- The framework: 5 tiers of doc
- Workflow
- Specific patterns
- Tooling
- AI-related notes
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore12,936 bytesSKILL.mdcore12,936 bytesreferences/_claude-frontmatter-extras.yamlasset406 bytesreferences/doc-types-guide.mddoc10,540 bytes
Read SKILL.md
# Documentation Strategy
Decide what gets documented, where, by whom, and how it stays fresh. Stack-agnostic. Applies to internal team docs, product docs, runbooks, READMEs, and knowledge bases.
---
## When to use
- Setting up documentation for a new team or product
- Auditing existing documentation
- Fixing stale or scattered docs
- Choosing a documentation tool or platform
- Defining what gets documented and what doesn't
- Establishing maintenance cadencedomain-strategy
When your agent uses it
Plan, manage, and optimize a domain portfolio. Use this skill for DNS architecture decisions, redirect strategies, registrar choice, parking unused domains, multi-site setups, and domain consolidation or split planning. Triggers on DNS, domain, registrar, redirect, parking, subdomain, apex, www vs non-www, multi-site, portfolio, hreflang setup, domain migration. Also triggers when planning a new site that needs domain decisions made before launch.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
1,957 tokensWhen the skill is activated
Reference documents
2,110 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 decisions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,677 bytesreferences/_claude-frontmatter-extras.yamlasset397 bytesreferences/dns-record-reference.mddoc7,891 bytes
Read SKILL.md
# Domain Strategy
Decide how domains, subdomains, and DNS work across a portfolio. Stack-agnostic. Works for one site or one hundred.
---
## When to use
- Setting up DNS for a new site (apex vs www, primary vs aliases)
- Choosing or switching registrars
- Planning redirects across multiple domains (parked, retired, consolidated)
- Deciding subdomain vs subfolder vs separate domain for a new product line
- Consolidating multiple sites into one
- Splitting one site into multipleeditorial-qa
When your agent uses it
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
What it loads into context
Frontmatter
194 tokensAlways available to the agent
SKILL.md
4,698 tokensWhen the skill is activated
Reference documents
16,409 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Catch-problems QA vs checkbox QA
- Brief adherence check
- Voice consistency check
- Fact accuracy and citation discipline
- Structure and clarity check
- AI-content audit
- SEO and AEO compliance check
- Internal linking and schema validation
- QA at scale
- The QA workflow
- Common failure modes
- The framework: 12 considerations for editorial QA
- Reference files
- Closing: QA is where quality gets enforced
Files
SKILL.mdcore22,148 bytesSKILL.mdcore22,148 bytesreferences/_claude-frontmatter-extras.yamlasset535 bytesreferences/ai-content-audit-patterns.mddoc9,219 bytesreferences/brief-adherence-checklist.mddoc6,950 bytesreferences/common-qa-failures.mddoc9,533 bytesreferences/fact-accuracy-and-citation-discipline.mddoc7,262 bytesreferences/internal-linking-and-schema-validation.mddoc7,152 bytesreferences/qa-at-scale-patterns.mddoc8,389 bytesreferences/qa-workflow-templates.mddoc8,208 bytesreferences/seo-aeo-compliance-checklist.mddoc7,112 bytesreferences/structure-and-clarity-review.mddoc7,106 bytesreferences/voice-consistency-patterns.mddoc6,791 bytes
Read SKILL.md
# Editorial QA
A senior editor's playbook for pre-publish content QA. The discipline that catches problems BEFORE content ships, not after.
Most content QA is broken in one of two directions. The thin version is "did I read it once and is the spelling OK," which catches typos but misses brief drift, voice inconsistency, hallucinated facts, AI tells, and structural problems that reach readers as "this is fine but not memorable." The thick version is a 47-item checklist that nobody completes honestly because it is process theater: checkboxes nobody actually believes catch problems.
This skill is the discipline of catch-problems QA. Each check earns its keep by catching a specific class of failure that would reach readers if missed. Checks that do not catch anything get cut. Checks the production volume cannot sustain get redesigned (sampling instead of full audit, automated instead of manual). The QA framework is what is left when you remove the theater.
The skill covers three production shapes: single editorial pieces (one at a time, full QA), AI-generated drafts (with the AI-content audit that did not exist as prominently 2 years ago), and programmatic SEO sets at scale (sampling discipline, threshold gating). Each needs its own QA shape; the underlying methodology composes across all three.
When to use this skill: building a content QA process from scratch, auditing an existing QA process that ships sloppy work or burns out the team, designing QA gates for an AI-assisted workflow, or building sampling discipline for programmatic SEO sets.
---
email-deliverability
When your agent uses it
Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation strategy, monitoring sender reputation, or hardening against email spoofing. Triggers on email deliverability, SPF, DKIM, DMARC, spam folder, sender reputation, mailbox provider, soft bounces, bounce rate, BIMI, MTA-STS, deliverability audit. Also triggers when a marketing or transactional email isn't reaching users.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,666 tokensWhen the skill is activated
Reference documents
2,264 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 pillars
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,369 bytesSKILL.mdcore11,369 bytesreferences/_claude-frontmatter-extras.yamlasset400 bytesreferences/dmarc-rollout-playbook.mddoc9,199 bytes
Read SKILL.md
# Email Deliverability
Get email into inboxes, not spam folders. Set up authentication. Monitor reputation. Diagnose problems before they hurt the business.
---
## When to use
- Setting up email for a new domain
- A meaningful percentage of email is going to spam
- Customers report they're not receiving emails
- Setting up DMARC, SPF, or DKIM
- Hardening against domain spoofing
- Migrating email service providersemail-sequences
When your agent uses it
Design and write email campaigns and sequences including onboarding flows, lifecycle campaigns, transactional emails, newsletters, broadcast sends, and launch and announcement emails. Use this skill whenever the user wants to write email copy, plan an email sequence, design an onboarding drip, or set up lifecycle email campaigns. Triggers on email sequence, drip campaign, onboarding email, lifecycle email, welcome email, transactional email, newsletter, email broadcast, launch email, announcement email, nurture sequence, abandoned cart, re-engagement, win-back. Also triggers when planning email automation flows or writing email subject lines for campaigns.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,345 tokensWhen the skill is activated
Reference documents
3,782 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 sequence types
- The 5 components of every email
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,319 bytesreferences/_claude-frontmatter-extras.yamlasset387 bytesreferences/sequence-templates.mddoc8,158 bytesreferences/subject-line-patterns.mddoc7,559 bytes
Read SKILL.md
# Email Sequences
Plan and write email campaigns. Sequences (multi-message flows triggered by events) and broadcasts (one-off sends). Stack-agnostic. Works with any email service provider.
---
## When to use
- Writing welcome and onboarding email sequences
- Planning lifecycle campaigns (activation, retention, win-back)
- Writing transactional emails (receipts, password resets, notifications)
- Newsletter design and writing
- Abandoned-cart or re-engagement flows
- Writing a one-off broadcast, launch announcement, or news emailevidence-based-reviews
When your agent uses it
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
2,458 tokensWhen the skill is activated
Reference documents
1,433 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: one rule, four evidence tiers
- The methodology block
- Structure discipline the method implies
- Google reviews-system alignment
- FTC alignment
- Schema judgment
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,294 bytesSKILL.mdcore12,294 bytesSKILL.mdcore12,294 bytesSKILL.mdcore12,294 bytesreferences/_claude-frontmatter-extras.yamlasset398 bytesreferences/evidence-tiers.mddoc4,193 bytesreferences/methodology-block-template.mddoc2,760 bytes
Read SKILL.md
# Evidence-Based Reviews
Produce product reviews and buying guides whose claims match their evidence. The method is evidence synthesis with a disclosed basis, and one rule anchors everything: never claim hands-on time that did not happen.
Most review sites fail this rule quietly. "We tested" appears above content assembled from spec sheets, and readers have learned to smell it. The honest alternative is stronger, not weaker: synthesis of owner experience at scale, verified specifications, and triangulated expert sources is demonstrable original analysis, and disclosing it builds the trust that fabricated testing destroys.
---
## When to use
- Writing product reviews or buying guides when hands-on access is partial or absent
- Setting up the review methodology for a new review or affiliate site
- Adding evidence disclosure to existing review content
- Auditing review content for claims its evidence cannot supportexperiment-design
When your agent uses it
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
6,324 tokensWhen the skill is activated
Reference documents
11,961 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The framework: 12 considerations for trustworthy experiment results
- Hypothesis discipline
- Sample size and minimum detectable effect
- Test duration
- What NOT to A/B test
- Segment analysis
- Interaction effects
- Ratio metrics and the delta method
- Network effects and two-sided markets
- Sequential testing and the peeking problem
- Pre-commitment vs p-hacking
- Reading results and making the call
- Common failures and fixes
- If required data is unavailable
- Reference files
- Closing: when in doubt
Files
SKILL.mdcore31,536 bytesSKILL.mdcore31,536 bytesreferences/_claude-frontmatter-extras.yamlasset468 bytesreferences/common-failures.mddoc10,946 bytesreferences/hypothesis-templates.mddoc8,742 bytesreferences/platform-comparison.mddoc10,392 bytesreferences/post-experiment-decision-framework.mddoc6,436 bytesreferences/pre-experiment-readiness-checklist.mddoc5,457 bytesreferences/results-interpretation-checklist.mddoc7,660 bytesreferences/sample-size-tables.mddoc6,398 bytes
Read SKILL.md
# Experiment Design
A senior product manager's playbook for running experiments that produce trustworthy decisions.
The default state of experimentation in most companies is sloppy. PMs run tests against vague hypotheses, look at results too early, ignore guardrails, stratify into noise, and ship features whose lift is mostly measurement error. The cost is real: ship the wrong thing, kill the right thing, learn the wrong lesson, repeat.
This skill is the discipline that prevents most of those mistakes. It assumes you have a working experimentation platform (Statsig, PostHog, GrowthBook, Optimizely, Amplitude, Eppo, Kameleoon; the platform does not matter for the principles). It assumes you have product-design and engineering pipelines that can deliver real treatment changes. The hard part is the thinking, and that is what is here.
When to use this skill: any time you are about to design or interpret an experiment. Read the relevant section before you start, not after the test is running.
---
## What this skill covers
experimentation-analytics
When your agent uses it
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this skill whenever the user is reading a finished experiment result panel and about to make a ship, kill, or iterate decision, or when an experiment number does not match the dashboard number. Triggers on read experiment results, result panel, ship or kill decision, p-value, confidence interval, statistical significance, multiple testing, peeking, sequential testing, CUPED, variance reduction, heterogeneous treatment effects, ratio metric, network effects, inconclusive test, experiment versus dashboard mismatch. Use `experiment-design` instead when the test has not run yet and the question is hypothesis, sample size, duration, or what to test.
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
7,249 tokensWhen the skill is activated
Reference documents
14,467 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every modern platform should expose
- Confidence intervals: the most important number
- P-values: what they mean and what they do not
- Multiple testing corrections
- Sequential testing math
- CUPED variance reduction
- Heterogeneous treatment effects (HTE) and segments
- Ratio metrics and the delta method
- Bayesian vs frequentist results panels
- Network effects and SUTVA violation
- Dashboard metric vs experiment metric reconciliation
- Long-term effect estimation
- Common interpretation failures
- The framework: 14 considerations for trustworthy experiment interpretation
- Reference files
- Closing: the courage to call it inconclusive
Files
SKILL.mdcore35,515 bytesreferences/_claude-frontmatter-extras.yamlasset518 bytesreferences/analytics-platform-comparison.mddoc10,160 bytesreferences/common-interpretation-failures.mddoc13,900 bytesreferences/confidence-interval-cheatsheet.mddoc7,164 bytesreferences/dashboard-vs-experiment-reconciliation.mddoc7,403 bytesreferences/p-value-interpretation-guide.mddoc8,111 bytesreferences/result-presentation-templates.mddoc9,227 bytesreferences/statistical-method-reference.mddoc11,787 bytes
Read SKILL.md
# Experimentation Analytics
A data-team-mentor's playbook for interpreting experiment results without fooling yourself.
The result panel is the moment-of-truth for an experiment. The numbers on it determine whether you ship, kill, or iterate. They also expose every shortcut taken in the design phase: an underpowered test produces wide confidence intervals; a peeked test produces a too-narrow p-value; a ratio metric without delta-method correction produces overconfident lift estimates. Most ship-the-wrong-thing decisions trace back to misreading the result panel.
This skill is the discipline that prevents misreading. It assumes the experiment was designed well (see the `experiment-design` skill). It assumes the platform's results panel is technically correct (most modern platforms are; some older ones are not). It assumes you can read a number off a screen. The hard part is knowing what each number actually means and what it does not, and that is what is here.
When to use this skill: any time you are reading an experiment result panel and about to make a ship, kill, or iterate decision.
---
## What this skill is for
experimentation-platform-orchestrator
When your agent uses it
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
5,297 tokensWhen the skill is activated
Reference documents
10,997 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The 7 considerations for the platform decision
- Statsig
- PostHog
- GrowthBook
- Optimizely
- Amplitude
- Eppo
- Kameleoon
- Decision matrix: which platform for which context
- Multi-platform: when warranted, when a mess
- Migration patterns
- The cost reality
- Governance and team fit
- The MCP capability layer
- When to defer the decision
- Common mistakes
- The framework: 11 considerations for sustainable platform choice
- Reference files
- Closing: when in doubt, pick boring
Files
SKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesSKILL.mdcore26,348 bytesreferences/_claude-frontmatter-extras.yamlasset538 bytesreferences/common-mistakes.mddoc9,003 bytesreferences/cost-and-pricing-models.mddoc8,045 bytesreferences/governance-and-team-setup.mddoc7,543 bytesreferences/mcp-capability-comparison.mddoc6,018 bytesreferences/migration-playbook.mddoc8,243 bytesreferences/multi-platform-orchestration.mddoc7,159 bytesreferences/platform-decision-matrix.mddoc6,525 bytes
Read SKILL.md
# Experimentation Platform Orchestrator
A senior product and engineering leader's playbook for making the experimentation platform decision and recovering from making it wrong.
Picking an experimentation platform is one of those decisions that looks easy at the start and compounds for years afterward. The wrong choice costs you in lost experiments (because the team avoids the painful workflow), in cost (because the wrong pricing model penalizes your usage shape), in vendor lock-in (because migration is real engineering work, not a config change), and in cultural drift (because the platform's defaults shape what your team thinks experimentation is).
This skill is the discipline that makes the decision well the first time and the migration plan when you didn't.
When to use this skill: choosing a platform from scratch, evaluating whether to switch, deciding whether to consolidate from multi-platform to single, or planning a migration that has already been approved.
---
## What this skill is for
feature-flagging
When your agent uses it
Operational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy, lifecycle, governance, stale flag management, and the technical debt patterns that bite teams who weren't deliberate about it.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
5,335 tokensWhen the skill is activated
Reference documents
9,530 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The five flag types
- Flag naming conventions
- The flag lifecycle
- Targeting rules and segmentation
- Rollout strategies
- Stale flag management
- Governance and permissions
- Flag dependencies and conflicts
- Performance considerations
- Testing flag-gated code
- Rollback discipline
- Observability on flags
- Common failures (rapid-fire)
- The framework: 14 considerations for sustainable feature flagging
- If required data is unavailable
- Reference files
- Closing: when to remove a flag
Files
SKILL.mdcore25,629 bytesSKILL.mdcore25,629 bytesSKILL.mdcore25,629 bytesreferences/_claude-frontmatter-extras.yamlasset443 bytesreferences/flag-lifecycle-checklist.mddoc5,006 bytesreferences/flag-naming-conventions.mddoc5,094 bytesreferences/flag-rollout-strategies.mddoc7,061 bytesreferences/flag-types-reference.mddoc6,712 bytesreferences/governance-and-permissions.mddoc6,954 bytesreferences/stale-flag-cleanup-playbook.mddoc6,154 bytesreferences/targeting-rule-patterns.mddoc6,706 bytes
Read SKILL.md
# Feature Flagging
A senior engineer's playbook for using feature flags well, not just frequently.
Feature flags are infrastructure. Treated as such, they enable kill switches, gradual rollouts, A/B experiments, permission gates, and operational toggles without redeploys. Treated casually, they become the largest accumulating technical debt in your codebase: thousands of dead flags, conflicting evaluation logic, brittle targeting, and a permission surface no one fully understands.
This skill is the discipline that prevents the second outcome. It assumes you have a feature flag platform (LaunchDarkly, Flagsmith, Split.io, VWO FME, GrowthBook, Statsig, PostHog, Optimizely; the platform does not matter for the principles). It assumes your engineering team can implement targeting rules and SDK integration. The hard part is the operational discipline, and that is what is here.
When to use this skill: any time you are about to introduce a flag, modify a flag, audit existing flags, or design a flag-related governance policy.
---
## What this skill is for
feature-launch-playbook
When your agent uses it
The operational playbook for launching a feature well. Positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring with pre-defined rollback triggers, post-launch measurement against spec hypotheses, and the discipline that distinguishes shipping from releasing from actually launching. Triggers on launch plan, feature launch, launch checklist, ship vs release, rollout strategy, gradual rollout, sales enablement, support readiness, launch announcement, post-launch measurement, launch failure, declared victory too early. Also triggers when planning a launch (any size, any segment), auditing an existing launch process, fixing the we shipped it but the metric did not move problem, or building a launch checklist for the team.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
5,392 tokensWhen the skill is activated
Reference documents
18,158 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Ship vs release vs launch
- Launch tiers
- Pre-launch: positioning
- Pre-launch: internal alignment
- Pre-launch: customer comms plan
- Pre-launch: sales enablement (B2B)
- Pre-launch: support readiness
- Launch day: rollout strategy
- Launch day: monitoring
- Launch day: comms execution
- Post-launch: measurement against spec hypotheses
- Post-launch: iteration and follow-ups
- Common failure modes
- The framework: 12 considerations for a real launch
- If required data is unavailable
- Reference files
- Closing: most failed launches are unlaunched
Files
SKILL.mdcore26,035 bytesSKILL.mdcore26,035 bytesreferences/_claude-frontmatter-extras.yamlasset538 bytesreferences/common-launch-failures.mddoc11,194 bytesreferences/customer-comms-playbook.mddoc8,102 bytesreferences/internal-alignment-checklist.mddoc7,355 bytesreferences/launch-tier-decision.mddoc6,987 bytesreferences/monitoring-readiness-checklist.mddoc8,429 bytesreferences/positioning-canvas.mddoc8,542 bytesreferences/post-launch-measurement-framework.mddoc9,449 bytesreferences/rollout-strategy-patterns.mddoc8,971 bytesreferences/sales-enablement-template.mddoc8,314 bytesreferences/support-readiness-checklist.mddoc7,719 bytes
Read SKILL.md
# Feature Launch Playbook
A veteran PM-leader's playbook for launching features well, not just shipping them.
Most teams conflate shipping, releasing, and launching. Shipping means engineering work is complete. Releasing means users can access it, even if it is behind a flag at 1 percent. Launching is the discipline of positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring, and post-launch measurement that turns "feature exists" into "feature lands."
A feature that ships without launching costs you the same engineering investment but captures a fraction of the value. Sales does not know how to sell it. Support does not know how to help with it. Customers do not notice it. The metric you said you would move does not move because nobody knows the feature is there.
This skill is the operational playbook. It assumes you have already written the spec (`pm-spec-writing`), prioritized it onto the roadmap (`roadmap-planning`), instrumented it (`product-analytics-setup`), and possibly tested it (`experiment-design`). The launch is the next discipline: how to actually get the feature in front of the right users, with the right context, in a way that lets you measure whether it worked.
When to use this skill: planning a launch (any size, any segment), auditing an existing launch process, fixing the "we shipped it but the metric did not move" problem, or building a launch checklist for the team.
---
form-strategy
When your agent uses it
Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are low or spam is overwhelming.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,493 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,312 bytesSKILL.mdcore11,312 bytesreferences/_claude-frontmatter-extras.yamlasset402 bytesreferences/form-anatomy-checklist.mddoc9,144 bytes
Read SKILL.md
# Form Strategy
Forms are where intent becomes action. Design them well or lose conversions, frustrate users, and drown in spam. Stack-agnostic.
---
## When to use
- Designing or redesigning a form
- Conversion is dropping on a key form
- Spam volume is overwhelming the inbox or database
- Auditing forms across a site
- Planning validation logic
- Choosing form tooling (form service, custom build, no-code)frontend-component-build
When your agent uses it
Build production-ready frontend components with accessible markup, sensible props, defined states, and tested behavior. Use this skill whenever the user wants to build a component from scratch, refactor an existing one, design a component API, or implement a UI element with proper states and accessibility. Triggers on build a component, create a button, create a modal, create a form input, component API, props design, component states, refactor component, accessible component. Also triggers when implementing UI from a design that needs to be reusable.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
1,896 tokensWhen the skill is activated
Reference documents
5,809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,532 bytesreferences/_claude-frontmatter-extras.yamlasset409 bytesreferences/accessibility-patterns.mddoc8,072 bytesreferences/component-api-patterns.mddoc8,038 bytesreferences/component-spec-template.mddoc7,070 bytes
Read SKILL.md
# Frontend Component Build
Build production-ready components. Stack-agnostic principles. Most patterns translate to React, Vue, Svelte, or vanilla web components.
This skill is about implementing a component well. For broader system design see `design-system`. For day-to-day visual decisions see `design-standards`.
---
## When to use
- Building a new component from scratch
- Refactoring an existing component
- Designing a component API (props, slots, events)
- Adding accessibility to an existing componentfunnel-flow-architecture
When your agent uses it
Architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. Honest about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience-and-stage) patterns. Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, multi-tool funnel orchestration. Also triggers when the team's growth tools are working individually but not together, when audience segments share one nurture path, or when a funnel is being architected from scratch.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
4,298 tokensWhen the skill is activated
Reference documents
16,383 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Silo-funnels vs kitchen-sink-funnels vs matched-funnels
- Audience and stage segmentation
- Entry-point architecture
- Tool-to-funnel mapping
- Nurture sequence architecture
- Cross-tool data flow
- Funnel measurement
- Funnel iteration discipline
- Architecture anti-patterns
- The framework: 12 considerations for funnel flow architecture
- If required data is unavailable
- Reference files
- Closing: funnels are architecture, not collections
- Closing: funnels earn investment when they compose
Files
SKILL.mdcore22,009 bytesSKILL.mdcore22,009 bytesreferences/_claude-frontmatter-extras.yamlasset603 bytesreferences/architecture-anti-patterns.mddoc8,941 bytesreferences/audience-and-stage-segmentation.mddoc9,391 bytesreferences/common-funnel-architecture-failures.mddoc8,080 bytesreferences/cross-tool-data-flow-patterns.mddoc10,099 bytesreferences/entry-point-architecture-patterns.mddoc8,906 bytesreferences/funnel-iteration-discipline.mddoc8,491 bytesreferences/funnel-measurement-patterns.mddoc9,505 bytesreferences/nurture-sequence-architecture.mddoc10,947 bytesreferences/tool-to-funnel-mapping.mddoc9,924 bytes
Read SKILL.md
# Funnel Flow Architecture
A senior growth practitioner's playbook for architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. The discipline of building a funnel architecture, not just collecting tools.
Most growth programs accumulate tools without architecture. A chatbot, a calculator, a quiz, a lead magnet, a newsletter signup, a demo CTA. Each tool works individually; none of them work together. Visitors hit one tool, leave, and never enter the broader nurture sequence. The funnel is a collection of orphans.
The growth programs that compound do something different. They architect the funnel deliberately. Different entry points lead to different nurture sequences. Different stages get different CTAs. Different tools serve different segments. Each tool is part of a larger architecture, not a standalone artifact.
This skill is the architecture skill that orchestrates the other 5 growth-tooling skills (lead-magnet-design, calculator-design, quiz-and-assessment-design, multi-step-form-design, chatbot-flow-design). Where those skills zoom into specific tool design, this skill zooms out to the cross-tool architecture that determines whether the tools compound.
The voice is the senior growth practitioner who has watched funnels architecture compound and watched siloed funnel collections produce engagement metrics with no business impact. Practical, opinionated about the difference between collecting tools and architecting funnels, willing to call out when a team's growth program needs architecture rather than another tool.
When to use this skill: architecting a funnel from scratch, auditing a growth program where tools work individually but conversion is flat, designing the cross-tool data flow that captures audience signal across touchpoints, or deciding which segments warrant which funnel paths.
incident-response
When your agent uses it
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
2,158 tokensWhen the skill is activated
Reference documents
1,981 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Roles during an incident
- Decision-making during an incident
- Status page communication patterns
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,853 bytesSKILL.mdcore9,853 bytesreferences/_claude-frontmatter-extras.yamlasset381 bytesreferences/incident-playbook.mddoc9,180 bytes
Read SKILL.md
# Incident Response
Manage active production incidents from detection to resolution. Stack-agnostic. Tool-agnostic.
This skill is for active incidents and incident process. For after-the-fact analysis, use `after-action-report`. For planned launches, use `launch-runbook`.
---
## When to use
- An active incident is happening
- Building incident response procedures
- Defining severity levels
- Setting up on-call rotationsinformation-architecture
When your agent uses it
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system level. Triggers on sitemap, site structure, navigation, IA, information architecture, URL structure, content types, taxonomy, categorization, breadcrumbs, hub pages, faceted navigation, site search, labeling. Also triggers when content is being created without a structural plan, or when an existing site's structure is being audited or restructured.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
2,221 tokensWhen the skill is activated
Reference documents
3,871 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,327 bytesSKILL.mdcore10,327 bytesreferences/_claude-frontmatter-extras.yamlasset413 bytesreferences/ia-document-template.mddoc7,519 bytesreferences/url-pattern-library.mddoc8,047 bytes
Read SKILL.md
# Information Architecture
Design the structure that holds the content. Stack-agnostic. Applies to marketing sites, product surfaces, knowledge bases, e-commerce, and editorial content.
A well-designed IA makes the rest of the project easier. A poorly-designed IA forces every downstream decision to fight the structure.
---
## When to use
- Designing a new site or major section from scratch
- Restructuring an existing site
- Adding a new content type or category
- Designing site navigation or menu systemsintegration-orchestrator
When your agent uses it
Generate a phased delivery orchestration plan for creative-direction-driven work: which skills run when, what locks at which gate, how handoffs occur, and how the cadence implements in the team's tools (Jira, Linear, Notion, Figma, GitHub) with AI agents via MCP and CLI. A temporal map of phases, lock points, handoff specs, gate definitions, and QA verification gates. Distinct from `creative-brief` (static project brief) and `creative-direction` (aesthetic direction). Triggers on integration orchestrator, delivery cadence, project orchestration, when does the brief lock, how to phase creative direction, design-development handoff, QA gate, agent-driven QA, and when a creative-direction project is starting, mid-flight with broken cadence, or integrating AI agents into PM workflow. Does NOT fire for project scoping (use `creative-brief`), aesthetic direction (use `creative-direction`), or general project management without a creative-direction throughline.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
4,341 tokensWhen the skill is activated
Reference documents
18,404 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is
- When to use
- When NOT to use
- Required inputs
- The framework: 7 considerations for orchestration
- Common project-type cadences
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore20,869 bytesSKILL.mdcore20,869 bytesreferences/_claude-frontmatter-extras.yamlasset423 bytesreferences/automation-and-qa-tooling.mddoc12,839 bytesreferences/cadence-patterns.mddoc11,589 bytesreferences/example-orchestration.mddoc15,949 bytesreferences/gate-definitions.mddoc9,868 bytesreferences/handoff-protocols.mddoc12,110 bytesreferences/platform-implementation.mddoc17,271 bytesreferences/team-size-modulation.mddoc7,938 bytes
Read SKILL.md
# Integration Orchestrator
A brief tells a team what to make. Creative direction tells them what it should feel like. Neither tells them when each decision locks, who reviews what, or what stops the next phase from starting before the prior one is done. That is the gap this skill fills.
The output is a phased orchestration plan the PM can paste into a calendar Monday morning and start running Tuesday. Phases, gates, lock points, handoffs, QA verification rules, and a platform-specific implementation guide for whatever stack the team actually uses (Jira, Linear, Notion, Figma, GitHub, agile sprints).
---
## What this skill is
A creative-direction project has three layers. The brief layer defines scope, audience, deliverables, constraints, success criteria. The direction layer defines tone, aesthetic, relationship, and sensory ambition. Both produce written artifacts. Neither answers the temporal question: when does the brief lock, when does identity lock, when does copy lock, who reviews each, what gets blocked while a gate is open, what happens when a downstream task discovers the brief is wrong, and what makes "Done" mean tested rather than self-reported.
This skill produces that temporal layer. Most teams have briefs and creative direction but no orchestration plan. The result, by week 3, is everyone working in parallel with no shared sense of which decisions are still open and which are locked. Brief drift. Re-work. Identity tokens shifted after copy was already drafted against the old ones. Engineering shipping before design had a chance to review. "Done" tickets that were never actually verified.
interactive-product-tour
When your agent uses it
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of need), and contextual-when-needed (surfaces help at the moment friction occurs) patterns. Triggers on product tour, in-product tooltip, contextual help, walkthrough, feature tour, hint system, in-app guidance, tour platform. Also triggers when feature adoption is low, when users miss key product capabilities, or when an in-product help system is being scoped for the first time.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
3,609 tokensWhen the skill is activated
Reference documents
12,998 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The tour decision: when tours earn vs when documentation suffices
- Tooltip-spam vs one-and-done vs contextual-when-needed
- Trigger logic: event-based vs time-based vs state-based
- Tour architecture: single tour vs branched vs library of micro-tours
- Contextual placement: where help appears, how it dismisses
- Completion tracking and re-trigger logic
- Power-user vs new-user differentiation
- Common failure modes
- The framework: 12 considerations for product tour design
- Reference files
- Closing: tours earn the user's attention by being absent until needed
Files
SKILL.mdcore17,420 bytesreferences/_claude-frontmatter-extras.yamlasset579 bytesreferences/common-tour-failures.mddoc5,873 bytesreferences/completion-tracking-and-re-trigger.mddoc7,291 bytesreferences/contextual-placement-patterns.mddoc6,927 bytesreferences/dismissal-and-non-intrusion-patterns.mddoc7,153 bytesreferences/power-user-vs-new-user-patterns.mddoc7,350 bytesreferences/tour-anti-patterns.mddoc7,293 bytesreferences/tour-architecture-patterns.mddoc6,595 bytesreferences/tour-decision-criteria.mddoc6,966 bytesreferences/trigger-logic-patterns.mddoc7,198 bytes
Read SKILL.md
# Interactive Product Tour
A senior product marketing director's playbook for designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. The discipline of building help systems that surface at moments of need and disappear when not needed.
Most product tours fail in one of two ways. They paint every button, link, and feature with "click for tour" hints until the visual noise is so great that users develop blindness to the dots. Or they show a single first-login tour the user skips or skims, after which the same help never re-surfaces when the user actually hits a moment of friction. Help that is invisible at the moment of need is help that does not exist.
The tours that work do something different. They trigger when the user is at a moment of friction, not all the time. They surface contextual hints when the user enters a section they have not explored, clicks into a feature requiring setup, or returns after a long absence. The system knows what the user knows and surfaces help at the right moment.
The voice is the senior product marketing director who has watched feature adoption double when tours were redesigned and watched it collapse when more tooltips were piled onto every surface. Practical, opinionated about the trigger logic that distinguishes useful help from visual noise, willing to call out when no in-product tour at all is the right answer.
When to use this skill: scoping an in-product help system for the first time, auditing a tour system that produces engagement metrics with no adoption lift, designing the trigger logic that decides when help surfaces, or deciding which features warrant tours vs documentation.
---
internationalization
When your agent uses it
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled internationalization rollout. Triggers on internationalization, i18n, localization, l10n, hreflang, multi-language, translation workflow, RTL, locale, ccTLD, subfolder vs subdomain, language switcher. Also triggers when international audiences underperform or translations are stale.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,643 tokensWhen the skill is activated
Reference documents
2,029 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore12,246 bytesSKILL.mdcore12,246 bytesSKILL.mdcore12,246 bytesSKILL.mdcore12,246 bytesSKILL.mdcore12,246 bytesSKILL.mdcore12,246 bytesreferences/_claude-frontmatter-extras.yamlasset400 bytesreferences/locale-checklist.mddoc8,829 bytes
Read SKILL.md
# Internationalization
Add languages and regions in a way that works for users, search engines, and the team maintaining the content. Stack-agnostic.
---
## When to use
- Adding the first non-English (or non-default) language
- Adding additional locales to an existing internationalized site
- Choosing URL structure for languages
- Implementing hreflang tags
- Designing translation workflow
- Handling currency, date, time, and number formatsjourney-mapping
When your agent uses it
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the user experience, or visualize touchpoints and pain points. Triggers on customer journey, journey map, service blueprint, user journey, experience map, touchpoint analysis, friction map, journey audit, end-to-end experience, customer experience map. Also triggers when the team has departmental views of users but no shared map of what the experience actually feels like.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
2,118 tokensWhen the skill is activated
Reference documents
1,721 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 deliverables
- Common phases by product type
- How to gather the inputs
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,891 bytesSKILL.mdcore9,891 bytesreferences/_claude-frontmatter-extras.yamlasset391 bytesreferences/journey-map-template.mddoc6,875 bytes
Read SKILL.md
# Journey Mapping
Build journey maps and service blueprints that surface friction, align teams, and identify opportunities. Stack-agnostic. Tool-agnostic.
This skill is for mapping the experience. For testing specific touchpoints, use `usability-testing`. For broader generative research, use `ux-research`. For analyzing conversion, use `cro-optimization`.
---
## When to use
- Departments have different mental models of the customer experience
- Customer experience feels disjointed across touchpoints
- Specific friction or drop-off points need diagnosis
- Strategic planning needs a shared view of the userjtbd-framing
When your agent uses it
The Jobs-to-be-Done framework as applied product methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity (discovery, prioritization, positioning) and where it becomes performative ritual (job-statement workshops that do not drive decisions, persona-theater disguised as JTBD). Triggers on jobs-to-be-done, JTBD, job statements, struggling moments, hire criteria, fire criteria, switch triggers, functional emotional social jobs, outcome-driven innovation. Also triggers when a team is over-relying on feature-request lists or persona archetypes that do not drive product decisions, when a positioning conversation needs the framing JTBD provides, or when discovery is producing outputs that do not connect to product strategy.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
4,323 tokensWhen the skill is activated
Reference documents
16,384 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Feature-request-list vs persona-theater vs job-framing
- The job statement structure
- Identifying struggling moments
- Hire and fire criteria
- Functional, emotional, and social dimensions of jobs
- Where JTBD adds clarity vs where it becomes ritual
- Applying JTBD to discovery, prioritization, positioning
- Common failure modes
- The framework: 12 considerations for JTBD framing
- If required data is unavailable
- Reference files
- Closing: jobs over features
Files
SKILL.mdcore21,488 bytesSKILL.mdcore21,488 bytesreferences/_claude-frontmatter-extras.yamlasset541 bytesreferences/applying-jtbd-to-discovery.mddoc10,969 bytesreferences/applying-jtbd-to-positioning.mddoc10,319 bytesreferences/applying-jtbd-to-prioritization.mddoc11,069 bytesreferences/common-jtbd-failures.mddoc11,018 bytesreferences/functional-emotional-social-dimensions.mddoc10,358 bytesreferences/hire-and-fire-criteria.mddoc10,674 bytesreferences/identifying-struggling-moments.mddoc9,877 bytesreferences/job-statement-structure-patterns.mddoc9,309 bytes
Read SKILL.md
# Jobs-to-be-Done Framing
A senior product leader's playbook for the Jobs-to-be-Done framework as applied methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity and where it becomes performative ritual.
JTBD has become one of the more cited and less practiced frameworks in product. Teams cite it in strategy docs, run job-statement workshops, produce wall-sized artifacts, and continue building from feature requests and persona archetypes the next quarter. The methodology gets the credit; the practice gets skipped.
This skill is JTBD as applied product methodology. The framework's actual contribution: surfacing what users are trying to ACCOMPLISH (the job) rather than treating users as preference-aggregators (feature requests) or demographic archetypes (persona theater). When the framing is grounded in struggling moments and hire/fire criteria, it produces decisions; when it stops at the job-statement worksheet, it produces ritual.
This skill is honest about both modes. JTBD genuinely earns its keep in discovery, prioritization, and positioning when applied with rigor. It becomes ceremony when teams treat job statements as deliverables rather than as analytical tools.
The voice is the senior product leader who has used JTBD well and watched plenty of teams use it badly. Concrete, opinionated about what the framework actually contributes, willing to call out where it gets oversold.
When to use this skill: applying JTBD to a discovery cycle, replacing persona-driven prioritization with job-driven prioritization, reframing positioning around what users hire the product to do, or auditing whether existing JTBD work in the org is driving decisions.
landing-page-copy
When your agent uses it
Write landing page copy with attention to the hero, value proposition, social proof, objection handling, and conversion-focused CTAs. Use this skill whenever the user wants to write a landing page, sales page, hero section, or any conversion-focused web copy. Triggers on landing page, sales page, hero copy, value proposition, headline, subheadline, hero section, CTA copy, conversion copy, opt-in page, squeeze page. Also triggers when the user has a marketing campaign or product launch needing dedicated conversion copy. Use `cro-optimization` instead when the page already exists and the ask is to lift its conversion rate through testing rather than to write the copy.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,480 tokensWhen the skill is activated
Reference documents
3,999 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 sections
- The CTA itself
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,708 bytesSKILL.mdcore10,708 bytesreferences/_claude-frontmatter-extras.yamlasset376 bytesreferences/hero-formulas.mddoc7,286 bytesreferences/objection-library.mddoc10,581 bytes
Read SKILL.md
# Landing Page Copy
Write copy for pages with a single conversion goal: signup, purchase, demo request, download, lead capture. Stack-agnostic.
This skill is narrower than `content-and-copy`. Landing pages exist to drive a specific action, not to inform broadly.
---
## When to use
- Writing a hero section for a homepage or product page
- Writing a sales page or long-form sales letter
- Drafting opt-in or lead-capture page copy
- Campaign-specific landing pageslaunch-runbook
When your agent uses it
Plan and execute a launch runbook covering pre-launch verification, go-live procedures, DNS cutover, post-launch monitoring, and rollback procedures. Use this skill whenever the user is preparing to launch a website or product, planning a DNS cutover, building a go-live checklist, or executing a launch day. Triggers on launch runbook, go-live, launch day, DNS cutover, deploy to production, site launch, product launch, cutover plan, launch checklist, deployment procedure. Also triggers when a launch is approaching and the team needs structured coordination, even if 'runbook' is not explicitly stated.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,742 tokensWhen the skill is activated
Reference documents
2,124 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Roles and responsibilities
- Rollback criteria
- Communication plan
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore7,761 bytesreferences/_claude-frontmatter-extras.yamlasset383 bytesreferences/runbook-template.mddoc8,785 bytes
Read SKILL.md
# Launch Runbook
Plan and execute the launch of a website, product, or major release. The runbook is the document everyone uses on launch day. Stack-agnostic.
This skill is for the launch event. For pre-launch QA, use `qa-testing`. For post-launch incident handling, use `incident-response`.
---
## When to use
- Launching a new website or major redesign
- Migrating from one platform to another
- Releasing a major product or feature
- Coordinating cross-team launcheslead-magnet-design
When your agent uses it
Designing lead magnets that earn the email. The discipline of building gated content (ebooks, templates, checklists, swipe files, mini-courses, free tools) that delivers genuine standalone value while qualifying the lead and warming them for what comes next. Honest about thin-bait (overpromises, underdelivers), kitchen-sink-resource (everything, helps with nothing), and earned-value-magnet (delivers standalone value while qualifying the lead). Triggers on lead magnet, gated content, opt-in offer, ebook, checklist, template, swipe file, mini-course, free tool, content upgrade, freebie, opt-in, list-building offer. Also triggers when an audience is being asked for an email and the offer attached to that ask needs design discipline, when previous lead magnets converted but did not produce qualified leads, or when a lead magnet is being scoped for the first time.
What it loads into context
Frontmatter
188 tokensAlways available to the agent
SKILL.md
5,090 tokensWhen the skill is activated
Reference documents
19,206 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The lead magnet decision: when to build one, when not to
- Thin-bait vs kitchen-sink-resource vs earned-value-magnet
- Format selection
- The "would they pay for this" test
- Audience-fit qualification
- Title and presentation discipline
- Delivery and follow-up sequence design
- Format-specific quality gates
- Common failure modes
- The framework: 12 considerations for lead magnet design
- If required data is unavailable
- Reference files
- Closing: magnets earn the email when they earn the reader's afternoon
Files
SKILL.mdcore24,758 bytesSKILL.mdcore24,758 bytesSKILL.mdcore24,758 bytesSKILL.mdcore24,758 bytesSKILL.mdcore24,758 bytesSKILL.mdcore24,758 bytesreferences/_claude-frontmatter-extras.yamlasset578 bytesreferences/audience-fit-qualification.mddoc10,332 bytesreferences/common-lead-magnet-failures.mddoc10,585 bytesreferences/delivery-and-follow-up-sequences.mddoc10,478 bytesreferences/format-selection-patterns.mddoc10,248 bytesreferences/format-specific-quality-gates.mddoc11,226 bytesreferences/lead-magnet-anti-patterns.mddoc10,160 bytesreferences/lead-magnet-decision-criteria.mddoc9,683 bytesreferences/title-and-presentation-discipline.mddoc10,262 bytesreferences/would-they-pay-for-this-test.mddoc9,875 bytes
Read SKILL.md
# Lead Magnet Design
A senior growth practitioner's playbook for designing lead magnets that earn the email. Templates, checklists, swipe files, mini-courses, free tools, ebooks. The discipline of building gated content that delivers genuine standalone value while qualifying the lead and warming them for the next conversation.
Most lead magnets are bait. A vague headline, a thin PDF, an email gate, a follow-up sequence the reader resents. Conversion-rate metrics look fine because the form converted; the email list grows; and the unsubscribe rate climbs because the magnet was a transaction the reader regrets the moment they download.
The lead magnets that work as compounding assets do something different. They deliver value the reader would have paid for if they had to. They qualify the lead by audience-fit, so the list that grows is the right list. They set up the next conversation honestly, so the follow-up sequence is a continuation rather than an apology.
This skill is the parent-frame methodology for the growth tooling track. Calculators (`calculator-design`) and quizzes (`quiz-and-assessment-design`) are specific lead-magnet types covered as their own skills. This skill provides the methodology for deciding WHAT to build before deciding WHAT TYPE.
The voice is the senior growth practitioner who has watched lead magnets earn long-term subscribers and watched them burn list trust within a single send. Practical, opinionated about format selection, willing to tell the reader when a lead magnet is the wrong investment for the goal.
When to use this skill: scoping a lead magnet for the first time, auditing a lead magnet that converts but does not qualify, deciding which format fits a specific audience and offer, or designing the post-download sequence that turns the magnet into a relationship.
logo-design
When your agent uses it
Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from `brand-identity`, which produces the complete system (logo plus color, type, voice, applications). Goes deep on the logo specifically: typographic register, symbol approach, application-context discipline (16px favicon, embroidery, signage, motion), and production specs (SVG-ready, single-color, reverse). Triggers on logo design, design a logo, wordmark, monogram, lockup, mark variants, logo iterations, redesign or refine the logo, logo refresh, letterform-as-symbol, and exploring mark variants for an established brand. Does NOT fire for full brand identity (use `brand-identity`), positioning or strategy (use `brand-discovery`), project-wide creative direction (use `creative-direction`), or one-off illustration.
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
4,879 tokensWhen the skill is activated
Reference documents
25,010 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 considerations for logo design
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore23,220 bytesreferences/_claude-frontmatter-extras.yamlasset447 bytesreferences/application-contexts.mddoc17,153 bytesreferences/architectures-explained.mddoc14,068 bytesreferences/category-conventions.mddoc24,902 bytesreferences/client-package.mddoc10,036 bytesreferences/example-variant-spec.mddoc9,457 bytesreferences/symbol-approaches.mddoc20,630 bytesreferences/typographic-registers.mddoc20,910 bytes
Read SKILL.md
# Logo Design
A logo is a system of marks, not a single drawing. This skill produces multiple production-grade variants exploring different architectural approaches, each with rationale, application specs, and a clear position on what it signals and rejects.
The output is decision material, not a finished logo. The brand owner selects from the variants and the skill produces production refinement on the chosen direction.
---
## When to use
- The brand has a name and tonal direction; the deliverable is logo work specifically
- Generating 6 to 12 variants for client review and selection
- Refining a wordmark to production: kerning, optical adjustments, weight selection
- Exploring symbol options to pair with an existing wordmarklong-form-content-frameworks
When your agent uses it
Patterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guides, manifestos, ebooks, long-form tutorials. The structural disciplines that distinguish publication-quality long-form from bloggy-long padding or academic bloat. Different from pillar-content-architecture (which covers hub structure); this skill covers individual deep-dive pieces. Triggers on long-form content, case study writing, whitepaper, research report, definitive guide, ebook, manifesto, long-form tutorial, deep-dive article, anchor piece, foundational article, structural archetypes. Also triggers when a piece is over 3,000 words and the team is unsure how to structure it, when a long-form draft feels padded or saggy, or when a flagship asset needs the depth to actually earn the length.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
6,223 tokensWhen the skill is activated
Reference documents
19,723 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Bloggy-long vs academic-bloat vs publication-quality
- Long-form formats and when each fits
- Structural archetypes
- Section weight calibration
- Lede patterns for long-form
- Sustaining attention across 5,000+ words
- Citations and source authority
- Visualization and breakouts
- Closing patterns
- Distribution implications for long-form
- Common failure modes
- The framework: 12 considerations for long-form content
- If required data is unavailable
- Reference files
- Closing: long-form earns its length or it does not
Files
SKILL.mdcore29,819 bytesSKILL.mdcore29,819 bytesSKILL.mdcore29,819 bytesSKILL.mdcore29,819 bytesreferences/_claude-frontmatter-extras.yamlasset585 bytesreferences/attention-sustaining-techniques.mddoc9,928 bytesreferences/breakouts-and-visualization.mddoc10,656 bytesreferences/citation-and-source-authority.mddoc10,608 bytesreferences/closing-patterns.mddoc12,274 bytesreferences/common-long-form-failures.mddoc11,920 bytesreferences/format-decision-framework.mddoc10,895 bytesreferences/lede-patterns-for-long-form.mddoc10,091 bytesreferences/section-weight-calibration.mddoc9,590 bytesreferences/structural-archetype-patterns.mddoc10,668 bytes
Read SKILL.md
# Long-Form Content Frameworks
A senior editorial leader's playbook for individual long-form content pieces. The structural disciplines that distinguish publication-quality work from bloggy-long padding or academic bloat.
Long-form is where most content programs lose their nerve or lose their way. Teams either stretch a 1,500-word post to 5,000 with filler (the bloggy-long failure mode), or they over-document the topic with no editorial spine (the academic-bloat failure mode). The pieces that earn their length are the ones where each section justifies its weight, the lede sets a thesis the body actually delivers, and the closing leaves the reader with something specific.
This skill covers the individual long-form piece: the case study, the whitepaper, the research report, the manifesto, the ebook chapter or full ebook, the definitive guide, the long-form tutorial. Different from `pillar-content-architecture` (which covers HUB architecture: how a pillar plus cluster system fits together), this skill covers the long-form PIECE itself, regardless of whether it sits at the center of a hub or stands alone.
The voice is the senior editorial leader who has shipped dozens of flagship long-form assets and watched plenty of others fail. Honest about which formats earn their length, which structural archetypes fit which problems, and where long-form most often goes wrong.
When to use this skill: planning a flagship long-form piece, structuring a draft that feels saggy, reviewing a long-form piece that is technically correct but emotionally flat, or auditing a content library to find the long-form pieces that should have been blog posts.
---
media-asset-management
When your agent uses it
Plan and run a media pipeline for images, video, and downloadable assets. Use this skill when designing image storage and delivery, choosing formats (WebP, AVIF), setting up responsive images, picking a video host, organizing a brand asset library, or auditing a slow image pipeline. Triggers on image pipeline, asset library, DAM, image optimization, WebP, AVIF, responsive images, video hosting, image CDN, asset workflow, media management. Also triggers when images are slow, broken, or scattered across systems.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,696 tokensWhen the skill is activated
Reference documents
2,796 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Format reference
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesSKILL.mdcore12,037 bytesreferences/_claude-frontmatter-extras.yamlasset405 bytesreferences/responsive-image-patterns.mddoc10,442 bytes
Read SKILL.md
# Media Asset Management
Design how images, video, and downloadable files get stored, processed, organized, and served. Stack-agnostic. The principles apply whether you're running a custom pipeline or using a hosted service.
---
## When to use
- Designing or redesigning the image and media pipeline
- Choosing a media CDN or image service
- Setting up responsive image delivery
- Planning a digital asset management (DAM) system
- Auditing media performance issues
- Picking video hosting and embedding strategymonitoring-and-alerting
When your agent uses it
Design and run a monitoring system for a website or web app. Use this skill when setting up uptime checks, defining SLOs, configuring error tracking, choosing what to alert on, designing on-call rotations, or fixing alert fatigue. Triggers on monitoring, alerts, uptime, SLO, SLA, error rate, on-call, pager, alert fatigue, observability, dashboards, what should we monitor. Also triggers when an incident reveals a gap in monitoring.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,398 tokensWhen the skill is activated
Reference documents
2,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- SLOs and error budgets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,338 bytesSKILL.mdcore10,338 bytesreferences/_claude-frontmatter-extras.yamlasset400 bytesreferences/slo-design-guide.mddoc9,231 bytes
Read SKILL.md
# Monitoring and Alerting
Decide what to watch, what to alert on, and how to make sure the right person finds out when things break.
---
## When to use
- Setting up monitoring on a new site or service
- Defining SLOs (service level objectives) and error budgets
- Choosing which alerts page someone vs which go to a quiet channel
- Designing or fixing on-call rotation
- Diagnosing alert fatigue
- Filling monitoring gaps revealed by an incidentmulti-step-form-design
When your agent uses it
Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent. Honest about kitchen-sink-single-page (overwhelms before the user starts), progress-theater (steps without genuine staging), and genuinely-staged (each step earns its own page) patterns. Triggers on multi-step form, multi-page form, form wizard, signup wizard, lead form, application form, intake form, configurator, onboarding form. Also triggers when a long form is converting poorly, when an audience is dropping off mid-form, or when a multi-step form is being scoped for the first time.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
4,437 tokensWhen the skill is activated
Reference documents
18,460 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The multi-step decision: when to break into steps vs keep single-page
- Kitchen-sink-single-page vs progress-theater vs genuinely-staged
- Step architecture: what belongs on each step
- Progress indicator design
- Conditional logic
- Save-and-resume mechanics
- Validation strategy
- Drop-off measurement and remediation
- Form anti-patterns
- Common failure modes
- The framework: 12 considerations for multi-step form design
- If required data is unavailable
- Reference files
- Closing: multi-step forms earn completion when each step earns its place
Files
SKILL.mdcore21,638 bytesSKILL.mdcore21,638 bytesreferences/_claude-frontmatter-extras.yamlasset594 bytesreferences/common-multi-step-form-failures.mddoc9,115 bytesreferences/conditional-logic-patterns.mddoc9,842 bytesreferences/drop-off-measurement-and-remediation.mddoc10,513 bytesreferences/form-anti-patterns.mddoc9,904 bytesreferences/multi-step-decision-criteria.mddoc9,397 bytesreferences/progress-indicator-patterns.mddoc9,529 bytesreferences/save-and-resume-mechanics.mddoc10,296 bytesreferences/step-architecture-patterns.mddoc10,195 bytesreferences/validation-strategy-patterns.mddoc10,607 bytes
Read SKILL.md
# Multi-Step Form Design
A senior growth practitioner's playbook for designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent.
Most multi-step forms are either kitchen-sink-single-pages dressed up as steps or arbitrary chunking that adds friction without adding clarity. The form looks more sophisticated; the completion rate does not move; the audience is no better served than before.
The multi-step forms that work do something different. Each step represents a coherent unit of cognitive work the user can complete with confidence. Progress indicators reinforce momentum. Conditional logic responds to earlier answers and removes irrelevant fields. The form feels like a guided process, not an obstacle course.
The voice is the senior growth practitioner who has watched multi-step forms convert at twice the single-page rate and watched them collapse to half. Practical, opinionated about when steps add value and when they add friction, willing to call out arbitrary chunking that does not earn its complexity.
When to use this skill: scoping a multi-step form for the first time, auditing a long single-page form that converts poorly, deciding when to break a form into steps and when to keep it on one page, or designing the conditional logic that makes the form feel adaptive.
---
okr-design
When your agent uses it
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition with quarterly accountability). Triggers on OKR design, OKR setting, key result design, OKR scoring, mid-quarter recalibration, OKR cascading, outcomes vs outputs, quarterly planning, goal setting. Also triggers when a team's OKRs are always hit and producing no learning, when OKRs are demoralizing because they were set as fantasy, or when the team uses OKR vocabulary but the practice has decayed.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
4,791 tokensWhen the skill is activated
Reference documents
18,538 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Sandbagged vs aspirational-fantasy vs stretch
- Objective design
- Key result design
- Cascading OKRs across the org
- Scoring discipline
- Mid-quarter recalibration
- The OKR review cadence
- OKRs vs roadmap items vs metrics
- Common failure modes
- The framework: 12 considerations for OKR design
- If required data is unavailable
- Reference files
- Closing: OKRs are accountability infrastructure
Files
SKILL.mdcore22,139 bytesSKILL.mdcore22,139 bytesreferences/_claude-frontmatter-extras.yamlasset589 bytesreferences/cascading-okrs-decisions.mddoc9,261 bytesreferences/common-okr-failures.mddoc9,801 bytesreferences/key-result-design-patterns.mddoc10,108 bytesreferences/mid-quarter-recalibration.mddoc9,998 bytesreferences/objective-design-patterns.mddoc9,503 bytesreferences/okr-anti-patterns.mddoc10,791 bytesreferences/okrs-vs-roadmap-vs-metrics.mddoc9,051 bytesreferences/review-cadence-templates.mddoc9,910 bytesreferences/scoring-discipline.mddoc9,650 bytes
Read SKILL.md
# OKR Design
A senior product leader's playbook for OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the practical disciplines that distinguish OKRs from quarterly to-do lists or impossible-fantasy goal-setting.
OKRs are accountability infrastructure. When designed well, they produce a quarterly rhythm of ambitious goal-setting, mid-quarter learning, end-of-quarter scoring, and adjustment for the next quarter. When designed badly, they become a tax on the team that produces no signal: sandbagged OKRs that always hit 100% (no ambition, no learning), aspirational fantasy OKRs that nobody can hit (demoralizing, ignored after week 2), or vague OKRs that the team scores generously regardless of outcome.
This skill is OKR design as practical methodology. The teams that benefit from OKRs are the ones that hold the discipline: outcomes over outputs, key results that actually measure the outcome, scoring honestly even when uncomfortable, recalibrating mid-quarter when warranted, and using the OKR review cadence to drive learning rather than performance theater.
The voice is the senior product leader who has run OKRs in healthy organizations and watched the practice decay in others. Concrete, opinionated about what actually works, willing to call out the failure modes that conference talks gloss over.
When to use this skill: designing OKRs for the next quarter, auditing why current OKRs are not driving decisions, recalibrating an OKR practice that has decayed, or onboarding a team to OKRs that has never used them.
---
onboarding-wizard-design
When your agent uses it
Designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. Honest about tutorial-overload (dump everything upfront), skip-friendly-empty (skipped onboarding leads to abandoned product), and earned-progressive-disclosure (right things at the right moments) patterns. Triggers on onboarding wizard, product onboarding, first-run experience, signup flow, activation flow, FRX, time-to-value, ah-ha moment design. Also triggers when activation rates are low, when users skip onboarding and never return, when onboarding flows are being scoped for the first time, or when audience research shows users not finding key features.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
4,187 tokensWhen the skill is activated
Reference documents
13,942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The wizard decision: when wizards earn vs when contextual help suffices
- Tutorial-overload vs skip-friendly-empty vs earned-progressive-disclosure
- Step architecture: what belongs in each step, sequence logic
- The ah-ha moment design
- Progressive disclosure patterns
- Skip and resume mechanics
- Drop-off measurement and remediation
- Wizard variations by user type
- Common failure modes
- The framework: 12 considerations for onboarding wizard design
- Reference files
- Closing: wizards earn the user's first session
Files
SKILL.mdcore20,411 bytesreferences/_claude-frontmatter-extras.yamlasset595 bytesreferences/ah-ha-moment-engineering.mddoc8,665 bytesreferences/common-onboarding-failures.mddoc6,305 bytesreferences/drop-off-measurement-templates.mddoc7,421 bytesreferences/progressive-disclosure-patterns.mddoc7,744 bytesreferences/skip-and-resume-mechanics.mddoc8,137 bytesreferences/step-architecture-patterns.mddoc8,267 bytesreferences/user-type-variation-patterns.mddoc6,413 bytesreferences/wizard-anti-patterns.mddoc7,636 bytesreferences/wizard-decision-criteria.mddoc7,484 bytes
Read SKILL.md
# Onboarding Wizard Design
A senior product marketing director's playbook for designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. The discipline of building an onboarding sequence the user actually completes.
Most product onboarding wizards fail in one of two ways. They cram every feature into a 12-step intro the user has not earned the patience for. Or they offer a "skip onboarding" button so prominent that users skip into an empty product with no context, and then churn the next day because they never found the value. The activation rate is the metric that matters, and most wizards are optimizing for the wrong thing.
The wizards that work do something different. Each step earns the user one step closer to value. The wizard surfaces the right thing at the right moment, not everything upfront. Skip exists but is balanced against staying engaged. The user reaches the ah-ha moment with a sense that the product respected their time.
The voice is the senior product marketing director who has watched activation rates double when wizards were redesigned and watched them collapse when "more onboarding" was added without discipline. Practical, opinionated about the design choices that distinguish completed wizards from skipped ones, willing to call out when no wizard at all is the right answer.
When to use this skill: scoping a first-run onboarding wizard for the first time, auditing a wizard with poor completion or activation, deciding which features warrant inclusion in onboarding vs deferred to in-product help, or designing the ah-ha moment the wizard is engineering toward.
---
oss-contribution-research
When your agent uses it
Research and prepare an outside contribution to an open-source repo, then stop at a queue item for a human to approve: policy check, intake, duplicate check, reproduction, patch, the repo's own checks, an independent critic rerun, and a disclosed, hashed draft of the exact text to post. Use this skill whenever the user wants to contribute to someone else's repo, fix an upstream bug, pick up a good-first-issue, draft an AI-assisted pull request for an outside project, follow up on their own outside PR, or run a gated contribution pipeline. Triggers on open source contribution, contribute to this repo, upstream fix, outside PR, external PR, good first issue, fix this issue in their repo, contribution research, AI-assisted PR, disclose AI in PR, reply to review on my PR. Also triggers when the user names an issue in a repo they do not maintain and asks for a fix, even if they do not say contribute.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
4,403 tokensWhen the skill is activated
Reference documents
6,201 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: gates in order, stop at the first fail
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore19,108 bytesSKILL.mdcore19,108 bytesSKILL.mdcore19,108 bytesSKILL.mdcore19,108 bytesreferences/_claude-frontmatter-extras.yamlasset440 bytesreferences/example-intake-item.mddoc3,366 bytesreferences/policy-classification.mddoc5,088 bytesreferences/pr-description-template.mddoc5,476 bytesreferences/queue-item-template.mddoc6,802 bytesreferences/repro-record-template.mddoc4,985 bytes
Read SKILL.md
# OSS Contribution Research
Prepare one outside contribution to an open-source repo, gate by gate, and stop at a queue item a human approves. The agent running this skill never posts.
---
## When to use
- Picking up an existing issue or confirmed bug in a repo the user does not maintain
- Checking whether a repo accepts AI-assisted pull requests before any work starts
- Asking a maintainer for a go-ahead before writing a patch (an intake comment)
- Turning a fix into a small, disclosed pull request draft that a human approves
- Following up on the user's own outside pull request: a review reply, the 14-day ping, or the 28-day close
- Running a contribution pipeline with an approval queue and a per-repo registrypaid-media-strategy
When your agent uses it
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media strategy, ad budget allocation, channel selection, paid media plan, audit my Google Ads, audit my Meta Ads, scale paid media, kill underperforming campaign, paid media hypothesis, ad spend strategy, attribution reality, performance marketing strategy. Also triggers when a team is asking how to scale paid media, or whether to add a new channel, or how to reallocate spend across channels.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
4,620 tokensWhen the skill is activated
Reference documents
10,603 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hypothesis discipline for paid spend
- Channel selection: when to use which platform
- Budget allocation: brand vs performance, baseline vs test
- Audience targeting: prospecting vs retargeting vs exclusion
- Bid strategy: when each fits
- Campaign types
- What NOT to spend on
- Creative testing: within campaign vs across campaign
- Frequency capping
- Attribution mismatch: platform-reported vs actual
- Common failures
- The framework: 11 considerations for sustainable paid media
- If required data is unavailable
- Reference files
- Closing: when in doubt, kill the campaign
Files
SKILL.mdcore22,161 bytesSKILL.mdcore22,161 bytesSKILL.mdcore22,161 bytesSKILL.mdcore22,161 bytesreferences/_claude-frontmatter-extras.yamlasset502 bytesreferences/ads-platform-comparison.mddoc7,238 bytesreferences/audience-segmentation-patterns.mddoc6,779 bytesreferences/bid-strategy-reference.mddoc6,441 bytesreferences/budget-allocation-templates.mddoc5,725 bytesreferences/campaign-type-reference.mddoc8,243 bytesreferences/channel-decision-matrix.mddoc5,956 bytesreferences/common-failures.mddoc8,642 bytes
Read SKILL.md
# Paid Media Strategy
A senior performance marketer's playbook for running paid media that produces real outcomes.
The default state of paid media is wasted spend. Most accounts have campaigns running because they always have, audiences targeting because the rep suggested it, bid strategies on auto because manual is hard, creative not refreshed because there is no system. The cost compounds. A 20% efficiency gain on a $500K-per-year account is $100K back to the business. A 50% gain on a $5M-per-year account is $2.5M.
This skill is the discipline that produces those gains. It assumes you have a paid media platform (Google Ads, Meta, LinkedIn, TikTok, or aggregators like Synter) connected. It assumes you have working analytics and conversion tracking. The hard part is the strategic discipline behind the spend, and that is what is here.
When to use this skill: any time you are designing a paid media plan, evaluating whether to scale or kill a campaign, allocating budget across channels, or auditing an existing account.
---
## What this skill is for
performance-optimization
When your agent uses it
Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,424 tokensWhen the skill is activated
Reference documents
5,168 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: Core Web Vitals
- Beyond Core Web Vitals
- Workflow
- Tools
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,649 bytesSKILL.mdcore10,649 bytesSKILL.mdcore10,649 bytesreferences/_claude-frontmatter-extras.yamlasset398 bytesreferences/audit-template.mddoc5,602 bytesreferences/optimization-checklist.mddoc5,634 bytesreferences/optimization-playbook.mddoc9,303 bytes
Read SKILL.md
# Performance Optimization
Diagnose web performance issues and produce a remediation plan. Stack-agnostic. Anchored to Core Web Vitals and standard browser performance patterns.
This skill goes deeper than the performance checks in `qa-testing` and `seo-technical`. Use this when performance itself is the goal.
---
## When to use
- Fixing Core Web Vitals (LCP, INP, CLS)
- Diagnosing slow page loads
- Reducing JavaScript bundle size
- Optimizing images, fonts, and other assetspillar-content-architecture
When your agent uses it
How to design a content hub that earns topical authority. Pillar topic selection, cluster planning, internal linking architecture, URL structure, pillar and cluster page anatomy, topical authority signals for SEO and AEO/GEO, and the maintenance discipline that distinguishes intentional hubs from accidental orphans. Triggers on pillar content, content hub, topic cluster, topical authority, content architecture, hub and spoke, pillar page, cluster page, content silo, internal linking strategy. Also triggers when a content set is not ranking despite individual piece quality, when a pillar was launched without a cluster, or when content has accumulated without an architecture.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
4,674 tokensWhen the skill is activated
Reference documents
15,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Pillar vs cluster vs orphan content
- Topic selection for pillar pages
- Cluster planning
- Internal linking architecture
- URL structure and information architecture
- Pillar page anatomy
- Cluster piece anatomy
- Topical authority signals
- Maintenance and refresh patterns
- Common failure modes
- The framework: 12 considerations for hub architecture
- If required data is unavailable
- Reference files
- Closing: architecture is the moat
Files
SKILL.mdcore21,853 bytesSKILL.mdcore21,853 bytesreferences/_claude-frontmatter-extras.yamlasset527 bytesreferences/cluster-piece-anatomy.mddoc6,439 bytesreferences/cluster-planning-patterns.mddoc6,294 bytesreferences/common-pillar-failures.mddoc9,390 bytesreferences/content-refresh-patterns.mddoc7,972 bytesreferences/internal-linking-architecture.mddoc7,222 bytesreferences/pillar-cluster-decision.mddoc5,860 bytesreferences/pillar-page-anatomy.mddoc7,443 bytesreferences/topic-selection-criteria.mddoc6,377 bytesreferences/topical-authority-signals.mddoc7,006 bytesreferences/url-structure-patterns.mddoc6,327 bytes
Read SKILL.md
# Pillar Content Architecture
A senior content architect's playbook for designing content hubs that earn topical authority.
Most content programs accumulate accidentally. Pieces ship one at a time, internal linking happens (or does not) in editing, similar topics get covered by multiple pieces with no coordination, and six months later the team has a content set that looks like a sitemap but feels like a yard sale. Search engines see disconnected pages; AI engines see scattered citations; readers cannot tell which piece is the entry point and which is the reference.
This skill is the discipline of intentional hub architecture. It assumes you have decided which topic areas to invest in (see `content-strategy`) and have keyword data (see `seo-keyword`). It does not write any individual piece (see `content-brief-authoring` for per-piece work and `content-and-copy` for execution). What it does is design the structure: which topic gets a pillar, which subtopics get cluster pieces, how the pieces link to each other, where they live in the URL hierarchy, and what topical authority signals the architecture is engineered to produce.
When to use this skill: launching a new content hub, restructuring an existing content set into a hub, deciding whether a piece should be a pillar or a cluster, or auditing why a content area is not ranking despite individual piece quality.
---
## What this skill is for
pm-spec-writing
When your agent uses it
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
2,042 tokensWhen the skill is activated
Reference documents
4,248 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesreferences/_claude-frontmatter-extras.yamlasset381 bytesreferences/dev-brief-template.mddoc6,155 bytesreferences/feature-spec-template.mddoc4,691 bytesreferences/prioritization-frameworks.mddoc6,889 bytes
Read SKILL.md
# PM Spec Writing
Take an idea (often vague) and turn it into a specification a developer or AI agent can actually build from. Stack-agnostic. Works for new features, bug fixes, content changes, or infrastructure work.
---
## When to use
- Translating an idea into a buildable feature spec
- Writing a PRD or product requirement document
- Filing a bug report that someone else can act on
- Scoping a project before kickoff
- Prioritizing a backlog of feature requests
- Writing acceptance criteria for an existing featureproduct-analytics-setup
When your agent uses it
How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
4,934 tokensWhen the skill is activated
Reference documents
15,527 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The instrumentation hierarchy
- Event taxonomy design
- Property design: event-level vs user-level
- Naming conventions
- Schema versioning
- Funnel design
- Cohort definitions
- Retention measurement
- North Star and supporting metrics
- The trustable dashboard principle
- Instrumentation debt
- Common failure modes
- The framework: 12 considerations for trustable product analytics
- If required data is unavailable
- Reference files
- Closing: when in doubt, instrument less
Files
SKILL.mdcore23,480 bytesSKILL.mdcore23,480 bytesSKILL.mdcore23,480 bytesreferences/_claude-frontmatter-extras.yamlasset557 bytesreferences/cohort-definition-patterns.mddoc7,519 bytesreferences/common-failures.mddoc9,554 bytesreferences/event-taxonomy-template.mddoc7,741 bytesreferences/funnel-design-templates.mddoc7,741 bytesreferences/instrumentation-audit-checklist.mddoc7,398 bytesreferences/naming-convention-reference.mddoc5,956 bytesreferences/north-star-metric-selection.mddoc8,027 bytesreferences/property-design-patterns.mddoc6,781 bytesreferences/schema-versioning-patterns.mddoc7,061 bytes
Read SKILL.md
# Product Analytics Setup
A senior PM and analyst's playbook for instrumenting product analytics correctly the first time.
Most product analytics setups are some combination of inherited mistakes, dashboard sprawl, and events nobody trusts. The team launches a new feature; instrumentation gets bolted on under deadline pressure; naming drifts; properties are inconsistent; six months later nobody can answer simple questions because the answer depends on which event you trust.
This skill is the discipline that prevents that. It assumes you have answered the strategic questions about what to measure (see `analytics-strategy`). It assumes you have a tool connected (Mixpanel, Heap, PostHog, Amplitude, or warehouse-native via BigQuery, Snowflake, or dbt). The hard part is the systematic execution: naming conventions, property design, schema versioning, funnel construction, cohort definitions, retention measurement.
When to use this skill: setting up product analytics from scratch, auditing an existing instrumentation, fixing a "we have data but cannot trust it" problem, or designing instrumentation for a new feature.
---
## What this skill is for
product-configurator-design
When your agent uses it
Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus meaningful constraints plus escape hatches) patterns. Triggers on configurator design, build-your-own, custom configuration, plan builder, product customizer, configuration tool. Also triggers when users abandon mid-configuration, when configurator conversion is poor, or when a configurator is being scoped for the first time.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
3,200 tokensWhen the skill is activated
Reference documents
8,103 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The configurator decision: when configurators earn investment vs when bundles suffice
- Infinite-options vs canned-bundles-only vs guided-configuration
- Default-configuration design
- Constraint logic
- Real-time pricing and impact display
- Validation and error patterns
- Save-and-share mechanics
- Configurator-to-cart handoff
- Common failure modes
- The framework: 12 considerations for configurator design
- Reference files
- Closing: configurators earn investment when they earn the configuration that ships
Files
SKILL.mdcore16,420 bytesreferences/_claude-frontmatter-extras.yamlasset608 bytesreferences/common-configurator-failures.mddoc5,145 bytesreferences/configurator-anti-patterns.mddoc5,057 bytesreferences/configurator-decision-criteria.mddoc4,204 bytesreferences/configurator-to-cart-handoff.mddoc4,526 bytesreferences/constraint-logic-patterns.mddoc4,485 bytesreferences/default-configuration-design.mddoc2,978 bytesreferences/real-time-pricing-patterns.mddoc4,007 bytesreferences/save-and-share-mechanics.mddoc5,134 bytesreferences/validation-and-error-patterns.mddoc4,810 bytes
Read SKILL.md
# Product Configurator Design
A senior product marketing director's playbook for designing build-your-own product configurators. Tesla-style vehicle configurators, custom-pricing builders, plan-builders, product customizers. Constraint logic, real-time pricing, validation, save-and-share mechanics. The discipline of building a configurator that produces configurations users actually commit to.
Most configurators fail in one of two ways. They expose every parameter at full granularity (47 toggles, 12 sliders) and produce decision paralysis; users abandon halfway through. Or they pretend to be configurators but are actually three pre-built bundles labeled "Custom"; the configurator framing was marketing while the product is bundles.
The configurators that work do something different. Smart defaults that produce a sensible starting configuration; meaningful constraints that prevent invalid combinations and surface why; escape hatches into deeper customization for users who want it; real-time pricing that responds to choices. Users feel guided rather than overwhelmed.
The voice is the senior product marketing director who has watched configurators double conversion when redesigned with smart defaults and watched them collapse when "more options" were added without constraint logic. Practical, opinionated about the constraints that protect users from themselves, willing to call out when canned bundles are the right answer.
When to use this skill: scoping a build-your-own configurator for the first time, auditing a configurator with high abandonment, designing the constraint logic that prevents invalid combinations, or deciding which parameters earn exposure vs which should default.
---
programmatic-seo
When your agent uses it
How to design and run a programmatic SEO program that produces durable traffic instead of penalty-bait. Data source identification, template design, schema patterns, quality control at scale, internal linking architecture, crawl budget management, AEO/GEO for programmatic pages, refresh discipline, and the make-or-break question of whether pSEO is the right answer for your program at all. Triggers on programmatic SEO, pSEO, scaled content, page generation, template SEO, location pages, comparison pages, directory site, listing site, scaled landing pages, programmatic content. Also triggers when a content set is not ranking, has been hit by an algorithm update, or when a team is considering pSEO as a growth lever.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
5,110 tokensWhen the skill is activated
Reference documents
15,715 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When pSEO is the right answer
- Data source identification
- Template design
- Schema design
- Quality control at scale
- Internal linking across the set
- Crawl budget management
- AEO and GEO for programmatic pages
- Refresh and maintenance at scale
- Common failure modes
- The framework: 12 considerations for programmatic SEO
- If required data is unavailable
- Reference files
- Closing: quality at scale or not at all
Files
SKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesSKILL.mdcore24,820 bytesreferences/_claude-frontmatter-extras.yamlasset537 bytesreferences/aeo-geo-for-programmatic-pages.mddoc7,984 bytesreferences/common-pseo-failures.mddoc10,408 bytesreferences/crawl-budget-management.mddoc7,087 bytesreferences/data-source-identification-patterns.mddoc6,693 bytesreferences/internal-linking-at-scale.mddoc7,396 bytesreferences/quality-control-at-scale.mddoc7,880 bytesreferences/refresh-at-scale.mddoc7,454 bytesreferences/schema-design-patterns.mddoc7,817 bytesreferences/template-design-patterns.mddoc6,634 bytesreferences/when-pseo-works-decision.mddoc6,952 bytes
Read SKILL.md
# Programmatic SEO
A senior SEO strategist's playbook for designing and running programmatic SEO programs that produce durable traffic instead of penalty-bait.
Programmatic SEO has a complicated reputation. Sites like Zillow, Airbnb, TripAdvisor, Indeed, and Yelp have built billion-dollar traffic engines on pSEO. Other sites have built pSEO programs that got hit by Google's helpful-content updates and lost 80% of their traffic in a week. The difference is rarely the technique; it is the underlying data quality and the quality control discipline at scale.
This skill is the playbook for getting that distinction right. It assumes you have decided what keyword space to target (see `seo-keyword`) and how the broader content program is shaped (see `content-strategy`). It does not write individual editorial pieces (see `content-and-copy` for that) and does not architect editorial topic hubs (see `pillar-content-architecture` for that). What it does is teach the discipline of generating high-volume pages programmatically from structured data sources without producing thin content, duplicate content, or scale-without-substance pages that get penalized.
When to use this skill: deciding whether pSEO is a fit for the program at all (the most important question), designing a new pSEO system, auditing an existing pSEO set that is not ranking or has been hit by an algorithm update, or building quality-control discipline for a pSEO program that grew faster than its quality processes.
---
## What this skill is for
qa-testing
When your agent uses it
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.
What it loads into context
Frontmatter
176 tokensAlways available to the agent
SKILL.md
3,223 tokensWhen the skill is activated
Reference documents
1,174 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 tiers
- Specific QA snippets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,789 bytesSKILL.mdcore12,789 bytesreferences/_claude-frontmatter-extras.yamlasset375 bytesreferences/qa-report-template.mddoc4,363 bytes
Read SKILL.md
# QA Testing
Verify that a page, feature, or site is working before declaring it shipped. Stack-agnostic. Console-snippet driven for speed.
This skill is faster than `accessibility-audit` (which goes deeper on WCAG) and `performance-optimization` (which goes deeper on Core Web Vitals). Use this skill for general QA. Use the specialists for deep audits.
---
## When to use
- After every deploy (smoke test)
- After launching a new page or feature (standard audit)
- Before a major release (full release matrix)
- Investigating a "something looks off" reportquiz-and-assessment-design
When your agent uses it
Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.
What it loads into context
Frontmatter
161 tokensAlways available to the agent
SKILL.md
4,275 tokensWhen the skill is activated
Reference documents
18,897 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The quiz/assessment decision: when this format earns investment
- Clickbait-quiz vs vanity-result vs actionable-segmentation
- Question architecture
- Scoring algorithms
- Result categorization
- Result-to-recommendation mapping
- Lead capture integration
- Quiz anti-patterns
- Common failure modes
- The framework: 12 considerations for quiz and assessment design
- Reference files
- Closing: quizzes earn engagement when they earn the next step
Files
SKILL.mdcore21,319 bytesSKILL.mdcore21,319 bytesreferences/_claude-frontmatter-extras.yamlasset604 bytesreferences/clickbait-vs-actionable-distinctions.mddoc10,891 bytesreferences/common-quiz-failures.mddoc9,721 bytesreferences/lead-capture-integration-patterns.mddoc10,098 bytesreferences/question-architecture-patterns.mddoc10,502 bytesreferences/quiz-anti-patterns.mddoc10,555 bytesreferences/quiz-investment-criteria.mddoc9,217 bytesreferences/result-categorization-patterns.mddoc10,462 bytesreferences/result-to-recommendation-mapping.mddoc11,699 bytesreferences/scoring-algorithm-patterns.mddoc11,391 bytes
Read SKILL.md
# Quiz and Assessment Design
A senior growth practitioner's playbook for designing quizzes and assessments that produce actionable segmentation rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping. The discipline of building a quiz the audience actually uses to make a decision.
Most quizzes on the web are clickbait. "What kind of pizza are you?" energy applied to brand-building, with results that flatter the taker but drive no specific next step. The quiz captures emails because the format implies fun; the leads are unqualified because the result told them nothing they could act on.
The quizzes that work as compounding assets do something different. They categorize the taker into a defined segment with a specific recommendation matched to that segment. The taker comes away knowing what to do next, not just what they are. The brand becomes the source of the recommendation the audience acted on.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the quiz-specific methodology (scoring algorithms, result categorization, recommendation matching) lives here.
The voice is the senior growth practitioner who has watched quizzes earn long-term subscribers and watched them produce engagement metrics with no downstream impact. Practical, opinionated about the difference between fun-quiz and decision-quiz, willing to call out when a quiz is the wrong format for the goal.
When to use this skill: scoping a quiz or assessment for the first time, auditing a quiz that produces engagement but no qualified leads, designing the result categories that drive specific recommendations, or deciding which inputs warrant the lead-capture step.
roadmap-planning
When your agent uses it
Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next, sequencing, prioritization, OKR planning, capacity planning, what's on the roadmap, plan the year, what to ship next quarter. Also triggers when stakeholders are pulling in different directions and the team needs a defensible plan.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,438 tokensWhen the skill is activated
Reference documents
1,766 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,872 bytesreferences/_claude-frontmatter-extras.yamlasset385 bytesreferences/prioritization-frameworks.mddoc8,044 bytes
Read SKILL.md
# Roadmap Planning
Take a pile of ideas, requests, and ongoing work. Produce a defensible plan for what to ship, when, and why. The output is a roadmap document plus the prioritization work that made it credible.
---
## When to use
- Planning the next quarter or the next year
- Sequencing work where some items depend on others
- Balancing new builds, improvements, and maintenance
- Saying no (or "not yet") to specific requests with a defensible reason
- Aligning a team around a single shared plan
- Communicating the plan to stakeholders outside the teamscheduler-and-booking-design
When your agent uses it
Designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic Calendly link. Availability logic, qualification gating, prep automation, follow-up sequencing. Honest about any-time-friction (no qualification, just a booking link), interrogation-gate (so much qualification it scares users off), and qualified-fast-path (just enough qualification to set up the call well) patterns. Triggers on scheduler design, meeting booking, demo scheduling, sales call scheduling, calendar tool, booking page, qualification flow. Also triggers when sales team complains about cold demos, when booking conversion is poor, or when scheduler is being scoped for the first time.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
3,569 tokensWhen the skill is activated
Reference documents
12,565 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The booking-flow decision: scheduler vs forms vs sales-pipeline tools
- Any-time-friction vs interrogation-gate vs qualified-fast-path
- Qualification field design
- Availability logic
- Routing patterns
- Prep automation
- Confirmation and reminder sequences
- Reschedule and no-show handling
- Common failure modes
- The framework: 12 considerations for scheduler and booking design
- Reference files
- Closing: schedulers earn the booking when they earn the better call
Files
SKILL.mdcore17,425 bytesSKILL.mdcore17,425 bytesreferences/_claude-frontmatter-extras.yamlasset607 bytesreferences/availability-logic-patterns.mddoc7,422 bytesreferences/common-scheduler-failures.mddoc5,777 bytesreferences/prep-automation-patterns.mddoc7,162 bytesreferences/qualification-field-design.mddoc7,144 bytesreferences/reminder-sequence-patterns.mddoc6,530 bytesreferences/reschedule-and-no-show-handling.mddoc6,899 bytesreferences/routing-patterns.mddoc6,007 bytesreferences/scheduler-anti-patterns.mddoc5,811 bytesreferences/scheduler-decision-criteria.mddoc7,105 bytes
Read SKILL.md
# Scheduler and Booking Design
A senior growth practitioner's playbook for designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic booking link. Availability logic, qualification gating, prep automation, follow-up sequencing. The discipline of building a scheduler that earns the booking by earning a better call.
Most schedulers fail in one of two ways. Generic booking links produce cold demos where reps know nothing about the person they are about to talk to. Conversion stays at the rate of unqualified raw demos. Or qualification forms with 12 fields scare users off before they can book; drop-off at the form approaches 90 percent; only the leads who happen to survive the form actually convert.
The schedulers that work do something different. Just enough qualification to set up the call well (3-5 strategic fields), context-aware availability (high-fit leads see senior reps; low-fit leads route differently), prep automation that briefs the rep before the call. The booking is honest about who the audience is; the call is set up to succeed.
The voice is the senior growth practitioner who has watched schedulers double demo conversion when redesigned and watched them collapse when more qualification was added. Practical, opinionated about which fields earn their place, willing to call out when the booking flow is the wrong tool.
When to use this skill: scoping a scheduler for the first time, auditing a booking flow with poor conversion or poor downstream call quality, designing the qualification gate that produces context without producing friction, or deciding routing logic that matches leads to the right reps.
---
security-baseline
When your agent uses it
Establish a security baseline for a website or web app. Use this skill when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, doing a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scan, security audit, harden, OWASP, security baseline. Also triggers when a security review is required for compliance or before going live.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
2,618 tokensWhen the skill is activated
Reference documents
1,999 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Content Security Policy
- Workflow
- Common compliance touchpoints
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,846 bytesSKILL.mdcore11,846 bytesSKILL.mdcore11,846 bytesreferences/_claude-frontmatter-extras.yamlasset404 bytesreferences/headers-checklist.mddoc8,049 bytes
Read SKILL.md
# Security Baseline
Establish the security floor for any production website or web app. Stack-agnostic. Covers the things that should be in place before public launch and verified periodically after.
---
## When to use
- Pre-launch security review
- Setting up a new site or environment
- Periodic security audit (quarterly recommended)
- Onboarding a new vendor or third-party integration
- Responding to a security finding or report
- Hardening after an incidentseo-aeo-geo
When your agent uses it
Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI assistants. Use this skill whenever the user wants to optimize for AI search, get cited by language models, appear in AI overviews, build llms.txt, structure content for AI extraction, or future-proof their SEO for the shift from blue links to AI answers. Triggers on AEO, GEO, AI search, AI SEO, AI overview, generative search, LLM optimization, llms.txt, AI citation, ChatGPT search, Perplexity, Gemini, Claude search, AI assistant optimization, answer engine. Also triggers when the user expresses concern about AI eating their organic traffic or wants to understand how to remain visible as search shifts.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
1,963 tokensWhen the skill is activated
Reference documents
4,184 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,023 bytesSKILL.mdcore9,023 bytesSKILL.mdcore9,023 bytesreferences/_claude-frontmatter-extras.yamlasset394 bytesreferences/extraction-friendly-patterns.mddoc10,550 bytesreferences/llms-txt-guide.mddoc7,985 bytes
Read SKILL.md
# AEO and GEO
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO). Make content discoverable, extractable, and citable by AI search experiences.
This skill encodes principles. AI search products evolve fast. The principles age slower than the products.
---
## When to use
- Optimizing content for AI overviews and generative answer engines
- Building or updating llms.txt
- Structuring content so AI assistants can extract and cite it correctly
- Future-proofing a site as search shifts from blue links to AI answersseo-audit-orchestration
When your agent uses it
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,888 tokensWhen the skill is activated
Reference documents
1,517 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases of an end-to-end audit
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,312 bytesSKILL.mdcore8,312 bytesreferences/_claude-frontmatter-extras.yamlasset412 bytesreferences/audit-rollup-template.mddoc5,704 bytes
Read SKILL.md
# SEO Audit Orchestration
Run a complete SEO audit by sequencing the sibling audit skills in a defined order. Stack-agnostic. Assumes the Ahrefs MCP is connected. Produces a single rollup report that synthesizes findings across backlinks, keywords, content, traffic, technical health, and rankings.
---
## When to use
- Running a full SEO audit (quarterly, biannual, annual)
- Pre-acquisition SEO due diligence
- Post-migration verification (after content move, replatform, or domain change)
- Onboarding a new client or new property
- Building a baseline before a major SEO investment
- Diagnosing chronic underperformanceseo-backlink-audit
When your agent uses it
Audit a backlink profile using Ahrefs MCP data: profile health, anchor text distribution, toxic link identification, lost link reclamation, and gap analysis against competitors. Use this skill when reviewing backlink health, scoping a disavow project, recovering from a manual action, planning link building, or doing M&A due diligence on a property's link equity. Triggers on backlink audit, link profile, toxic links, disavow, anchor text analysis, lost links, link reclamation, referring domains, link gap. Also triggers when traffic decline correlates with link loss or when an unnatural link warning appears in Search Console.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
1,686 tokensWhen the skill is activated
Reference documents
1,339 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions of a backlink profile
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,675 bytesSKILL.mdcore7,675 bytesSKILL.mdcore7,675 bytesreferences/_claude-frontmatter-extras.yamlasset407 bytesreferences/toxic-link-criteria.mddoc5,888 bytes
Read SKILL.md
# SEO Backlink Audit
Audit a backlink profile using data pulled from the Ahrefs MCP. Stack-agnostic. Produces a profile health assessment, a toxic link list (if needed), a reclamation list, and a gap analysis against competitors.
---
## When to use
- Periodic backlink health check (quarterly or biannual)
- Recovering from a Google manual action or unnatural link warning
- Scoping a disavow file
- Pre-acquisition due diligence on link equity
- Planning a link building campaign (need a baseline)
- Investigating ranking drops correlated with link lossseo-competitor
When your agent uses it
Run a competitive SEO analysis comparing the user's site to chosen competitors across SERP overlap, content depth, backlink profiles, technical posture, and brand presence. Use this skill whenever the user wants to analyze competitors, find content gaps, identify backlink opportunities, understand why competitors outrank them, or benchmark against the rest of their category. Triggers on competitor analysis, competitive analysis, SERP analysis, content gap, backlink gap, why is X ranking, who is winning the SERP, beat my competitor, benchmark, market positioning. Also triggers when planning a content strategy and the question 'what are competitors doing' is implicit.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
1,498 tokensWhen the skill is activated
Reference documents
3,031 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 angles
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,039 bytesSKILL.mdcore7,039 bytesreferences/_claude-frontmatter-extras.yamlasset399 bytesreferences/competitive-audit-template.mddoc3,764 bytesreferences/content-gap-method.mddoc8,556 bytes
Read SKILL.md
# SEO Competitor Analysis
Compare a site to its competitors and find the gaps worth closing. Stack-agnostic. Tool-friendly but tool-optional.
---
## When to use
- Identifying which competitors to study
- Finding content gaps (topics they cover, you do not)
- Finding backlink gaps (sites linking to them, not you)
- Understanding why a specific competitor outranks the user
- Benchmarking authority, technical posture, and content depth
seo-content-audit
When your agent uses it
Audit existing content across a site to decide what to keep, update, merge, redirect, or delete. Use this skill whenever the user wants to audit existing content, fix content decay, resolve keyword cannibalization, prune underperforming pages, prioritize content updates, or apply a keep/update/merge/redirect/delete framework to a content library. Triggers on content audit, content decay, content refresh, cannibalization, keyword cannibalization, prune content, delete pages, redirect old pages, content inventory, what to keep, what to update, content scorecard, evergreen refresh. Also triggers when traffic is dropping site-wide and the cause might be content quality, even if 'audit' is not said explicitly.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
1,866 tokensWhen the skill is activated
Reference documents
3,415 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 actions
- Scoring inputs
- Decision matrix
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,466 bytesSKILL.mdcore8,466 bytesreferences/_claude-frontmatter-extras.yamlasset396 bytesreferences/audit-template.mddoc8,633 bytesreferences/cannibalization-resolution.mddoc6,603 bytes
Read SKILL.md
# Content Audit
Inventory existing content, score it, and decide for each piece: keep, update, merge, redirect, or delete. Stack-agnostic. Works on blogs, marketing sites, knowledge bases, and product content.
---
## When to use
- Inheriting a content library you did not create
- Diagnosing site-wide traffic decline
- Resolving cannibalization (two pages competing for the same query)
- Pre-migration cleanup
- Annual or semi-annual content health check
- Pruning before a redesign or replatformseo-content-gap-audit
When your agent uses it
Audit content gaps and decay using Ahrefs MCP data: missing topics, thin coverage, outdated content, and decaying pages. Use this skill when planning a content roadmap, refreshing a stale catalog, building topical authority, or identifying which existing pages need update versus replacement. Triggers on content gap, content audit, content refresh, content roadmap, decaying content, content decay, topical authority, what topics should we cover, where is competitor content stronger. Also triggers when organic traffic is flat despite consistent publishing.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
1,894 tokensWhen the skill is activated
Reference documents
1,750 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of content opportunity
- Workflow
- The action decision matrix
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,990 bytesSKILL.mdcore8,990 bytesreferences/_claude-frontmatter-extras.yamlasset408 bytesreferences/content-decision-matrix.mddoc7,756 bytes
Read SKILL.md
# SEO Content Gap Audit
Find content gaps and decay using Ahrefs MCP data. Stack-agnostic. Produces a roadmap of create, update, merge, and prune actions across the existing content catalog and identified topic gaps.
---
## When to use
- Planning the next quarter or half of content investment
- Refreshing a stale or underperforming content catalog
- Building topical authority in a target space
- Identifying decaying pages before they tank traffic
- Audit prep before a major site redesign or migration
- Diagnosing why content investment is not driving organic growthseo-keyword
When your agent uses it
Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production. Use this skill whenever the user asks to do keyword research, find target keywords, identify ranking opportunities, classify search intent, build a topical map, or plan a content strategy around what people search for. Triggers on keyword research, keyword strategy, search intent, keyword clustering, topic clusters, keyword difficulty, search volume, ranking opportunity, content gap, what should I write about, target keyword, primary keyword, secondary keyword, long-tail. Also triggers when planning a content calendar or new site without keywords yet defined.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,757 tokensWhen the skill is activated
Reference documents
3,183 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,891 bytesSKILL.mdcore7,891 bytesreferences/_claude-frontmatter-extras.yamlasset393 bytesreferences/intent-classification-guide.mddoc10,815 bytesreferences/keyword-research-template.mddoc3,039 bytes
Read SKILL.md
# Keyword Research
Find the queries worth ranking for, classify them by intent, cluster them into topics, and prioritize what to produce. Stack-agnostic. Tool-agnostic (works with any keyword tool).
---
## When to use
- Starting a new site or content section
- Planning a content calendar
- Looking for ranking opportunities on an existing site
- Understanding search intent before writing
- Building topic clusters for internal linking
- Identifying content gaps vs competitorsseo-keyword-gap-audit
When your agent uses it
Find keywords competitors rank for that the target property does not, and prioritize them by opportunity. Uses Ahrefs MCP for keyword and competitor data. Use this skill when planning content investment, identifying quick wins, building a content calendar against a competitor set, or scoping a market entry. Triggers on keyword gap, content gap, competitor keywords, opportunity keywords, what should we target, where are competitors winning, keyword opportunity. Also triggers when planning content for a new market or after losing organic share to a specific competitor.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
1,714 tokensWhen the skill is activated
Reference documents
1,983 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: the gap matrix
- Opportunity scoring
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,756 bytesSKILL.mdcore7,756 bytesreferences/_claude-frontmatter-extras.yamlasset407 bytesreferences/opportunity-scoring-rubric.mddoc7,013 bytes
Read SKILL.md
# SEO Keyword Gap Audit
Find keyword opportunities by comparing the target property's organic footprint against a competitor set, using Ahrefs MCP data. Stack-agnostic. Produces a prioritized list of keywords to target with new or improved content.
---
## When to use
- Planning content investment for the next quarter
- Identifying quick-win keywords for fast organic gains
- Scoping market entry into a new vertical
- Refreshing a stale content strategy
- Diagnosing why a competitor is gaining organic share
- Pre-acquisition due diligence on growth ceilingseo-offpage
When your agent uses it
Plan and execute off-page SEO including link building, digital PR, brand mentions, citation building, and external authority signals. Use this skill whenever the user wants to build backlinks, plan a digital PR campaign, list local citations, run guest post outreach, develop linkable assets, recover lost links, or audit a backlink profile for risk. Triggers on link building, backlinks, digital PR, brand mentions, citation building, guest post, outreach, linkable asset, broken link building, HARO, podcast outreach, off-page SEO, anchor text, link velocity, toxic backlinks, disavow. Also triggers when the user is trying to grow domain authority or earn coverage.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
1,703 tokensWhen the skill is activated
Reference documents
4,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 strategies
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,001 bytesSKILL.mdcore8,001 bytesreferences/_claude-frontmatter-extras.yamlasset386 bytesreferences/linkable-assets-guide.mddoc11,668 bytesreferences/outreach-templates.mddoc6,138 bytes
Read SKILL.md
# Off-Page SEO
Build the external signals that earn rankings: backlinks, brand mentions, citations, and trusted sources pointing back to the site. Stack-agnostic.
---
## When to use
- Planning a link-building strategy
- Running digital PR or earned-media campaigns
- Building citations for a local business
- Developing linkable assets (research, tools, calculators)
- Recovering lost backlinks after a migration or audit
- Auditing a backlink profile for spam or toxicityseo-onpage
When your agent uses it
Run a comprehensive on-page SEO audit or optimization pass covering title tags, meta descriptions, header structure, content quality, internal links, image optimization, URL hygiene, and on-page schema. Use this skill whenever the user asks to optimize a page, audit on-page SEO, fix titles or meta tags, review header structure, check internal linking, improve a single URL's search performance, or write SEO-friendly copy. Triggers on on-page SEO, page audit, title tag, meta description, H1, header structure, internal links, image alt, URL slug, page optimization, optimize this page, SEO this page. Also triggers for any single-page review where ranking, click-through, or relevance signal quality is the goal, even if the user does not say 'SEO' explicitly.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,575 tokensWhen the skill is activated
Reference documents
3,582 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 8 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore6,768 bytesreferences/_claude-frontmatter-extras.yamlasset387 bytesreferences/audit-template.mddoc2,216 bytesreferences/onpage-checklist.mddoc2,663 bytesreferences/title-and-meta-patterns.mddoc9,878 bytes
Read SKILL.md
# On-Page SEO
Optimize a single page for search relevance, click-through, and crawler comprehension. Stack-agnostic. Works on any CMS, framework, or static site.
---
## When to use
- Auditing or optimizing a single page (homepage, product page, article, landing page)
- Writing or reviewing title tags and meta descriptions
- Fixing header structure or content hierarchy
- Reviewing internal links from or to a page
- Improving a page's CTR from search results
seo-rank-tracking
When your agent uses it
Set up and run rank tracking using Ahrefs MCP: pick the right keywords to track, segment them by purpose, set baselines, and define alert thresholds. Use this skill when starting a new tracking project, baselining for a campaign, choosing what to monitor, or building a rank reporting cadence. Triggers on rank tracking, keyword tracking, monitor rankings, track positions, what should we track, ranking dashboard, baseline rankings, alert thresholds. Also triggers when a stakeholder wants weekly or monthly ranking visibility.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
2,152 tokensWhen the skill is activated
Reference documents
1,784 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: tracking taxonomy
- Selection criteria
- Segmentation beyond buckets
- Baselines
- Alert thresholds
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,191 bytesSKILL.mdcore10,191 bytesreferences/_claude-frontmatter-extras.yamlasset393 bytesreferences/dashboard-template.mddoc7,392 bytes
Read SKILL.md
# SEO Rank Tracking
Set up and run an ongoing rank tracking program using Ahrefs MCP data. Stack-agnostic. Produces a tracked keyword set, segmentation, baseline, alert thresholds, and a review cadence.
---
## When to use
- Starting rank tracking for a new property or section
- Baselining before a campaign, content launch, or major site change
- Deciding what keywords are worth tracking
- Setting up a ranking dashboard for stakeholders
- Establishing alert thresholds for ranking drops
- Reviewing whether the current tracked set is still meaningfulseo-site-health-audit
When your agent uses it
Triage technical SEO findings from Ahrefs Site Audit (and similar crawlers) by SEO impact, not just severity. Use this skill when reviewing crawl results, prioritizing technical fixes, scoping a technical SEO sprint, or after running any site-wide crawl. Triggers on site audit results, technical fix list, crawl errors, technical SEO triage, prioritize technical issues, what should we fix first, broken links, redirect chains. Also triggers when a long list of crawler issues is creating decision paralysis.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,289 tokensWhen the skill is activated
Reference documents
2,074 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: triage by SEO impact, not severity
- The triage matrix
- Workflow
- High-leverage clusters worth looking for
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,876 bytesSKILL.mdcore9,876 bytesSKILL.mdcore9,876 bytesreferences/_claude-frontmatter-extras.yamlasset405 bytesreferences/issue-impact-table.mddoc8,612 bytes
Read SKILL.md
# SEO Site Health Audit
Triage technical SEO findings from Ahrefs Site Audit (or any equivalent crawler) by impact on rankings and traffic, not by raw issue count or severity label. Stack-agnostic. Produces a prioritized backlog of fixes mapped to business impact.
---
## When to use
- After running an Ahrefs Site Audit or other site-wide crawl
- Reviewing a long list of technical issues and needing to prioritize
- Scoping a technical SEO sprint
- Pre-launch or post-migration technical verification
- Quarterly technical health check
- When developer time is limited and you must pick the highest-leverage fixesseo-technical
When your agent uses it
Run a comprehensive technical SEO audit covering crawlability, indexability, rendering, site architecture, structured data, page experience, security, and internationalization. Use this skill whenever the user asks about technical SEO, crawl issues, indexing problems, sitemaps, robots.txt, canonical tags, schema markup, page speed, Core Web Vitals, hreflang, redirects, or site-wide search performance. Triggers on technical SEO, site audit, crawlability, indexability, sitemap, robots.txt, canonical, redirect chain, schema, JSON-LD, Core Web Vitals, page speed, hreflang, mobile usability, HTTPS, security headers, render-blocking, JavaScript SEO. Also triggers when a site has indexing problems, traffic drops, or migration concerns, even if 'technical SEO' is not said explicitly.
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
1,600 tokensWhen the skill is activated
Reference documents
3,610 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,237 bytesSKILL.mdcore7,237 bytesreferences/_claude-frontmatter-extras.yamlasset397 bytesreferences/audit-template.mddoc9,991 bytesreferences/migration-checklist.mddoc5,020 bytes
Read SKILL.md
# Technical SEO
Audit and fix the layer beneath the content: how search engines crawl, render, index, and trust a site. Stack-agnostic.
---
## When to use
- Site-wide audit before or after a migration
- Investigating indexing or ranking drops
- Setting up SEO foundations on a new site
- Auditing Core Web Vitals or page experience signals
- Fixing crawl waste, redirect chains, or canonical issues
- Setting up multilingual or multi-regional sitesseo-traffic-diagnosis
When your agent uses it
Diagnose organic traffic changes (drops, stalls, or unexpected wins) using Ahrefs MCP plus Search Console data. Use this skill when traffic suddenly dropped, has been flat despite investment, after an algorithm update, after a migration or deploy, or when a competitor seems to be taking share. Triggers on traffic dropped, traffic decline, traffic stalled, organic decline, lost rankings, why is traffic down, algorithm update, post-migration traffic loss, traffic diagnosis. Also triggers when stakeholders are panicking about an organic traffic number they cannot explain. A panic about tracking, event, or dashboard setup is a measurement problem, not a traffic problem: route those to `analytics-strategy`.
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
1,870 tokensWhen the skill is activated
Reference documents
1,720 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers of diagnosis
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,744 bytesSKILL.mdcore8,744 bytesSKILL.mdcore8,744 bytesreferences/_claude-frontmatter-extras.yamlasset407 bytesreferences/diagnosis-checklist.mddoc7,863 bytes
Read SKILL.md
# SEO Traffic Diagnosis
Diagnose why organic traffic moved (down, flat, or unexpectedly up) using Ahrefs MCP combined with Search Console and analytics data. Stack-agnostic. Produces a root-cause diagnosis and an action plan.
---
## When to use
- Organic traffic dropped sharply
- Organic traffic has been flat for months despite content investment
- After a known Google algorithm update
- After a migration, replatform, or domain change
- After a deploy that touched routing, redirects, or rendering
- When a competitor is visibly taking organic shareskill-creation-walkthrough
When your agent uses it
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not triggering or not loading the right context, when you are auditing a skill that is underperforming, or when you want to publish a skill for others. Also triggers when someone asks "how do I make a skill" or "what makes a good skill". Useful for individuals, teams, and anyone publishing skills publicly.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
3,032 tokensWhen the skill is activated
Reference documents
4,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: how skills work
- Workflow
- Deep dive: description anatomy
- Deep dive: worked example
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore13,822 bytesreferences/_claude-frontmatter-extras.yamlasset401 bytesreferences/description-cookbook.mddoc9,417 bytesreferences/methodology-vs-implementation.mddoc7,734 bytesreferences/skill-template.mddoc5,760 bytes
Read SKILL.md
A walkthrough for designing, writing, and maintaining your own Claude Skills. Covers when a skill is the right shape for your problem, how to write a description that actually triggers, how to structure SKILL.md and references, and how to test and iterate.
## When to use
- You catch yourself writing the same prompt or instructions repeatedly.
- You want to package a workflow or framework for reuse.
- An existing skill of yours is not triggering when it should.
- You are publishing skills for others to use.
- You want to teach Claude a domain-specific way of working.
- You are reviewing a skill someone wrote and need a quality bar.
## When NOT to use
- For one-off prompts (just write the prompt).sprint-operations
When your agent uses it
Run the measurement and ceremony layer of a delivery team: the metric set, estimation and capacity, the five sprint ceremonies, and the sprint report and quarterly rollup. Use this skill whenever the user is acting as PMO or scrum lead, planning a sprint, running standup, refinement, review, or retro, measuring velocity, cycle time, or throughput, checking capacity, or reporting on how a team is doing. Triggers on PMO, sprint planning, plan the sprint, standup, refinement, backlog grooming, sprint review, retro, velocity, capacity, cycle time, lead time, throughput, WIP, burndown, carryover, sprint report, story points to hours, how is the team doing, delivery metrics, agent lanes. Also triggers when the user asks how much work fits in a sprint or whether a team is on track, even if they never say sprint or PMO.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
2,626 tokensWhen the skill is activated
Reference documents
6,507 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 parts
- Workflow
- Deep dive: measuring agent lanes
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,040 bytesSKILL.mdcore12,040 bytesreferences/_claude-frontmatter-extras.yamlasset418 bytesreferences/capacity-checklist.mddoc2,800 bytesreferences/example-sprint-report.mddoc4,357 bytesreferences/metrics-reference.mddoc6,079 bytesreferences/planning-template.mddoc1,947 bytesreferences/refinement-template.mddoc2,030 bytesreferences/retro-template.mddoc2,512 bytesreferences/review-template.mddoc1,577 bytesreferences/sprint-report-template.mddoc2,370 bytesreferences/standup-template.mddoc1,790 bytes
Read SKILL.md
# Sprint Operations
Run the measurement and ceremony layer of a delivery team so planning is grounded in history and reporting is derived from the tracker, not typed in. Tracker-agnostic: works with Jira, Linear, GitHub Issues, or your tracker of choice.
---
## When to use
- Setting up the metric set for a new or inherited team
- Planning a sprint and checking it against real capacity
- Running standup, refinement, review, or retro with a consistent template
- Answering "how is the team doing?" with numbers instead of adjectives
- Writing the sprint report or the quarterly rollup
- Deriving a points-to-hours ratio for financestakeholder-communication
When your agent uses it
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on stakeholder update, status report, executive summary, exec review, manage up, communicate bad news, project comms, status meeting, weekly update. Also triggers when a project is going off track and the team needs to communicate it.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
2,546 tokensWhen the skill is activated
Reference documents
2,551 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 questions
- The structure: the inverted pyramid
- Update templates
- Tone and register
- Workflow
- Cadence design
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,252 bytesreferences/_claude-frontmatter-extras.yamlasset402 bytesreferences/update-templates.mddoc9,864 bytes
Read SKILL.md
# Stakeholder Communication
Get the right information to the right people at the right time, in a form they can act on. Stack-agnostic. Applies to any team operating with cross-functional stakeholders.
---
## When to use
- Writing weekly or monthly status updates
- Preparing for an executive review or board update
- Sharing a technical decision with a non-technical audience
- Communicating a delay, miss, or quality problem
- Asking for help, resources, or decisions
- Managing up to a manager or sponsorteam-onboarding-playbook
When your agent uses it
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also triggers when one person owns all the tribal knowledge and you need to capture it, when you keep losing people in their first 90 days, or when a new project has many fresh members joining at once. Useful for engineering, design, product, marketing, and operations roles.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,097 tokensWhen the skill is activated
Reference documents
1,695 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework
- The 30/60/90 plan
- The role-specific overlay
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,032 bytesreferences/_claude-frontmatter-extras.yamlasset403 bytesreferences/onboarding-checklist.mddoc6,967 bytes
Read SKILL.md
A repeatable framework for building an onboarding playbook that ramps new team members predictably without burning out the people training them.
## When to use
- A new hire is joining and you do not have a written onboarding plan.
- An existing onboarding process is informal and inconsistent.
- A team is growing fast and onboarding is the bottleneck.
- A contractor or agency partner needs to ramp up quickly.
- A team member is leaving and their knowledge needs capturing.
- Onboarding currently takes too long and you want to reduce it.
## When NOT to use
- For ongoing performance management (different problem).ticket-authoring
When your agent uses it
Write complete, ready-to-pull work items for an issue tracker: bugs, tasks, stories, spikes, and epics, each with the fields, attachments, and done test its type requires. Use this skill whenever the user wants to write a ticket, create a Jira issue, Linear issue, or GitHub issue, file a bug report, write a user story or acceptance criteria, scope a spike, open an epic, or break work into tasks. Triggers on write a ticket, create an issue, file a bug, bug report, user story, spike, epic, task breakdown, turn this into tickets, break this down, acceptance criteria, definition of ready, ready for dev, backlog item, capitalization stage. Also triggers when the user pastes a PRD, a spec, or a bug description and asks what to do with it, even if they never say the word ticket.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
2,351 tokensWhen the skill is activated
Reference documents
7,022 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: five types, one definition of ready each
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesreferences/_claude-frontmatter-extras.yamlasset406 bytesreferences/bug-template.mddoc4,010 bytesreferences/capitalization-guide.mddoc5,934 bytesreferences/definition-of-ready-checklist.mddoc3,423 bytesreferences/epic-template.mddoc2,474 bytesreferences/example-bug-and-story.mddoc5,925 bytesreferences/spike-template.mddoc2,348 bytesreferences/story-template.mddoc2,862 bytesreferences/task-template.mddoc2,802 bytes
Read SKILL.md
# Ticket Authoring
Turn specs, bug reports, and loose requests into work items someone can pull and start without asking a question. Tracker-agnostic: works in Jira, Linear, GitHub Issues, or your tracker of choice.
---
## When to use
- Turning a PRD or spec into a set of tickets
- Filing a bug that someone else will fix
- Writing a user story with checkable acceptance criteria
- Scoping a spike so it ends in a decision, not a shrug
- Opening an epic with a goal, a metric, and a way to kill it
- Auditing a backlog for tickets that are not ready to pullupgrade-flow-design
When your agent uses it
Designing free-to-paid conversion flows for SaaS products. Trigger moments, paywall design, value demonstration, upsell vs downsell, win-back flows, churn prevention. Honest about paywall-everywhere (gates everything aggressively), free-forever-trap (no upgrade path surfaces), and value-triggered-upgrade (paywall surfaces at moments of demonstrated value) patterns. Triggers on upgrade flow, paywall, free-to-paid, freemium conversion, trial conversion, plan upgrade, subscription upgrade, win-back flow, churn prevention. Also triggers when free-to-paid conversion is low, when paywalls are blocking the wrong moments, or when upgrade flows are being scoped for the first time.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
3,839 tokensWhen the skill is activated
Reference documents
13,470 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The free-tier decision: freemium vs free-trial vs no-free
- Paywall-everywhere vs free-forever-trap vs value-triggered-upgrade
- Trigger-moment design: where paywalls earn their interruption
- Paywall presentation: modal vs banner vs inline
- Upsell vs downsell logic
- Win-back flow design
- Churn prevention upstream of upgrade
- Plan structure: tier count, feature gating, pricing-page design
- Common failure modes
- The framework: 12 considerations for upgrade flow design
- Reference files
- Closing: upgrade flows earn revenue when they earn the user's yes
Files
SKILL.mdcore18,072 bytesreferences/_claude-frontmatter-extras.yamlasset577 bytesreferences/churn-prevention-upstream.mddoc7,181 bytesreferences/common-upgrade-failures.mddoc6,254 bytesreferences/free-tier-decision-criteria.mddoc7,823 bytesreferences/paywall-presentation-patterns.mddoc7,977 bytesreferences/plan-structure-patterns.mddoc7,806 bytesreferences/trigger-moment-design.mddoc7,389 bytesreferences/upgrade-flow-anti-patterns.mddoc6,384 bytesreferences/upsell-vs-downsell-logic.mddoc6,514 bytesreferences/win-back-flow-patterns.mddoc7,244 bytes
Read SKILL.md
# Upgrade Flow Design
A senior product marketing director's playbook for designing free-to-paid conversion flows in SaaS products. Trigger moments, paywall design, value demonstration, upsell vs downsell, win-back flows, churn prevention. The discipline of asking for the upgrade at the moment the user has a reason to say yes.
Most upgrade flows fail in one of two ways. They block meaningful product use behind paywalls so aggressively that users churn before reaching the moment that would justify paying. Or they offer a generous free tier with no upgrade path that ever surfaces; users get everything they need; conversion stays at single-digit percentages indefinitely.
The upgrade flows that work do something different. They surface paywalls at moments where the user has demonstrably gotten value. The user has hit a usage threshold, completed a flow, or otherwise demonstrated they are getting the product's promise. The upgrade ask is honest about what they get next; the user is positioned to say yes because the value is fresh.
The voice is the senior product marketing director who has watched conversion rates double when paywalls were re-timed and watched them collapse when more aggressive paywalls were added. Practical, opinionated about the moments that earn the upgrade ask, willing to call out when the product's free tier is too generous to convert.
When to use this skill: scoping a free-to-paid conversion flow for the first time, auditing paywalls that block conversion or never surface, designing the trigger moments that earn upgrade asks, or deciding plan structure that supports upgrades over time.
---
usability-testing
When your agent uses it
Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task completion. Triggers on usability test, usability testing, moderated test, unmoderated test, task script, think aloud, prototype testing, user testing, design validation, task completion. Also triggers when the user has built something and wants to know if real users can use it before shipping.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
2,141 tokensWhen the skill is activated
Reference documents
2,423 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,456 bytesSKILL.mdcore9,456 bytesreferences/_claude-frontmatter-extras.yamlasset374 bytesreferences/task-script-patterns.mddoc10,751 bytes
Read SKILL.md
# Usability Testing
Plan and run tests that find usability problems before users hit them in production. Stack-agnostic. Tool-agnostic.
This skill is for testing existing designs or prototypes. For broader discovery research, use `ux-research`. For conversion testing in production, use `cro-optimization`.
---
## When to use
- Before launching a new flow or major redesign
- After a redesign to verify it doesn't introduce new problems
- When analytics show drop-off but you don't know why
- When customer support tickets pattern around specific UI areasuser-feedback-aggregation
When your agent uses it
Collecting and synthesizing user feedback across channels (support tickets, NPS, in-app feedback, sales calls, social mentions, customer councils) into a continuous signal that informs product decisions. The triage discipline that distinguishes loudest-voice (whoever complains most wins) from averaged-noise (every signal weighted equally) from triaged-synthesis (signal weighted by source quality, frequency, and decision relevance). Triggers on user feedback, customer feedback aggregation, NPS, support ticket analysis, customer councils, feedback synthesis, voice of customer, feedback triage, in-app feedback. Also triggers when feedback channels overflow with volume that does not produce decisions, when the loudest-voice problem is steering roadmap, or when continuous feedback streams need synthesis discipline.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
3,943 tokensWhen the skill is activated
Reference documents
17,557 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Loudest-voice vs averaged-noise vs triaged-synthesis
- Feedback channels and what each surfaces
- Channel-source weighting
- Categorization and tagging discipline at scale
- Frequency vs intensity
- From feedback to product decision
- Closing the loop with users
- Detecting drift in feedback patterns over time
- Feedback aggregation tooling considerations
- Common failure modes
- The framework: 12 considerations for feedback aggregation
- Reference files
- Closing: feedback as continuous signal, not periodic survey
Files
SKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesSKILL.mdcore20,542 bytesreferences/_claude-frontmatter-extras.yamlasset634 bytesreferences/categorization-and-tagging-at-scale.mddoc9,921 bytesreferences/channel-source-weighting.mddoc11,159 bytesreferences/channel-types-and-what-each-surfaces.mddoc11,456 bytesreferences/closing-the-loop-with-users.mddoc9,771 bytesreferences/common-feedback-aggregation-failures.mddoc10,499 bytesreferences/detecting-drift-in-feedback.mddoc9,679 bytesreferences/frequency-vs-intensity.mddoc9,855 bytesreferences/from-feedback-to-product-decision.mddoc10,028 bytesreferences/tooling-considerations.mddoc9,072 bytes
Read SKILL.md
# User Feedback Aggregation
A senior product leader's playbook for collecting and synthesizing user feedback across channels into continuous decision signal. Support tickets, NPS surveys, in-app feedback, sales calls, social mentions, customer councils, all aggregated into a triaged synthesis the team can actually act on.
Most product programs accumulate feedback they do not use. Channels overflow with submissions; CSAT and NPS scores get reported in monthly updates; customer council meetings produce notes that nobody references. The loudest voices steer roadmap because they are easiest to hear; quieter signal that matters more goes unaddressed.
This skill is the triage discipline that turns continuous feedback streams into continuous decision signal. Each channel surfaces different signal at different reliability. Each signal type warrants different weight in different decisions. The team that aggregates feedback well makes better decisions; the team that drowns in feedback makes the same decisions they would have made without the feedback.
Different from `discovery-research-synthesis`, which covers one-off research projects (a defined batch of artifacts, a defined synthesis output). This skill covers the always-on streams: feedback that arrives every day, every week, every month, and that the team must continuously triage and synthesize.
The voice is the senior product leader who has watched feedback aggregation work and watched it fail. Concrete, opinionated about which channels matter for which decisions, willing to call out where loudest-voice or averaged-noise patterns produce bad outcomes.
When to use this skill: building a feedback aggregation system, auditing a feedback program that is producing volume without decisions, deciding which feedback channels matter for the program, or designing the synthesis cadence for ongoing feedback streams.
ux-research
When your agent uses it
Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design interviews, recruit participants, conduct discovery, run formative research, or synthesize qualitative findings. Triggers on user research, UX research, user interviews, discovery research, generative research, formative research, qualitative research, user insights, research synthesis, recruitment, interview guide, jobs to be done. Also triggers when product decisions are being made without user input and the user wants to fix that.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
2,334 tokensWhen the skill is activated
Reference documents
1,836 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,831 bytesSKILL.mdcore10,831 bytesreferences/_claude-frontmatter-extras.yamlasset384 bytesreferences/interview-guide-template.mddoc8,034 bytes
Read SKILL.md
# UX Research
Plan and execute user research that produces decisions, not just decks. Stack-agnostic. Tool-agnostic.
This skill is for generative and discovery research. For testing existing designs, use `usability-testing`. For mapping the full customer experience, use `journey-mapping`.
---
## When to use
- Starting a new product or major feature without sufficient user understanding
- Diagnosing why something isn't working without clear data signals
- Generating new opportunity hypotheses
- Validating a strategic direction before significant investmentvendor-evaluation
When your agent uses it
Evaluate, select, and contract with vendors and SaaS tools. Use this skill when comparing alternatives, running an RFP, scoring vendors against criteria, negotiating contracts, planning a switch, or assessing a vendor's risk. Triggers on vendor evaluation, RFP, vendor selection, build vs buy, SaaS evaluation, vendor scorecard, vendor comparison, contract negotiation, vendor switch, procurement. Also triggers when a renewal is coming up or when a tool isn't meeting expectations.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,472 tokensWhen the skill is activated
Reference documents
1,748 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,243 bytesSKILL.mdcore11,243 bytesSKILL.mdcore11,243 bytesSKILL.mdcore11,243 bytesreferences/_claude-frontmatter-extras.yamlasset392 bytesreferences/evaluation-rubric.mddoc6,889 bytes
Read SKILL.md
# Vendor Evaluation
Pick the right tool or service, negotiate fair terms, and avoid the lock-in traps. Stack-agnostic. Applies to SaaS, infrastructure providers, agencies, and any external dependency.
---
## When to use
- Selecting a tool or vendor for a new need
- Evaluating alternatives to a current vendor
- Build vs buy analysis
- Renewal coming up: should we stay or switch?
- Running a formal RFP or RFI
- Comparing finalists in a vendor selectionvertical-site-conventions
When your agent uses it
Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that reads as generic or off-vertical, build to an experience bar produced by competitor-experience-audit, or compose pages with the merchandising, density, and layout conventions a credible site in the category is expected to carry. Triggers on vertical conventions, storefront layout, ecommerce layout, retail conventions, merchandising layout, category page composition, site composition, build to the experience bar, make it look like the vertical, off-vertical, looks generic, build conventions for a vertical, site grammar. Also triggers when a build that is technically clean reads wrong for its category, and the cause is composition, not visual taste.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
3,976 tokensWhen the skill is activated
Reference documents
14,114 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: build to the seven dimensions
- How the skill consumes an experience bar
- Stays in its lane (load-bearing)
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore19,012 bytesreferences/_claude-frontmatter-extras.yamlasset401 bytesreferences/shape-b2b-manufacturer.mddoc14,698 bytesreferences/shape-conventions-checklist.mddoc6,411 bytesreferences/shape-directory-marketplace.mddoc1,515 bytesreferences/shape-ecommerce-catalog.mddoc13,007 bytesreferences/shape-ecommerce-standout.mddoc1,794 bytesreferences/shape-hospitality-experience.mddoc1,728 bytesreferences/shape-hospitality-food.mddoc11,002 bytesreferences/shape-institution-mission.mddoc1,911 bytesreferences/shape-inventory-listing.mddoc1,511 bytesreferences/shape-local-service-booking.mddoc11,284 bytesreferences/shape-subscription-app.mddoc1,524 bytes
Read SKILL.md
# Vertical Site Conventions
Compose pages and whole sites to the layout, density, and merchandising conventions that make a build read as a credible member of its vertical. Stack-agnostic. Works on any framework that can express server-rendered pages and component composition.
This skill owns vertical-level composition: which modules go where, how dense the page is, how much of the catalog or offering is surfaced, and which paths the navigation serves. It routes the day-to-day visual decisions to `design-standards`, the aesthetic register to `creative-direction`, the site-structure modeling to `information-architecture`, and the component implementation to `frontend-component-build`. It does not duplicate any of them; it composes their outputs into a vertical-correct site.
It is the build-side counterpart to `competitor-experience-audit`. The audit measures the field on seven dimensions; this skill builds to those same seven, dimension by dimension. The two are deliberately structured as two sides of one standard so an experience bar produced by the audit maps one-to-one onto what this skill builds.
---
## When to use
- Building a new site in a vertical you have not built in before
- Fixing a build that reads as generic or off-vertical even though it is technically clean (the SEO, accessibility, and component implementation are correct, but the page does not read like its category)accessibility-audit
When your agent uses it
Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
2,441 tokensWhen the skill is activated
Reference documents
8,000 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: WCAG's 4 principles
- Audit methodology
- Workflow
- Severity classification
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,456 bytesSKILL.mdcore11,456 bytesSKILL.mdcore11,456 bytesreferences/aria-patterns.mddoc18,175 bytesreferences/audit-report-template.mddoc5,175 bytesreferences/wcag-quick-reference.mddoc8,655 bytes
Read SKILL.md
# Accessibility Audit
Run a thorough accessibility audit and produce a remediation plan. Stack-agnostic. Anchored to WCAG 2.1 AA, with notes on AAA where relevant.
This skill goes deeper than the accessibility checks in `qa-testing` and `design-standards`. Use this when accessibility itself is the goal.
---
## When to use
- Pre-launch accessibility verification
- Compliance preparation (ADA, EN 301 549, AODA, Section 508)
- Remediation after an audit finding or complaint
- Annual or quarterly accessibility health checkads-creative-development
When your agent uses it
How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
4,527 tokensWhen the skill is activated
Reference documents
9,865 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Performance vs brand creative
- Hook patterns: the first 3 seconds
- Format selection
- Video pacing
- Variation systems
- Sequential testing methodology
- Creative fatigue detection
- Brand-voice alignment without conversion dilution
- Platform-specific creative norms
- Common failures
- The framework: 10 considerations for sustainable creative production
- Reference files
- Closing: the hook is the whole game
Files
SKILL.mdcore21,341 bytesreferences/brand-voice-performance-balance.mddoc7,397 bytesreferences/creative-variation-templates.mddoc5,621 bytesreferences/fatigue-detection-checklist.mddoc6,431 bytesreferences/format-decision-matrix.mddoc4,791 bytesreferences/hook-pattern-library.mddoc7,100 bytesreferences/platform-creative-norms.mddoc6,827 bytesreferences/testing-cadence-playbook.mddoc6,034 bytes
Read SKILL.md
# Ads Creative Development
A senior creative strategist's playbook for producing ad creative that performs.
Performance creative is a different discipline from brand creative. Brand work optimizes for memorability, emotional resonance, and distinctive identity. Performance creative optimizes for stopping the scroll, communicating value in three seconds, and producing a click. Both matter. Mixing them up costs money. Brand creative running as performance ads bleeds budget; performance creative running as brand ads erodes equity.
This skill is the discipline that produces performance creative without diluting brand. It assumes you know your audience and offer (see `paid-media-strategy`). It assumes you have brand-voice guidance (see `brand-voice`). The hard part is the systematic production of variations that test cleanly and ship without manual approval bottlenecks, and that is what is here.
When to use this skill: producing ad creative for paid campaigns, planning a creative testing cycle, diagnosing creative fatigue, or auditing why creative is not converting.
---
## What this skill is for
ads-performance-analytics
When your agent uses it
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
5,133 tokensWhen the skill is activated
Reference documents
11,524 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every paid media platform should expose
- Platform-reported vs reality
- Attribution models in practice
- Multi-platform reconciliation
- ROAS vs LTV: the time horizon trap
- Cohort analysis vs daily metrics
- Statistical noise in performance metrics
- Incrementality testing
- Geo experiments and holdouts
- Platform self-attribution bias
- Common interpretation failures
- The framework: 12 considerations for trustworthy paid media interpretation
- If required data is unavailable
- Reference files
- Closing: the courage to call it incremental zero
Files
SKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesreferences/attribution-model-comparison.mddoc7,456 bytesreferences/cohort-analysis-templates.mddoc6,603 bytesreferences/common-interpretation-failures.mddoc9,164 bytesreferences/dashboard-reconciliation-patterns.mddoc6,692 bytesreferences/incrementality-testing-playbook.mddoc7,127 bytesreferences/metric-definitions-glossary.mddoc6,677 bytesreferences/platform-reporting-quirks.mddoc8,963 bytes
Read SKILL.md
# Ads Performance Analytics
A data-team-mentor's playbook for interpreting paid media dashboards without fooling yourself.
The dashboard is the moment of truth for paid media decisions. The numbers on it determine whether you scale, hold, or kill. They also expose every platform's self-attribution bias, every modeled-conversion shortcut, every cross-platform double-count. Most "scale this campaign" decisions trace back to misreading the dashboard.
This skill is the discipline that prevents misreading. It assumes the campaign was strategically sound (see `paid-media-strategy`). It assumes the creative was tested properly (see `ads-creative-development`). The hard part is knowing what each number actually means, what it does not, and how to reconcile platform-reported metrics with the truth in your warehouse.
When to use this skill: any time you are about to scale, kill, or rebudget a campaign based on platform metrics; reconciling platform reports with revenue data; evaluating an agency's reporting; or building a paid media dashboard that will not lie to you.
---
## What this skill is for
after-action-report
When your agent uses it
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
2,231 tokensWhen the skill is activated
Reference documents
2,122 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: blameless analysis
- The framework: 6 sections
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,902 bytesSKILL.mdcore9,902 bytesSKILL.mdcore9,902 bytesreferences/aar-template.mddoc8,344 bytes
Read SKILL.md
# After-Action Report
Run a structured retrospective on a launch, incident, or completed project. Produce actionable lessons, not just a document.
This skill is for after-the-fact analysis. For active incident response, use `incident-response`. For planning launches, use `launch-runbook`.
---
## When to use
- After any incident (any severity)
- After every major launch
- At the end of a project (sprint retro, quarterly retro, project closeout)
- When a recurring issue has happened enough times to demand investigationai-content-collaboration
When your agent uses it
How humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
4,638 tokensWhen the skill is activated
Reference documents
16,129 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Humans own, AI accelerates
- Where AI legitimately participates
- Where humans must own
- Hybrid workflow patterns
- Voice ownership preservation
- The AI slop problem
- Disclosure and transparency
- Team training and calibration
- Ethics: training data, attribution, intellectual honesty
- Common failure modes
- The framework: 12 considerations for AI content collaboration
- Reference files
- Closing: collaboration, not replacement
Files
SKILL.mdcore22,585 bytesSKILL.mdcore22,585 bytesSKILL.mdcore22,585 bytesreferences/ai-participation-boundaries.mddoc7,481 bytesreferences/ai-slop-detection-and-avoidance.mddoc8,587 bytesreferences/common-collaboration-failures.mddoc10,479 bytesreferences/disclosure-and-transparency-patterns.mddoc9,437 bytesreferences/ethics-and-intellectual-honesty.mddoc10,412 bytesreferences/hybrid-workflow-patterns.mddoc8,302 bytesreferences/quality-calibration-with-ai-in-loop.mddoc9,077 bytesreferences/team-training-and-calibration.mddoc8,499 bytesreferences/voice-ownership-preservation.mddoc8,373 bytes
Read SKILL.md
# AI Content Collaboration
A senior editorial leader's playbook for how humans and AI compose in content workflows. Pragmatic, tool-agnostic, honest about both what AI in the loop enables and what it threatens.
Most content programs in 2026 use AI somewhere in the workflow. Pretending otherwise is dishonest; treating AI as a magic content factory is the failure mode this skill exists to prevent. The discipline is in between: knowing where AI legitimately accelerates, where humans must own, what hybrid patterns produce work that earns reader trust, and what crosses the line into AI slop or intellectual dishonesty.
This skill is the WORKFLOW layer that composes with every other content skill. Briefs can be AI-assisted; hub architectures can be AI-assisted; programmatic SEO is almost always AI-involved; editorial QA now includes AI-content audit by necessity. The collaboration discipline applies to all production stages, not to a single artifact type.
The voice is pragmatic and tool-agnostic deliberately. The methodology applies whether the AI in your loop is one of the major commercial models, an open-source model, or whatever ships next quarter. What stays constant is the workflow shape, the participation boundaries, the voice ownership question, and the ethical frame. What changes is which specific tool you reach for, which is implementation work that varies by team and budget.
When to use this skill: building or refining an AI-content workflow, calibrating a team on consistent AI usage, addressing the "we use AI but our work feels generic" problem, designing disclosure policies, or working through the ethics of AI-assisted content production for a regulated or trust-sensitive context.
---
analytics-strategy
When your agent uses it
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement. Triggers on analytics strategy, measurement plan, event taxonomy, tracking plan, KPI framework, dashboard design, north star metric, attribution model, conversion tracking, GA4 setup, Mixpanel setup, analytics audit. Also triggers when the user has data but no clear way to use it, or wants to make decisions but doesn't know what to track.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
2,033 tokensWhen the skill is activated
Reference documents
2,292 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- The tracking plan document
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,470 bytesreferences/event-taxonomy-template.mddoc9,896 bytes
Read SKILL.md
# Analytics Strategy
Design measurement frameworks that produce decisions, not just dashboards. Stack-agnostic. Tool-agnostic.
This skill is for measurement planning. For conversion optimization, use `cro-optimization`. For SEO measurement specifically, use `seo-onpage` and adjacent SEO skills.
---
## When to use
- Setting up analytics on a new product or site
- Auditing existing analytics setup
- Designing dashboards for a team or business
- Defining KPIs and a north star metricart-direction
When your agent uses it
Direct visual and creative work for campaigns, photography, illustration, video, and branded experiences. Use this skill whenever the user wants to brief a photographer, direct illustrators, plan a creative campaign, develop visual concepts, or evaluate creative work for fit. Triggers on art direction, photo brief, photography brief, illustration brief, campaign concept, creative concept, visual direction, mood board, look and feel, visual treatment, video direction. Also triggers when the user has approved brand identity but needs to extend it into specific creative deliverables. Use `creative-direction` instead when the ask is the project-wide aesthetic brief that this skill consumes as input.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
2,059 tokensWhen the skill is activated
Reference documents
5,011 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,611 bytesreferences/creative-brief-template.mddoc6,077 bytesreferences/illustration-brief.mddoc7,946 bytesreferences/photo-shoot-brief.mddoc6,424 bytes
Read SKILL.md
# Art Direction
Direct creative work that extends the brand into specific deliverables. Photography, illustration, video, motion, campaigns, environmental design.
This skill assumes brand identity is approved (`brand-identity` complete). Art direction is about applying and extending it, not defining it.
---
## When to use
- Briefing photographers, illustrators, videographers
- Developing campaign creative concepts
- Directing in-house creative teams
- Writing creative direction documents for vendorsbackup-and-disaster-recovery
When your agent uses it
Plan and run backups, set recovery objectives, and run disaster recovery drills. Use this skill when defining RPO/RTO targets, designing backup architecture, deciding what to back up and how often, planning for full-region or platform outages, or running a restoration drill. Triggers on backup, restore, RPO, RTO, disaster recovery, DR, business continuity, what if the database is gone, what if our hosting goes down, recovery drill, ransomware planning. Also triggers when an incident reveals a gap in restoration capability.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,406 tokensWhen the skill is activated
Reference documents
1,338 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 questions
- Workflow
- Special topics
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,870 bytesSKILL.mdcore10,870 bytesreferences/restore-runbook-template.mddoc5,525 bytes
Read SKILL.md
# Backup and Disaster Recovery
Plan for the worst case: the database is gone, the host is down for a week, the deploy was poisoned, ransomware encrypted everything. The skill is in advance preparation, not reaction.
---
## When to use
- Setting up backups for a new system
- Reviewing and validating backup architecture
- Defining RPO (recovery point objective) and RTO (recovery time objective)
- Running a disaster recovery drill
- Diagnosing gaps after an incident
- Planning for ransomware, data corruption, or insider threatsbeta-program-management
When your agent uses it
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria). Triggers on beta program, alpha test, beta cohort, beta participant, beta feedback, beta to GA decision, design partner, early access program, closed beta, open beta, RC release. Also triggers when a feature is approaching launch and the team needs structured pre-GA validation, when prior betas produced noise rather than signal, or when the team has soft-launched before but wants more structured feedback this time.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
4,942 tokensWhen the skill is activated
Reference documents
18,246 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Soft-launch vs kitchen-sink vs structured-beta
- Beta type decisions
- Participant selection criteria
- Beta cohort sizing
- Onboarding beta participants
- Feedback collection patterns
- Mid-beta triage and iteration
- Beta-to-GA decision criteria
- Beta wind-down and participant communication
- Common failure modes
- The framework: 12 considerations for beta program management
- If required data is unavailable
- Reference files
- Closing: betas earn their keep with structure
Files
SKILL.mdcore24,454 bytesSKILL.mdcore24,454 bytesreferences/beta-onboarding-templates.mddoc10,602 bytesreferences/beta-to-ga-graduation-criteria.mddoc11,663 bytesreferences/beta-type-decisions.mddoc10,326 bytesreferences/beta-wind-down-communication.mddoc9,512 bytesreferences/cohort-sizing-patterns.mddoc8,928 bytesreferences/common-beta-failures.mddoc10,373 bytesreferences/feedback-collection-patterns.mddoc10,916 bytesreferences/mid-beta-triage-and-iteration.mddoc9,669 bytesreferences/participant-selection-criteria.mddoc10,154 bytes
Read SKILL.md
# Beta Program Management
A senior product leader's playbook for running betas that produce real signal. Closed and open betas, alpha programs, design partner programs, early access. Participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria).
Most betas underperform. Teams ship a beta because they think they should run a beta; participants are recruited loosely or open-flooded; feedback is collected ad-hoc through whatever channels exist; the decision to graduate to GA happens on calendar rather than on signal. The beta produced activity but not learning; the team launches with the same uncertainty they had before the beta.
This skill is the discipline that turns betas into decision input. Calibrated cohorts who match the post-launch user profile. Structured feedback that captures what the team needs to know. Mid-beta triage that uses what is being learned. Graduation criteria that distinguish "ready" from "we are tired of running the beta." The discipline is not bureaucratic; it is the difference between a beta that informs the GA launch and a beta that produces noise.
The voice is the senior product leader who has run betas with real signal and watched plenty of betas produce nothing. Concrete, opinionated about what produces signal, willing to call out where beta programs slide into ceremony.
When to use this skill: planning a beta for an upcoming launch, auditing why prior betas have not produced actionable signal, designing the beta participant experience, or deciding whether a feature is ready to graduate from beta to GA.
---
brand-archetype-system
When your agent uses it
Apply pre-composed aesthetic archetype defaults to jumpstart brand design work covering color, typography, layout, voice, and imagery direction. Use this skill whenever the user wants a starting point for brand visual and verbal direction, references a brand they want to design near (for example 'something like Stripe' or 'editorial like Linear'), needs to converge faster from many directions to one, or wants known-good defaults for a specific industry vertical. Triggers on archetype, design archetype, brand archetype, near to (brand), in the style of, similar aesthetic, design starting point, brand template, vertical-typical, industry-typical. Also triggers when the user has a brief and wants to map it to a known aesthetic family rather than design from first principles.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
32,712 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: 12 core archetypes plus 18 vertical applications
- The 12 core archetypes
- The 18 vertical applications
- Trademark and attribution
- The four creative-direction axes (reference)
- Reference files
Files
SKILL.mdcore7,664 bytesreferences/00-archetype-system-overview.mddoc3,231 bytesreferences/01-how-to-apply-an-archetype.mddoc3,898 bytesreferences/by-vertical/01-b2b-saas-developer-tools.mddoc3,609 bytesreferences/by-vertical/02-b2b-saas-business-productivity.mddoc3,547 bytesreferences/by-vertical/03-b2b-saas-marketing-sales.mddoc3,408 bytesreferences/by-vertical/04-b2b-saas-data-analytics.mddoc3,255 bytesreferences/by-vertical/05-fintech-consumer.mddoc3,264 bytesreferences/by-vertical/06-fintech-enterprise.mddoc3,438 bytesreferences/by-vertical/07-dtc-fashion.mddoc3,520 bytesreferences/by-vertical/08-dtc-beauty.mddoc3,447 bytesreferences/by-vertical/09-dtc-home-lifestyle.mddoc3,493 bytesreferences/by-vertical/10-dtc-food-beverage.mddoc3,513 bytesreferences/by-vertical/11-consumer-health-wellness.mddoc3,502 bytesreferences/by-vertical/12-hospitality-travel.mddoc3,308 bytesreferences/by-vertical/13-media-publishing.mddoc3,279 bytesreferences/by-vertical/14-edtech.mddoc3,608 bytesreferences/by-vertical/15-gaming-entertainment.mddoc3,438 bytesreferences/by-vertical/16-marketplace.mddoc3,474 bytesreferences/by-vertical/17-crypto-web3.mddoc3,443 bytesreferences/by-vertical/18-real-estate-proptech.mddoc3,648 bytesreferences/core-archetypes/01-editorial-restrained.mddoc6,292 bytesreferences/core-archetypes/02-technical-precise.mddoc6,632 bytesreferences/core-archetypes/03-warm-conversational.mddoc6,988 bytesreferences/core-archetypes/04-bold-confident.mddoc6,347 bytesreferences/core-archetypes/05-playful-energetic.mddoc6,623 bytesreferences/core-archetypes/06-luxe-considered.mddoc6,956 bytesreferences/core-archetypes/07-clinical-trustworthy.mddoc7,397 bytesreferences/core-archetypes/08-rugged-utilitarian.mddoc6,933 bytesreferences/core-archetypes/09-retro-nostalgic.mddoc7,336 bytesreferences/core-archetypes/10-minimal-essentialist.mddoc6,995 bytesreferences/core-archetypes/11-vibrant-saturated.mddoc6,758 bytesreferences/core-archetypes/12-documentary-honest.mddoc7,119 bytes
Read SKILL.md
# Brand Archetype System
Pre-composed aesthetic archetype defaults that jumpstart brand design work. Each archetype bundles color tendencies, type pairings, layout patterns, voice samples, and imagery direction for a recognizable aesthetic family. Stack-agnostic. Tool-agnostic.
This is a starting-point library, not a methodology library. The agent applies archetype defaults to a specific brief; the archetypes themselves provide anchor points, not endpoints.
---
## When to use
- The user wants a starting point rather than designing from first principles
- The user references a brand or aesthetic family they want to design near
- Need to converge faster from many directions to one
- The user wants vertical-typical defaults (for example fintech consumer, B2B developer tools)brand-discovery
When your agent uses it
Run upstream brand discovery covering audience research, competitive landscape, category dynamics, problem space, and positioning territory exploration. Use this skill at the very start of a brand or website project when the user needs to understand who they're for, who they compete with, what the audience actually needs, and where the brand could plausibly stand. Triggers on brand discovery, audience research, market research, competitive scan, category research, customer research, who is this for, who are we, positioning research, intake, kickoff. Also triggers when a creative brief is requested but the upstream inputs (audience, competitors, problem space) are not yet clear.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
2,088 tokensWhen the skill is activated
Reference documents
2,544 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,702 bytesSKILL.mdcore9,702 bytesreferences/discovery-report-template.mddoc4,597 bytesreferences/interview-guide.mddoc6,923 bytes
Read SKILL.md
# Brand Discovery
Upstream of every brief, identity, and content plan. Discovery answers four questions: who the brand is for, what they need, who else is competing for that need, and where the brand could plausibly stand that competitors do not.
---
## When to use
- The very first phase of a new brand or website project
- Understanding an audience before any creative work begins
- Mapping competitors and category dynamics
- Surfacing the problem space the brand will operate in
- Generating positioning territories before brief or ideation
- When a creative brief was requested but the inputs are missingbrand-ideation
When your agent uses it
Generate, evaluate, and narrow brand concepts during early ideation including positioning territories, naming candidates, mood directions, and narrative angles. Use this skill whenever the user is in the early phase of brand creation, exploring brand directions, brainstorming names, building moodboards, generating positioning options, or trying to choose between multiple brand directions. Triggers on brand ideation, brand concept, naming, brand name, name candidates, positioning, brand positioning, mood board, brand directions, exploring brands, early brand work, brand exploration, brand brainstorm, brand options. Also triggers when the user has multiple half-formed brand ideas and needs help converging on one, even if they do not say 'ideation' explicitly.
What it loads into context
Frontmatter
176 tokensAlways available to the agent
SKILL.md
2,205 tokensWhen the skill is activated
Reference documents
2,735 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,612 bytesSKILL.mdcore9,612 bytesreferences/ideation-output-template.mddoc4,755 bytesreferences/naming-evaluation-rubric.mddoc6,497 bytes
Read SKILL.md
# Brand Ideation
Generate and converge on brand directions before committing to identity work. This is upstream of `brand-identity` (the visual system) and `brand-style-guide` (the documentation). It is the divergent-then-convergent thinking phase where ideas are cheap and direction matters more than polish.
---
## When to use
- Generating naming options for a new brand or product
- Exploring positioning territories before committing
- Building moodboards and visual direction options
- Drafting narrative or origin-story angles
- Helping the user converge from many half-ideas to one direction
- Stress-testing an existing brand idea before investing in identity workbrand-identity
When your agent uses it
Design or evaluate a brand visual identity system covering logo, color, typography, imagery direction, iconography, and motion principles. Use this skill whenever the user wants to design a logo, build a visual identity, define brand colors, choose brand typography, develop iconography, plan brand imagery, or evaluate an existing identity for cohesion. Triggers on logo design, brand identity, visual identity, brand mark, wordmark, monogram, color palette, brand colors, brand typography, type system, iconography, brand imagery, motion design, brand system, identity system. Also triggers when the user has a brand direction approved and now needs the visual artifacts that express it.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
2,393 tokensWhen the skill is activated
Reference documents
3,411 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 elements
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,632 bytesSKILL.mdcore10,632 bytesSKILL.mdcore10,632 bytesreferences/contrast-and-accessibility.mddoc6,761 bytesreferences/identity-system-spec.mddoc6,266 bytes
Read SKILL.md
# Brand Identity
Design or evaluate the visual artifacts that express a brand: logo system, color, typography, imagery, iconography, and motion. Stack-agnostic. Tool-agnostic.
This skill assumes a brand direction is already approved (positioning, mood, name). If not, run `brand-ideation` first.
---
## When to use
- Designing a logo system
- Defining a brand color palette
- Choosing brand typography
- Developing iconography or illustration stylebrand-style-guide
When your agent uses it
Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style guide for completeness, or produce the artifact that other teams will reference for years. Triggers on style guide, brand guidelines, brand book, brand standards, brand manual, style sheet, brand documentation, brand reference. Also triggers when the brand identity is finished and needs to be documented for handoff to designers, developers, vendors, or future team members.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,866 tokensWhen the skill is activated
Reference documents
3,893 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 8 sections
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesreferences/maintenance-playbook.mddoc7,873 bytesreferences/style-guide-template.mddoc7,669 bytes
Read SKILL.md
# Brand Style Guide
Document the brand system so other people can use it without ambiguity. This is the artifact that lives longest. Designers, developers, agencies, and vendors will reference it for years. Build it like a reference manual, not a presentation.
This skill assumes the brand identity is designed (run `brand-identity` first if not). The output of this skill is the canonical reference document.
---
## When to use
- Creating brand guidelines for a finished identity
- Documenting an existing brand that has no formal guide
- Auditing an existing style guide for gaps or inconsistencies
- Building a brand book to hand to vendors, partners, or new team membersbrand-voice
When your agent uses it
Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
1,993 tokensWhen the skill is activated
Reference documents
3,243 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,904 bytesreferences/voice-document-template.mddoc5,656 bytesreferences/voice-frameworks.mddoc7,630 bytes
Read SKILL.md
# Brand Voice
Define how a brand sounds in writing. Document it in a way that anyone (writer, designer, founder, AI assistant) can apply it consistently.
This skill produces a standalone voice document that can either live in the brand style guide or feed into it.
---
## When to use
- Defining brand voice for the first time
- Auditing existing copy for voice consistency
- Training a team, freelancer, or AI assistant on the brand voice
- Refining a voice that exists but is inconsistent across applicationscalculator-design
When your agent uses it
Designing interactive calculators (ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments) that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. Honest about vanity-calculator (no real value), lead-trap (hides the answer behind email), and transparent-decision-tool (gives the result and earns the email through tiered value) patterns. Triggers on calculator, ROI calculator, pricing estimator, savings calculator, custom calculator, interactive tool, decision tool, financial calculator. Also triggers when an audience needs a calculation-driven lead magnet, when a vanity calculator is producing leads but no qualified ones, or when a calculator is being scoped for the first time.
What it loads into context
Frontmatter
215 tokensAlways available to the agent
SKILL.md
4,787 tokensWhen the skill is activated
Reference documents
19,463 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The calculator decision: when calculators earn investment
- Vanity-calculator vs lead-trap vs transparent-decision-tool
- Input design
- Calculation logic transparency
- Result presentation
- Email-capture decision
- Tiered-value structures
- Calculator anti-patterns
- Common failure modes
- The framework: 12 considerations for calculator design
- If required data is unavailable
- Reference files
- Closing: calculators earn the email when they would have been worth paying for
Files
SKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesreferences/calculation-logic-transparency.mddoc11,693 bytesreferences/calculator-anti-patterns.mddoc10,366 bytesreferences/calculator-investment-criteria.mddoc10,002 bytesreferences/common-calculator-failures.mddoc9,313 bytesreferences/email-capture-decision-tree.mddoc10,868 bytesreferences/input-design-patterns.mddoc10,986 bytesreferences/methodology-disclosure-templates.mddoc10,700 bytesreferences/result-presentation-patterns.mddoc10,900 bytesreferences/tiered-value-structures.mddoc10,560 bytes
Read SKILL.md
# Calculator Design
A senior growth practitioner's playbook for designing interactive calculators that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments. The discipline of building a tool the audience actually trusts.
Most calculators on the web are bait. Random multipliers behind official-looking math; an "Industry Average" number that does not cite a source; the result hidden behind a contact-sales form. The calculator captures emails because the format implies calculation; the leads are unqualified because the calculator did not actually help anyone decide anything.
The calculators that work as compounding assets do something different. They give the audience a result they can defend to a stakeholder. They show the methodology so the result is interrogatable. They capture leads through value (a PDF report, a save-and-compare account, a custom analysis) rather than through manipulation.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the calculator-specific methodology (calculation transparency, tiered value, methodology disclosure) lives here.
The voice is the senior growth practitioner who has watched calculators earn long-term credibility and watched them burn it within weeks of launch. Practical, opinionated about transparency, willing to say when a calculator is the wrong investment for the goal.
When to use this skill: scoping a calculator for the first time, auditing a calculator that converts but does not qualify, designing the methodology disclosure that earns audience trust, or deciding which features warrant the email gate.
chatbot-flow-design
When your agent uses it
Designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. Honest about scripted-bot (rigid trees, fail edge cases), hallucinating-bot (LLM without structure, makes things up), and structured-guided-conversation (LLM-powered with intent architecture and fallback discipline) patterns. Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION (engineering and platform work). Triggers on chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding. Also triggers when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time.
What it loads into context
Frontmatter
236 tokensAlways available to the agent
SKILL.md
4,164 tokensWhen the skill is activated
Reference documents
17,487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The chatbot decision: when chatbots earn deployment
- Scripted-bot vs hallucinating-bot vs structured-guided-conversation
- Intent architecture
- Knowledge-base grounding
- Branching and conditional logic
- Fallback patterns
- Escalation to human
- Conversation analytics
- Common failure modes
- The framework: 12 considerations for chatbot flow design
- Reference files
- Closing: chatbots earn deployment when they know what they don't know
Files
SKILL.mdcore20,622 bytesSKILL.mdcore20,622 bytesreferences/branching-and-conditional-logic.mddoc9,490 bytesreferences/chatbot-anti-patterns.mddoc9,772 bytesreferences/chatbot-decision-criteria.mddoc9,562 bytesreferences/common-chatbot-failures.mddoc8,438 bytesreferences/conversation-analytics-patterns.mddoc10,047 bytesreferences/escalation-to-human-patterns.mddoc9,193 bytesreferences/fallback-pattern-design.mddoc9,859 bytesreferences/intent-architecture-patterns.mddoc10,376 bytesreferences/knowledge-base-grounding-patterns.mddoc10,778 bytes
Read SKILL.md
# Chatbot Flow Design
A senior growth practitioner's playbook for designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. The discipline of building a bot that knows what it knows and routes appropriately when it does not.
Most chatbots on the web fail in one of two ways. Scripted bots break the moment a user phrases something the script did not anticipate; the user gets pushed through a decision tree that does not fit their situation. LLM-powered bots without structure hallucinate; they confidently answer questions about pricing, policy, or capabilities and frequently make up answers, creating support burden and trust damage.
The chatbots that work do something different. They have an intent architecture that defines what the bot can and cannot handle. They ground their responses in a knowledge base so they do not invent facts. They have explicit fallback paths for unclear or out-of-scope intents. They escalate to humans cleanly when the bot's job is done. The audience trusts the bot because the bot is honest about its scope.
The voice is the senior growth practitioner who has watched chatbots become trusted brand surfaces and watched them become liability risks. Practical, opinionated about the architecture that distinguishes the two outcomes, willing to call out when a chatbot is the wrong investment or when an existing chatbot needs to be redesigned rather than tuned.
When to use this skill: scoping a chatbot for the first time, auditing a chatbot that hallucinates or fails edge cases, designing the intent architecture and fallback patterns, or deciding when to escalate to humans.
---
code-review-web
When your agent uses it
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
2,322 tokensWhen the skill is activated
Reference documents
4,786 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 review dimensions
- Common bug patterns (stack-agnostic)
- Workflow
- Failure patterns
- Debugging workflow
- Output format
- Reference files
Files
SKILL.mdcore10,703 bytesreferences/nextjs-patterns.mddoc8,960 bytesreferences/review-template.mddoc3,090 bytesreferences/wordpress-headless-patterns.mddoc8,259 bytes
Read SKILL.md
# Code Review for Web
Review and debug web application code with a focus on the patterns that actually break production. Stack-agnostic principles in SKILL.md. Stack-specific patterns in references.
---
## When to use
- Reviewing a pull request before merging
- Debugging a production issue
- Investigating a build failure
- Auditing security or performance of existing code
- Investigating environment variable or configuration issues
- Triaging a "the site is broken" reportcomparison-tool-design
When your agent uses it
Designing side-by-side comparison tools (plan-compare, product-compare, alternative-compare) that help users decide rather than just listing features. Axis selection, default-comparison logic, recommendation discipline. Honest about feature-list-dump (every feature in a row, no decision support), hidden-recommendation (biased comparison pretending to be neutral), and honest-comparison-with-guidance (genuine comparison plus opinionated recommendation) patterns. Triggers on comparison tool, plan compare, product compare, alternative compare, vs page, decision support tool. Also triggers when conversion through comparison stages is poor, when users are abandoning at the comparison step, or when a comparison tool is being scoped for the first time.
What it loads into context
Frontmatter
222 tokensAlways available to the agent
SKILL.md
3,355 tokensWhen the skill is activated
Reference documents
10,173 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The comparison-tool decision: when comparison tools earn investment
- Feature-list-dump vs hidden-recommendation vs honest-comparison-with-guidance
- Axis selection: which dimensions matter, which are noise
- Default-comparison logic
- Recommendation engine design
- Filter and toggle UX
- Comparison-fatigue patterns
- Common failure modes
- The framework: 12 considerations for comparison tool design
- If required data is unavailable
- Reference files
- Closing: comparison tools earn the choice when they earn the user's trust
Files
SKILL.mdcore16,793 bytesSKILL.mdcore16,793 bytesreferences/axis-selection-patterns.mddoc4,706 bytesreferences/common-comparison-failures.mddoc5,720 bytesreferences/comparison-anti-patterns.mddoc5,991 bytesreferences/comparison-fatigue-patterns.mddoc5,906 bytesreferences/comparison-tool-decision-criteria.mddoc4,643 bytesreferences/default-comparison-logic.mddoc5,752 bytesreferences/filter-and-toggle-patterns.mddoc6,237 bytesreferences/honest-recommendation-discipline.mddoc6,823 bytesreferences/recommendation-engine-design.mddoc5,157 bytes
Read SKILL.md
# Comparison Tool Design
A senior product marketing director's playbook for designing side-by-side comparison tools that help users decide rather than just listing features. Plan-compare, product-compare, alternative-compare. Axis selection, default-comparison logic, recommendation discipline. The discipline of building a comparison tool that earns the user's trust.
Most comparison tools fail in one of two ways. They dump every feature into a giant grid (4 options × 40 features = 160 cells) and ask the user to weigh everything against everything. The user leaves without choosing. Or they pretend to be neutral comparisons but are actually sales pitches with biased defaults and weighted framing; the user catches the bias and trust collapses.
The comparison tools that work do something different. Genuine like-for-like comparison plus an explicit opinionated recommendation. "For X audience, choose Y." The recommendation is visible, defended, and not the only path; users can override. The tool helps the user decide rather than asking them to decide alone.
The voice is the senior product marketing director who has watched comparison tools double conversion when redesigned with honest recommendations and watched them collapse when feature grids grew without decision support. Practical, opinionated about which axes matter, willing to call out when the comparison is decoration.
When to use this skill: scoping a comparison tool for the first time, auditing a feature-grid comparison that produces no conversion lift, designing recommendation logic that is honest about the recommendation, or deciding which axes earn placement in a comparison tool.
---
competitor-experience-audit
When your agent uses it
Audit the brand, UX, and site design of the leading sites in a vertical as a set of observable cross-site patterns, producing the experience bar a new build must meet or beat. Use this skill whenever the user wants to assess the competitive design field, capture vertical conventions, identify the design and UX bar of a category, or set the experience standard before a build. Triggers on competitor experience audit, UX audit, site design audit, brand audit, design conventions, what makes these sites good, vertical conventions, storefront patterns, merchandising patterns, layout density, primary task, design bar, category conventions, retail vs marketing register, what does the field do. Also triggers when an audit of the competitive field has captured technical signals (SEO, accessibility) but never named the brand, UX, or design conventions, and the build downstream will read as off-vertical without that bar.
What it loads into context
Frontmatter
210 tokensAlways available to the agent
SKILL.md
3,052 tokensWhen the skill is activated
Reference documents
2,684 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 experience dimensions
- The honesty guardrail (load-bearing)
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore14,437 bytesreferences/audit-template.mddoc4,750 bytesreferences/experience-dimensions-checklist.mddoc7,203 bytes
Read SKILL.md
# Competitor Experience Audit
Capture the brand, UX, and site design that the leading sites in a vertical observably share, and where they fall short. The output is the experience bar a new build must meet or beat, grounded in cross-site patterns rather than aesthetic opinion.
Stack-agnostic. Works on any SiteShape (ecommerce-catalog, inventory-listing, hospitality-food, b2b-manufacturer, and so on). Auto-parts catalogs are the first test case, not the only target.
This skill is the brand / UX / design counterpart to a technical audit like `seo-onpage` or `accessibility-audit`. Technical findings are objective (a missing canonical is missing). Design is more subjective, so this skill is deliberately written to make the subjective assessable: every dimension is judged by observable questions about what the leading sites actually do, reported as patterns and gaps, and marked `not_assessable` whenever the evidence does not support a judgment.
---
## When to use
- Setting the experience bar for a new build in a vertical you have not built in before
- Capturing the design and UX conventions a credible site in the category is expected to carrycontent-and-copy
When your agent uses it
Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog post, draft an article, write copy for, edit this, rewrite this, write content, write a guide, draft a how-to, write web copy. Also triggers when content has been outlined and now needs to be written, or when existing content needs voice or clarity edits.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
1,892 tokensWhen the skill is activated
Reference documents
3,535 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,236 bytesreferences/content-brief-template.mddoc7,426 bytesreferences/content-edit-checklist.mddoc7,284 bytes
Read SKILL.md
# Content and Copy
Write or edit content that serves a specific reader and goal. Stack-agnostic. This skill is for general content production. Specialized skills exist for landing pages (`landing-page-copy`) and email (`email-sequences`).
---
## When to use
- Writing a blog post or article
- Drafting website copy (homepage sections, about, services)
- Editing existing content for voice or clarity
- Writing how-to guides, listicles, or explainers
- Producing knowledge base or help center articles
- Adapting brand voice to a specific piececontent-brief-authoring
When your agent uses it
How to author a content brief that actually guides a writer (human or AI) to produce a piece that ranks, converts, or both. Per-piece editorial brief: target keyword and cluster, search intent, audience and JTBD, heading structure, entity coverage for AEO/GEO, internal linking strategy, success criteria. The middle path between thin briefs (a keyword and a deadline) and thick briefs (a 4-page document nobody reads). Triggers on content brief, brief the writer, brief the article, brief authoring, content brief template, brief audit, per-piece brief, editorial brief, target keyword brief, search intent brief. Also triggers when briefing a human writer or an AI agent on a single content piece.
What it loads into context
Frontmatter
204 tokensAlways available to the agent
SKILL.md
4,885 tokensWhen the skill is activated
Reference documents
11,075 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Thin vs thick vs effective briefs
- The 12 fields of an effective brief
- Search intent classification
- Heading structure design
- Entity coverage for AEO and GEO
- Internal linking strategy
- Brief templates by content type
- The brief-to-writer handoff
- Brief governance
- Common failure modes
- The framework: 12 considerations for brief authoring
- If required data is unavailable
- Reference files
- Closing: the brief is the contract
Files
SKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesreferences/brief-governance-patterns.mddoc6,083 bytesreferences/brief-templates.mddoc7,826 bytesreferences/common-brief-failures.mddoc7,803 bytesreferences/entity-coverage-checklist.mddoc5,700 bytesreferences/heading-structure-patterns.mddoc5,438 bytesreferences/internal-linking-strategy.mddoc5,650 bytesreferences/search-intent-classification.mddoc4,799 bytesreferences/writer-handoff-protocols.mddoc6,094 bytes
Read SKILL.md
# Content Brief Authoring
A senior content strategist's playbook for authoring per-piece content briefs that actually guide writers to produce content worth publishing.
Most content briefs are some flavor of broken. The thin version is a keyword, a word count, and a deadline; the writer fills in everything else from scratch and the output is generic. The thick version is a 4-page document nobody reads, that the writer skims for the headline and the outline and ignores the rest. Either way, the brief failed at its job: making the writer's work easier and the output more predictable.
This skill is the middle path. It defines the 12 fields that earn their keep in a content brief, the fields that bloat without helping, and the discipline of writing briefs that route a writer (human or AI) toward a content piece that ranks for its target keyword, gets cited by AI engines, converts the right reader, or whatever the success criteria say. It assumes you have decided what to write (see `content-strategy` for program-level decisions) and now you are briefing each piece. The piece itself gets written separately (see `content-and-copy`).
When to use this skill: briefing a writer (human or AI) on an individual content piece, auditing existing briefs that are not producing good content, building a brief template for a content program, or running a brief-generation pipeline through Frase, AirOps, or another tool.
---
## What this skill is for
content-distribution
When your agent uses it
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel matching, distribution cadence. Triggers on content distribution, channel strategy for content, owned earned paid channels, content amplification, content promotion, audience-channel matching, content-channel matching, distribution cadence, syndication strategy, organic distribution. Also triggers when content is publishing but reach is low, when the team is distributing on every channel without strategy, or when the content program needs a distribution discipline rather than just publication.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
5,032 tokensWhen the skill is activated
Reference documents
18,908 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hope-and-pray vs spam-everywhere vs channel-fit
- Channel taxonomy
- Audience-channel matching
- Content-channel matching
- Distribution cadence
- Owned-channel discipline
- Earned-channel work
- Paid promotion of organic content
- Distribution measurement
- Common failure modes
- The framework: 12 considerations for content distribution
- If required data is unavailable
- Reference files
- Closing: distribution is half the work
Files
SKILL.mdcore25,964 bytesSKILL.mdcore25,964 bytesreferences/audience-channel-matching.mddoc10,402 bytesreferences/channel-taxonomy.mddoc13,084 bytesreferences/common-distribution-failures.mddoc11,960 bytesreferences/content-channel-matching.mddoc9,399 bytesreferences/distribution-cadence-patterns.mddoc10,644 bytesreferences/distribution-measurement.mddoc11,013 bytesreferences/earned-channel-work.mddoc11,074 bytesreferences/owned-channel-discipline.mddoc11,261 bytesreferences/paid-promotion-patterns.mddoc11,630 bytes
Read SKILL.md
# Content Distribution
A senior editorial leader's playbook for content distribution as a discipline. Owned, earned, and paid channels matched to audience and content type, with the channel-fit decisions that distinguish strategic distribution from spam-everywhere or hope-and-pray.
Content distribution is half the work and gets a fraction of the attention. Most programs spend 90% of capacity on production and 10% on distribution; the resulting ratio of effort-to-reach is consistently poor. The teams producing content that reaches audiences are the ones who treat distribution as a real discipline: channels chosen for fit, cadence calibrated to audience attention, owned-earned-paid balance set by program strategy, and effectiveness measured per channel.
This skill is the channel discipline. Different from `content-repurposing` (which turns one piece into many formats), this skill is about getting content TO audiences via the right channels. The two skills compose: repurpose first, then distribute the right format on the right channel.
The voice is the senior editorial leader who has watched programs underperform because distribution was treated as posting-after-publishing rather than as the equal half of the work.
When to use this skill: building a distribution discipline for a content program, auditing why content publishes consistently but reach is low, calibrating owned-earned-paid balance, designing channel-fit decisions for a multi-format program.
---
content-migration
When your agent uses it
Move content between platforms, domains, or URL structures while preserving SEO equity, user bookmarks, and integrations. Use this skill when planning a CMS migration, replatforming, consolidating sites, changing URL structures, or merging content from multiple sources. Triggers on content migration, replatform, CMS migration, domain migration, URL restructure, redirect map, site merge, content consolidation, migration plan, post-migration drop. Also triggers when planning a launch that involves moving existing content.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
2,447 tokensWhen the skill is activated
Reference documents
2,209 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesreferences/migration-runbook.mddoc9,515 bytes
Read SKILL.md
# Content Migration
Move content from one platform, domain, or URL structure to another without breaking SEO, user bookmarks, or downstream integrations. Stack-agnostic.
---
## When to use
- Migrating from one CMS to another (e.g., WordPress to a headless setup)
- Consolidating multiple sites into one
- Splitting one site into multiple
- Changing URL structures
- Domain migration (one brand to another, mergers, rebrands)
- Migrating from a custom build to a platform (or vice versa)content-refresh-system
When your agent uses it
Systematic content refresh discipline. Quarterly audits, refresh prioritization (which pieces, when, how deep), refresh-vs-merge-vs-delete decisions, the lifecycle that distinguishes intentional refresh from set-and-forget decay. Builds on the refresh sections of pillar-content-architecture and editorial-qa with a program-level discipline. Triggers on content refresh, content decay, content audit, refresh prioritization, content lifecycle, refresh strategy, traffic decay, ranking drop, content freshness, evergreen content, content maintenance. Also triggers when traffic is eroding silently across an aging content library, when teams cannot decide which pieces to refresh, or when refresh work is happening but the impact is unclear.
What it loads into context
Frontmatter
194 tokensAlways available to the agent
SKILL.md
5,210 tokensWhen the skill is activated
Reference documents
19,150 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Refresh-everything vs refresh-nothing vs triaged-refresh
- Refresh signals
- The audit cadence
- Refresh prioritization
- Refresh depth options
- Refresh vs merge vs delete decisions
- Refresh execution patterns
- Re-promotion after refresh
- Refresh tracking and effectiveness measurement
- Common failure modes
- The framework: 12 considerations for content refresh
- If required data is unavailable
- Reference files
- Closing: refresh is content's immune system
Files
SKILL.mdcore25,907 bytesSKILL.mdcore25,907 bytesreferences/audit-cadence-patterns.mddoc10,396 bytesreferences/common-refresh-failures.mddoc11,774 bytesreferences/effectiveness-measurement.mddoc11,055 bytesreferences/re-promotion-after-refresh.mddoc10,690 bytesreferences/refresh-depth-decision.mddoc10,655 bytesreferences/refresh-execution-patterns.mddoc10,036 bytesreferences/refresh-prioritization-matrix.mddoc11,361 bytesreferences/refresh-signals-checklist.mddoc10,605 bytesreferences/refresh-vs-merge-vs-delete.mddoc10,295 bytes
Read SKILL.md
# Content Refresh System
A senior editorial leader's playbook for systematic content refresh. The discipline that distinguishes intentional refresh programs from set-and-forget decay, and the prioritization framework that prevents both over-refresh (refresh-everything-on-calendar) and under-refresh (refresh-nothing-until-traffic-collapses).
Content decays. Search behavior shifts; SERP intent reshapes; facts go stale; competitors publish stronger pieces; the brand's own positioning evolves past what older pieces represent. Programs that ignore this reality watch traffic erode silently across the library. Programs that overreact (rewriting everything on calendar) burn editorial capacity that should be producing new flagship work. The discipline is in the middle: refresh what matters when signals say so, and document the decisions so the program is auditable.
This skill is the program-level refresh discipline across the whole content library. It builds on `pillar-content-architecture`'s hub-level refresh consideration (refresh as ONE consideration in hub design) and `editorial-qa`'s pre-publish quality gate (this skill is post-publish lifecycle, not pre-publish QA). Together those skills cover content quality at the moments quality decisions get made; this skill covers the moments between, when content is in the field and decaying or holding.
The voice is the senior editorial leader who has watched refresh programs fail in both directions and who has shipped the systems that produced durable refresh discipline.
When to use this skill: building a refresh program from scratch, auditing why refresh work is happening but traffic is not responding, designing the prioritization that keeps refresh tractable across a 200-piece or 2,000-piece library, or fixing a refresh program that is eating editorial capacity without clear results.
---
content-repurposing
When your agent uses it
Cross-format content adaptation. Turning one substantial piece into many derivative formats (blog series, email sequences, social posts, webinars, podcasts, video shorts) without losing the original's value or producing AI-slop variants. The discipline of adaptation per medium rather than mass-blast distribution. Triggers on content repurposing, content adaptation, cross-format content, content atomization, content multiplication, content distribution across formats, source-piece-to-derivative, video shorts from blog, email from whitepaper, podcast from article, blog series from research. Also triggers when a flagship piece is shipping but the team has not planned how to extend it across formats, when repurposing is happening but the derivatives feel mass-produced, or when AI-assisted repurposing is producing slop variants of strong source pieces.
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
4,928 tokensWhen the skill is activated
Reference documents
20,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- One-and-done vs mass-blast vs adapt-by-format
- Source-piece selection
- Format adaptation patterns
- Per-format constraints
- Voice consistency across formats
- Sequencing and cadence
- Cross-promotion across derivatives
- Repurposing for AI search visibility
- Common failure modes
- The framework: 12 considerations for content repurposing
- If required data is unavailable
- Reference files
- Closing: adaptation is craft, not duplication
Files
SKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesreferences/aeo-extraction-patterns.mddoc10,691 bytesreferences/common-repurposing-failures.mddoc10,731 bytesreferences/cross-promotion-patterns.mddoc9,690 bytesreferences/format-adaptation-patterns.mddoc13,696 bytesreferences/per-format-constraints.mddoc10,774 bytesreferences/repurposing-pipeline-templates.mddoc11,655 bytesreferences/sequencing-and-cadence-patterns.mddoc11,444 bytesreferences/source-piece-selection-criteria.mddoc11,167 bytesreferences/voice-consistency-across-formats.mddoc10,950 bytes
Read SKILL.md
# Content Repurposing
A senior editorial leader's playbook for cross-format content adaptation. The discipline of turning one substantial piece into many derivative formats without losing the original's value or producing slop variants.
Most content programs underspend on repurposing. A flagship piece costs 40-80 hours to produce; the program publishes it once, shares it on three channels, and moves on. The same piece could have produced a blog series, an email sequence, a webinar, a podcast episode, a dozen social posts, video shorts, and FAQ extractions for AI search visibility. The work to extend the source piece across formats is small relative to the value extracted; programs that skip repurposing leave most of the value unrealized.
The failure mode in the other direction is mass-blast: the same content reposted across channels without adaptation. A blog post pasted into LinkedIn as a long-text post; the email newsletter is the blog's first three paragraphs with "read more" tacked on; the YouTube video is a slideshow of the article text read aloud. Mass-blast respects neither the medium nor the audience. AI-assisted repurposing has made mass-blast cheap; the result is a wave of derivative content that performs poorly across every channel because it was adapted to none of them.
This skill is the discipline of adaptation per medium. Each format has constraints, conventions, and reader expectations the source piece does not have. Repurposing that respects those constraints produces work that earns engagement on the new format; repurposing that ignores them produces filler.
When to use this skill: planning the extension of a flagship piece across formats, auditing a repurposing pipeline that is producing low-engagement derivatives, calibrating an AI-assisted repurposing workflow that is producing slop, or designing the cross-format adaptation conventions for a content program.
---
content-strategy
When your agent uses it
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align content production with broader brand and SEO goals. Triggers on content strategy, content plan, editorial strategy, content pillars, content calendar, editorial calendar, topical authority, topic clusters, content governance, content roadmap, content production. Also triggers when the user is about to start producing content without a strategic plan.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
2,301 tokensWhen the skill is activated
Reference documents
3,489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,530 bytesSKILL.mdcore10,530 bytesreferences/content-strategy-template.mddoc6,745 bytesreferences/editorial-calendar-template.mddoc7,906 bytes
Read SKILL.md
# Content Strategy
Plan what content to produce, why, when, and how. Stack-agnostic. Works for blogs, knowledge bases, marketing sites, newsletters, and product content surfaces.
This skill is the strategic layer. Tactical execution sits in `content-and-copy`, `landing-page-copy`, and `email-sequences`. SEO-driven content planning sits in `seo-keyword`. This skill stitches those together into a coherent program.
---
## When to use
- Planning a new content program or relaunching an existing one
- Defining editorial positioning and content pillars
- Building an editorial calendar
- Structuring topic clusters and content hubscost-optimization
When your agent uses it
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
2,658 tokensWhen the skill is activated
Reference documents
1,995 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 levers
- Workflow
- Common opportunities by category
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesreferences/cloud-audit-checklist.mddoc8,556 bytes
Read SKILL.md
# Cost Optimization
Audit cloud, SaaS, and infrastructure spend. Cut what's not earning its keep. Rightsize what's oversized. Negotiate what's negotiable. Without breaking what works.
---
## When to use
- Quarterly or annual cost review
- Finance flags rising spend
- Vendor contract renewal coming up
- Budget cut required
- New leadership wants the numbers
- Migrating between providers (cost is part of the case)creative-brief
When your agent uses it
Create or refine a creative brief that bridges discovery and execution. Use this skill whenever the user is starting a new project, kicking off a website, beginning a brand build or redesign, briefing a designer or developer or AI agent, or trying to align a team before building. Triggers on creative brief, design brief, brand brief, project kickoff, kicking off, briefing the team, project intake, design direction, brief the designer, brief the dev, where do we start, how do we start, write a brief, project overview, scope this project, align on direction. Also triggers when the user has a vague idea and needs to make it concrete enough to hand off, even if they do not say 'brief' explicitly.
What it loads into context
Frontmatter
180 tokensAlways available to the agent
SKILL.md
1,897 tokensWhen the skill is activated
Reference documents
4,585 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: brief structure
- Eliciting missing info
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,293 bytesreferences/creative-brief-template.mddoc3,956 bytesreferences/example-brief.mddoc7,985 bytesreferences/voice-and-tone-guide.mddoc6,978 bytes
Read SKILL.md
# Creative Brief
Bridges discovery and execution. Translates "we want a website" into a brief a designer, developer, or AI agent can actually run with.
---
## When to use
- Starting a new project (website, app, brand, campaign)
- Kicking off a redesign or rebrand
- Handing work to a designer, developer, or AI agent
- Aligning a team that has drifted off course
- Turning a vague idea into something buildable
creative-brief-selector
When your agent uses it
Produce a creative brief grounded in live reference sites and deliberately distinct from existing demos, for any new brand build. Composes with brand-archetype-system and creative-direction. Use this skill at the start of any brand or microsite build when the result needs to land in a specific aesthetic position and not drift into a default house style. Triggers on creative brief, design brief, build brief, brand direction, where should this brand sit, what should this site look like, reference sites for, archetype for, distinct from our other brands, divergence from prior, not the same as. Also triggers when prior builds have come out as siblings and a systematic divergence approach is needed.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
2,137 tokensWhen the skill is activated
Reference documents
22,901 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: five steps, three rules, one hybrid bank
- The hybrid references model
- The divergence schema
- Trademark and attribution
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,044 bytesSKILL.mdcore10,044 bytesreferences/00-overview.mddoc5,349 bytesreferences/01-process.mddoc9,538 bytesreferences/02-brief-template.mddoc8,976 bytesreferences/03-divergence-check.mddoc12,675 bytesreferences/04-shipped-demos-signatures-example.mddoc8,664 bytesreferences/05-section-shapes-vocabulary.mddoc10,893 bytesreferences/reference-bank/README.mddoc7,350 bytesreferences/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.mddoc3,849 bytesreferences/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.mddoc4,837 bytesreferences/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.mddoc3,196 bytesreferences/reference-bank/editorial-restrained-literary-quarterly.mddoc3,606 bytesreferences/reference-bank/heritage-local-service-barbershop.mddoc1,888 bytesreferences/reference-bank/hospitality-experience-balloon-ride.mddoc1,891 bytesreferences/reference-bank/luxe-considered-curated-stays-directory.mddoc6,244 bytesreferences/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.mddoc3,636 bytesreferences/reference-bank/minimal-essentialist-documentary-honest-trades-directory.mddoc6,645 bytesreferences/reference-bank/premium-dtc-maker-western-boots.mddoc1,889 bytesreferences/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.mddoc3,427 bytes
Read SKILL.md
# Creative Brief Selector
A starting-point selector for brand and microsite builds. Given a business spec (name, vertical, shape, one-line vibe, optional list of shipped demos), produces a creative brief grounded in three things:
1. An archetype position from `brand-archetype-system`, picked or composed to be deliberately distinct from the shipped demos.
2. A small set of live reference sites for that archetype-and-vertical combination, drawn from a curated bank plus optional per-build discovery.
3. A divergence check against the shipped demos that flags palette, voice, structural pattern, and section-shape overlap before the brief is handed off.
The brief output is concrete tokens, not abstract families, including explicit section-shape choices (hero shape and footer shape) as first-class outputs alongside palette and voice. It is meant to be loaded by downstream build skills as the single creative artifact for the build.
---
## When to use
creative-direction
When your agent uses it
Walk the user through four directional axes (tone register, aesthetic philosophy, audience relationship, sensory ambition) and produce a structured aesthetic brief that downstream content, copy, design, and art-direction skills consume as required input. The aesthetic depth layer, distinct from `creative-brief` (operational kickoff: scope, audience, deliverables, constraints). Use when a project needs aesthetic coherence across many small decisions and the user has only a vague feeling, or when multiple downstream aesthetic-producing skills need a shared brief. Triggers on creative direction, aesthetic direction, set the aesthetic, define the visual direction, what's the vibe, what's the tone, the four axes. Does NOT fire for a general kickoff brief (use `creative-brief`), tactical single-piece work, already-documented direction, purely functional output, or locked production-stage work.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
2,349 tokensWhen the skill is activated
Reference documents
4,285 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 directional axes
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,645 bytesreferences/axes-explained.mddoc12,970 bytesreferences/brief-template.mddoc2,049 bytesreferences/example-aesthetic-brief.mddoc6,306 bytes
Read SKILL.md
# Creative Direction
Frameworks produce competent output. Coherent output requires a brief.
This skill turns vague creative intent into a structured brief that downstream skills can reference. It does not generate taste. It captures direction, so the dozens of small decisions a project requires (word choice, image selection, white space, sequencing, what to leave out) all answer to the same question.
---
> Worked examples for each axis position can be assembled from any reference brand library that documents tone, aesthetic, audience relationship, and sensory ambition consistently. The framework below describes the four axes; the user's own reference set positions each example along the axes during the brief workflow.
---
## When to use
cro-optimization
When your agent uses it
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze test results. Triggers on conversion optimization, CRO, A/B test, split test, multivariate test, hypothesis, conversion funnel, funnel audit, experiment design, statistical significance, lift, optimization. Also triggers when the user has a conversion problem and isn't sure where to start, or when test results are ambiguous and need interpretation.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,411 tokensWhen the skill is activated
Reference documents
2,132 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Statistical foundations
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,931 bytesSKILL.mdcore10,931 bytesreferences/hypothesis-library.mddoc10,380 bytes
Read SKILL.md
# CRO Optimization
Run conversion rate optimization as a structured discipline: audit → hypothesize → test → decide. Stack-agnostic. Tool-agnostic.
This skill is for running tests against existing pages and flows. For writing landing page copy from scratch, use `landing-page-copy`. For setting up the analytics that make CRO possible, use `analytics-strategy`.
---
## When to use
- Converting traffic at lower rate than expected
- Specific funnel step has high drop-off
- Pages with high traffic that could move the needle if optimized
- A/B testing infrastructure exists (or can be set up)data-warehouse-experimentation
When your agent uses it
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like Statsig and Optimizely. Triggers on warehouse-native experimentation, run experiments in BigQuery, run experiments in Snowflake, dbt experiments, SQL t-test, CUPED variance reduction, exposure log, sample ratio mismatch, sequential testing, mSPRT, doubly robust estimation, build vs buy experimentation. Also triggers when the team is choosing between platform and warehouse, building warehouse-native experiment infrastructure, auditing one, or running an experiment with a custom metric the platform cannot handle.
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
6,083 tokensWhen the skill is activated
Reference documents
15,259 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When warehouse-native is the right call
- The architecture
- Assignment patterns
- The exposure log
- Metric definitions in dbt models
- Statistical analysis in SQL
- Statistical analysis in Python
- Variance reduction: CUPED and beyond
- Pre-experiment power analysis
- Sequential testing patterns
- Common pitfalls
- The framework: 12 considerations for warehouse-native experimentation
- If required data is unavailable
- Reference files
- Closing: the build-vs-buy decision is real
Files
SKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesreferences/assignment-and-exposure-patterns.mddoc8,125 bytesreferences/common-pitfalls.mddoc10,052 bytesreferences/metric-definitions-in-dbt.mddoc8,099 bytesreferences/power-analysis-calculations.mddoc8,161 bytesreferences/sequential-testing-patterns.mddoc7,762 bytesreferences/statistical-analysis-templates.mddoc7,627 bytesreferences/variance-reduction-techniques.mddoc9,091 bytesreferences/warehouse-vs-platform-decision.mddoc7,976 bytes
Read SKILL.md
# Data Warehouse Experimentation
A senior data scientist's playbook for running experiments natively out of BigQuery, Snowflake, or any modern data warehouse, with metric definitions in dbt and statistical analysis in SQL or Python.
Most companies that run experiments at scale use a dedicated platform. Statsig, Optimizely, LaunchDarkly with experimentation, PostHog, Amplitude Experiment. The platforms are good. They handle assignment, instrumentation, and analysis in one product, and the SQL-savvy data team does not have to reinvent the variance reduction wheel.
There is a different operational model that mature data teams increasingly choose: warehouse-native experimentation. Assignment happens in code or via feature flags. Exposure events fire to the warehouse like any other event. Metrics are defined as dbt models. Statistical analysis runs as SQL or in a Python notebook against warehouse data. The "experiment platform" is just your existing data stack.
This skill covers when warehouse-native is the right call, the architecture, and the specific techniques that make it work: assignment patterns, exposure logging discipline, metric definitions in dbt, t-tests and CUPED in SQL, sequential testing, and the pitfalls that take down homegrown setups.
When to use this skill: deciding between platform vs warehouse-native, building a warehouse-native experiment infrastructure, auditing an existing one, or running a specific experiment when the platform of record cannot handle a custom metric or segmentation.
---
dependency-management
When your agent uses it
Manage third-party libraries, runtimes, and SaaS dependencies. Use this skill when setting an update cadence, responding to security advisories, dealing with deprecated dependencies, evaluating new dependencies, auditing what's installed, or unblocking a dependency upgrade. Triggers on dependency, package update, security patch, lockfile, deprecated, breaking change, supply chain, dependency audit, npm audit, dependabot, renovate. Also triggers when a build breaks after an update or when an advisory is published for a used package.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,401 tokensWhen the skill is activated
Reference documents
1,915 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of dependency
- The framework: 5 risk dimensions
- Workflow
- New dependency evaluation
- Dependency removal
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,004 bytesSKILL.mdcore11,004 bytesSKILL.mdcore11,004 bytesreferences/upgrade-checklist.mddoc8,457 bytes
Read SKILL.md
# Dependency Management
Decide what to depend on, keep dependencies current, respond to advisories, and reduce supply chain risk. Stack-agnostic principles; specifics vary by package manager.
---
## When to use
- Setting up dependency hygiene for a new or existing project
- Responding to a security advisory
- Major version upgrade of a key dependency
- Adding a new dependency (evaluation, decision)
- Removing a dependency (cleanup)
- Audit of what's installed and what's actually useddesign-standards
When your agent uses it
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card, CTA, layout, review the UI, fix the design, design system, design tokens, spacing, typography scale, button standards, mobile design. Also triggers for any production design decision where contrast, accessibility, spacing, or visual hierarchy matters.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
2,178 tokensWhen the skill is activated
Reference documents
6,137 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 standards
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,597 bytesSKILL.mdcore9,597 bytesreferences/design-tokens-template.mddoc7,347 bytesreferences/preship-checklist.mddoc5,862 bytesreferences/tailwind-patterns.mddoc8,867 bytes
Read SKILL.md
# Design Standards
Production design standards for any web project. Stack-agnostic. Tool-agnostic. Covers tokens, contrast, hierarchy, spacing, mobile rules, and the pre-ship checklist.
This skill complements `brand-identity` (which defines the visual system) and `brand-style-guide` (which documents it). This skill is for the day-to-day work of applying those standards in real components and pages.
---
## When to use
- Building a new page, section, or component
- Reviewing UI for quality, accessibility, or consistency
- Setting up design tokens for a new project
- Fixing layout, contrast, or hierarchy issuesdesign-system
When your agent uses it
Build or audit a design system including component library, design tokens, naming conventions, contribution model, and documentation. Use this skill whenever the user wants to build a design system, audit an existing system, define design tokens at the system level, structure a component library, or set up design system governance. Triggers on design system, component library, design tokens, atomic design, atoms, molecules, organisms, design system documentation, Storybook, Figma library, system governance, design contribution model. Also triggers when teams are inconsistent across products and a system is the answer.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
2,088 tokensWhen the skill is activated
Reference documents
5,782 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,771 bytesSKILL.mdcore9,771 bytesSKILL.mdcore9,771 bytesreferences/governance-playbook.mddoc8,423 bytesreferences/system-architecture.mddoc10,153 bytesreferences/system-audit-template.mddoc7,412 bytes
Read SKILL.md
# Design System
Build, evolve, or audit a design system. Stack-agnostic in principle. Implementation is stack-specific (Figma, Storybook, code library, etc.) but the structure and governance principles transfer.
This skill is for building the system. For applying a system to specific pages or components, use `design-standards`. For brand visual identity, use `brand-identity`.
---
## When to use
- Building a design system from scratch
- Auditing an existing system for gaps or fragmentation
- Defining design tokens at the system level
- Structuring a component librarydiscovery-research-synthesis
When your agent uses it
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis. Also triggers when a team has done research but cannot turn it into decisions, when synthesis is producing pretty decks but no roadmap movement, or when an upcoming PM decision needs to be grounded in research already conducted.
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
4,929 tokensWhen the skill is activated
Reference documents
18,581 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Data-dump vs insight-theater vs actionable-synthesis
- Discovery research types
- The synthesis sequence
- Tagging and clustering discipline
- Pattern naming
- From pattern to product implication
- Writing for decisions, not deck performance
- The synthesis review and validation loop
- When to halt and gather more data
- Common failure modes
- The framework: 12 considerations for discovery synthesis
- Reference files
- Closing: synthesis is where research earns its keep
Files
SKILL.mdcore25,186 bytesreferences/common-discovery-synthesis-failures.mddoc11,581 bytesreferences/from-pattern-to-product-implication.mddoc10,038 bytesreferences/pattern-naming-patterns.mddoc9,029 bytesreferences/research-types-and-when-each-fits.mddoc10,694 bytesreferences/synthesis-review-and-validation.mddoc10,987 bytesreferences/synthesis-sequence-walkthrough.mddoc11,419 bytesreferences/tagging-and-clustering-discipline.mddoc9,507 bytesreferences/when-to-gather-more-data.mddoc11,254 bytesreferences/writing-for-decisions-not-decks.mddoc10,630 bytes
Read SKILL.md
# Discovery Research Synthesis
A senior PM's playbook for turning research artifacts into decisions. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the product direction they are meant to inform.
Most discovery research never produces decisions. The team conducts interviews; the transcripts pile up; a researcher hands product the raw artifacts (data-dump) or builds a polished readout deck (insight-theater); the deck gets a 30-minute review meeting and is never referenced again. Two months later the team is making the same product decisions that the research was supposed to inform, with the same gut-feel inputs the research was supposed to displace.
The discipline is in the synthesis. Synthesis is where research earns its keep: where transcripts become tagged observations, observations cluster into patterns, patterns get named, named patterns surface product implications, and implications drive specific decisions. Without that sequence, research is performance art.
This skill covers one-off discovery research projects: a 12-week customer development sprint, a sales-call review for an onboarding redesign, a support-ticket audit informing a roadmap quarter. Different from `user-feedback-aggregation`, which covers ongoing feedback streams; different from `jtbd-framing`, which is a specific framing technique often applied within synthesis but narrower in scope.
The voice is the senior PM or staff product researcher who has run synthesis well and seen plenty of teams fail at it. Honest about where polish becomes performance and where pattern-naming slides into pattern-fabrication.
When to use this skill: synthesizing a recent batch of customer interviews, auditing why prior research has not produced product decisions, designing the synthesis output for a multi-week discovery sprint, or establishing the synthesis discipline a team currently lacks.
dispatch-authoring
When your agent uses it
Write the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope, specification, verification, delivery rules, and stop conditions, so the agent can execute unattended and return a reviewable draft PR. Use this skill whenever the user wants to hand work to an agent, write an agent brief, write instructions for Claude Code, Codex, or a Cursor agent, queue work to run overnight, or turn a plan into something an AI coder can execute without asking questions. Triggers on dispatch, hand off to an agent, agent brief, agent handoff, task brief for an AI coder, instructions for Claude Code, Codex task, Cursor agent, background agent, run this overnight, give this to an agent, unattended run. Also triggers when the user has a plan or a spec and asks how to get an agent to build it, even if they never say dispatch.
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
1,840 tokensWhen the skill is activated
Reference documents
3,293 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 parts of a dispatch
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,195 bytesSKILL.mdcore8,195 bytesreferences/dispatch-template.mddoc3,831 bytesreferences/example-dispatch-new-skill.mddoc5,615 bytesreferences/gate-zero-checklist.mddoc3,146 bytesreferences/pr-body-template.mddoc1,802 bytes
Read SKILL.md
# Dispatch Authoring
Write the handoff that lets a coding agent execute a plan unattended and come back with something a human can review. Agent-agnostic: works for Claude Code, Codex, or your coding agent of choice.
---
## When to use
- Handing a planned change to a coding agent to run without supervision
- Queueing work to run overnight or in the background
- Turning a spec or a ticket set into an executable brief for an agent
- Standardizing handoffs so agent runs are comparable and measurable
- Reviewing a draft dispatch before it goes out
documentation-strategy
When your agent uses it
Design and run a documentation system for a team or product. Use this skill when planning what to document, choosing a documentation tool, organizing existing docs, fixing stale documentation, designing a maintenance cadence, or scoping technical writing work. Triggers on documentation, docs, tech writing, knowledge base, wiki, runbook, README, internal docs, doc audit, doc maintenance, stale docs, where do we document. Also triggers when the team is repeatedly answering the same questions or when onboarding takes too long.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
2,938 tokensWhen the skill is activated
Reference documents
2,418 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of documentation
- The framework: 5 tiers of doc
- Workflow
- Specific patterns
- Tooling
- AI-related notes
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore13,060 bytesSKILL.mdcore13,060 bytesreferences/doc-types-guide.mddoc10,540 bytes
Read SKILL.md
# Documentation Strategy
Decide what gets documented, where, by whom, and how it stays fresh. Stack-agnostic. Applies to internal team docs, product docs, runbooks, READMEs, and knowledge bases.
---
## When to use
- Setting up documentation for a new team or product
- Auditing existing documentation
- Fixing stale or scattered docs
- Choosing a documentation tool or platform
- Defining what gets documented and what doesn't
- Establishing maintenance cadencedomain-strategy
When your agent uses it
Plan, manage, and optimize a domain portfolio. Use this skill for DNS architecture decisions, redirect strategies, registrar choice, parking unused domains, multi-site setups, and domain consolidation or split planning. Triggers on DNS, domain, registrar, redirect, parking, subdomain, apex, www vs non-www, multi-site, portfolio, hreflang setup, domain migration. Also triggers when planning a new site that needs domain decisions made before launch.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
1,983 tokensWhen the skill is activated
Reference documents
2,110 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 decisions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,799 bytesreferences/dns-record-reference.mddoc7,891 bytes
Read SKILL.md
# Domain Strategy
Decide how domains, subdomains, and DNS work across a portfolio. Stack-agnostic. Works for one site or one hundred.
---
## When to use
- Setting up DNS for a new site (apex vs www, primary vs aliases)
- Choosing or switching registrars
- Planning redirects across multiple domains (parked, retired, consolidated)
- Deciding subdomain vs subfolder vs separate domain for a new product line
- Consolidating multiple sites into one
- Splitting one site into multipleeditorial-qa
When your agent uses it
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
What it loads into context
Frontmatter
249 tokensAlways available to the agent
SKILL.md
4,754 tokensWhen the skill is activated
Reference documents
16,409 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Catch-problems QA vs checkbox QA
- Brief adherence check
- Voice consistency check
- Fact accuracy and citation discipline
- Structure and clarity check
- AI-content audit
- SEO and AEO compliance check
- Internal linking and schema validation
- QA at scale
- The QA workflow
- Common failure modes
- The framework: 12 considerations for editorial QA
- Reference files
- Closing: QA is where quality gets enforced
Files
SKILL.mdcore22,411 bytesSKILL.mdcore22,411 bytesreferences/ai-content-audit-patterns.mddoc9,219 bytesreferences/brief-adherence-checklist.mddoc6,950 bytesreferences/common-qa-failures.mddoc9,533 bytesreferences/fact-accuracy-and-citation-discipline.mddoc7,262 bytesreferences/internal-linking-and-schema-validation.mddoc7,152 bytesreferences/qa-at-scale-patterns.mddoc8,389 bytesreferences/qa-workflow-templates.mddoc8,208 bytesreferences/seo-aeo-compliance-checklist.mddoc7,112 bytesreferences/structure-and-clarity-review.mddoc7,106 bytesreferences/voice-consistency-patterns.mddoc6,791 bytes
Read SKILL.md
# Editorial QA
A senior editor's playbook for pre-publish content QA. The discipline that catches problems BEFORE content ships, not after.
Most content QA is broken in one of two directions. The thin version is "did I read it once and is the spelling OK," which catches typos but misses brief drift, voice inconsistency, hallucinated facts, AI tells, and structural problems that reach readers as "this is fine but not memorable." The thick version is a 47-item checklist that nobody completes honestly because it is process theater: checkboxes nobody actually believes catch problems.
This skill is the discipline of catch-problems QA. Each check earns its keep by catching a specific class of failure that would reach readers if missed. Checks that do not catch anything get cut. Checks the production volume cannot sustain get redesigned (sampling instead of full audit, automated instead of manual). The QA framework is what is left when you remove the theater.
The skill covers three production shapes: single editorial pieces (one at a time, full QA), AI-generated drafts (with the AI-content audit that did not exist as prominently 2 years ago), and programmatic SEO sets at scale (sampling discipline, threshold gating). Each needs its own QA shape; the underlying methodology composes across all three.
When to use this skill: building a content QA process from scratch, auditing an existing QA process that ships sloppy work or burns out the team, designing QA gates for an AI-assisted workflow, or building sampling discipline for programmatic SEO sets.
---
email-deliverability
When your agent uses it
Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation strategy, monitoring sender reputation, or hardening against email spoofing. Triggers on email deliverability, SPF, DKIM, DMARC, spam folder, sender reputation, mailbox provider, soft bounces, bounce rate, BIMI, MTA-STS, deliverability audit. Also triggers when a marketing or transactional email isn't reaching users.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,695 tokensWhen the skill is activated
Reference documents
2,264 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 pillars
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,489 bytesSKILL.mdcore11,489 bytesreferences/dmarc-rollout-playbook.mddoc9,199 bytes
Read SKILL.md
# Email Deliverability
Get email into inboxes, not spam folders. Set up authentication. Monitor reputation. Diagnose problems before they hurt the business.
---
## When to use
- Setting up email for a new domain
- A meaningful percentage of email is going to spam
- Customers report they're not receiving emails
- Setting up DMARC, SPF, or DKIM
- Hardening against domain spoofing
- Migrating email service providersemail-sequences
When your agent uses it
Design and write email campaigns and sequences including onboarding flows, lifecycle campaigns, transactional emails, newsletters, broadcast sends, and launch and announcement emails. Use this skill whenever the user wants to write email copy, plan an email sequence, design an onboarding drip, or set up lifecycle email campaigns. Triggers on email sequence, drip campaign, onboarding email, lifecycle email, welcome email, transactional email, newsletter, email broadcast, launch email, announcement email, nurture sequence, abandoned cart, re-engagement, win-back. Also triggers when planning email automation flows or writing email subject lines for campaigns.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,369 tokensWhen the skill is activated
Reference documents
3,782 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 sequence types
- The 5 components of every email
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,431 bytesreferences/sequence-templates.mddoc8,158 bytesreferences/subject-line-patterns.mddoc7,559 bytes
Read SKILL.md
# Email Sequences
Plan and write email campaigns. Sequences (multi-message flows triggered by events) and broadcasts (one-off sends). Stack-agnostic. Works with any email service provider.
---
## When to use
- Writing welcome and onboarding email sequences
- Planning lifecycle campaigns (activation, retention, win-back)
- Writing transactional emails (receipts, password resets, notifications)
- Newsletter design and writing
- Abandoned-cart or re-engagement flows
- Writing a one-off broadcast, launch announcement, or news emailevidence-based-reviews
When your agent uses it
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
2,482 tokensWhen the skill is activated
Reference documents
1,433 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: one rule, four evidence tiers
- The methodology block
- Structure discipline the method implies
- Google reviews-system alignment
- FTC alignment
- Schema judgment
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesreferences/evidence-tiers.mddoc4,193 bytesreferences/methodology-block-template.mddoc2,760 bytes
Read SKILL.md
# Evidence-Based Reviews
Produce product reviews and buying guides whose claims match their evidence. The method is evidence synthesis with a disclosed basis, and one rule anchors everything: never claim hands-on time that did not happen.
Most review sites fail this rule quietly. "We tested" appears above content assembled from spec sheets, and readers have learned to smell it. The honest alternative is stronger, not weaker: synthesis of owner experience at scale, verified specifications, and triangulated expert sources is demonstrable original analysis, and disclosing it builds the trust that fabricated testing destroys.
---
## When to use
- Writing product reviews or buying guides when hands-on access is partial or absent
- Setting up the review methodology for a new review or affiliate site
- Adding evidence disclosure to existing review content
- Auditing review content for claims its evidence cannot supportexperiment-design
When your agent uses it
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.
What it loads into context
Frontmatter
237 tokensAlways available to the agent
SKILL.md
6,363 tokensWhen the skill is activated
Reference documents
11,961 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The framework: 12 considerations for trustworthy experiment results
- Hypothesis discipline
- Sample size and minimum detectable effect
- Test duration
- What NOT to A/B test
- Segment analysis
- Interaction effects
- Ratio metrics and the delta method
- Network effects and two-sided markets
- Sequential testing and the peeking problem
- Pre-commitment vs p-hacking
- Reading results and making the call
- Common failures and fixes
- If required data is unavailable
- Reference files
- Closing: when in doubt
Files
SKILL.mdcore31,727 bytesSKILL.mdcore31,727 bytesreferences/common-failures.mddoc10,946 bytesreferences/hypothesis-templates.mddoc8,742 bytesreferences/platform-comparison.mddoc10,392 bytesreferences/post-experiment-decision-framework.mddoc6,436 bytesreferences/pre-experiment-readiness-checklist.mddoc5,457 bytesreferences/results-interpretation-checklist.mddoc7,660 bytesreferences/sample-size-tables.mddoc6,398 bytes
Read SKILL.md
# Experiment Design
A senior product manager's playbook for running experiments that produce trustworthy decisions.
The default state of experimentation in most companies is sloppy. PMs run tests against vague hypotheses, look at results too early, ignore guardrails, stratify into noise, and ship features whose lift is mostly measurement error. The cost is real: ship the wrong thing, kill the right thing, learn the wrong lesson, repeat.
This skill is the discipline that prevents most of those mistakes. It assumes you have a working experimentation platform (Statsig, PostHog, GrowthBook, Optimizely, Amplitude, Eppo, Kameleoon; the platform does not matter for the principles). It assumes you have product-design and engineering pipelines that can deliver real treatment changes. The hard part is the thinking, and that is what is here.
When to use this skill: any time you are about to design or interpret an experiment. Read the relevant section before you start, not after the test is running.
---
## What this skill covers
experimentation-analytics
When your agent uses it
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this skill whenever the user is reading a finished experiment result panel and about to make a ship, kill, or iterate decision, or when an experiment number does not match the dashboard number. Triggers on read experiment results, result panel, ship or kill decision, p-value, confidence interval, statistical significance, multiple testing, peeking, sequential testing, CUPED, variance reduction, heterogeneous treatment effects, ratio metric, network effects, inconclusive test, experiment versus dashboard mismatch. Use `experiment-design` instead when the test has not run yet and the question is hypothesis, sample size, duration, or what to test.
What it loads into context
Frontmatter
228 tokensAlways available to the agent
SKILL.md
7,295 tokensWhen the skill is activated
Reference documents
14,467 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every modern platform should expose
- Confidence intervals: the most important number
- P-values: what they mean and what they do not
- Multiple testing corrections
- Sequential testing math
- CUPED variance reduction
- Heterogeneous treatment effects (HTE) and segments
- Ratio metrics and the delta method
- Bayesian vs frequentist results panels
- Network effects and SUTVA violation
- Dashboard metric vs experiment metric reconciliation
- Long-term effect estimation
- Common interpretation failures
- The framework: 14 considerations for trustworthy experiment interpretation
- Reference files
- Closing: the courage to call it inconclusive
Files
SKILL.mdcore35,748 bytesreferences/analytics-platform-comparison.mddoc10,160 bytesreferences/common-interpretation-failures.mddoc13,900 bytesreferences/confidence-interval-cheatsheet.mddoc7,164 bytesreferences/dashboard-vs-experiment-reconciliation.mddoc7,403 bytesreferences/p-value-interpretation-guide.mddoc8,111 bytesreferences/result-presentation-templates.mddoc9,227 bytesreferences/statistical-method-reference.mddoc11,787 bytes
Read SKILL.md
# Experimentation Analytics
A data-team-mentor's playbook for interpreting experiment results without fooling yourself.
The result panel is the moment-of-truth for an experiment. The numbers on it determine whether you ship, kill, or iterate. They also expose every shortcut taken in the design phase: an underpowered test produces wide confidence intervals; a peeked test produces a too-narrow p-value; a ratio metric without delta-method correction produces overconfident lift estimates. Most ship-the-wrong-thing decisions trace back to misreading the result panel.
This skill is the discipline that prevents misreading. It assumes the experiment was designed well (see the `experiment-design` skill). It assumes the platform's results panel is technically correct (most modern platforms are; some older ones are not). It assumes you can read a number off a screen. The hard part is knowing what each number actually means and what it does not, and that is what is here.
When to use this skill: any time you are reading an experiment result panel and about to make a ship, kill, or iterate decision.
---
## What this skill is for
experimentation-platform-orchestrator
When your agent uses it
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
What it loads into context
Frontmatter
218 tokensAlways available to the agent
SKILL.md
5,354 tokensWhen the skill is activated
Reference documents
10,997 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The 7 considerations for the platform decision
- Statsig
- PostHog
- GrowthBook
- Optimizely
- Amplitude
- Eppo
- Kameleoon
- Decision matrix: which platform for which context
- Multi-platform: when warranted, when a mess
- Migration patterns
- The cost reality
- Governance and team fit
- The MCP capability layer
- When to defer the decision
- Common mistakes
- The framework: 11 considerations for sustainable platform choice
- Reference files
- Closing: when in doubt, pick boring
Files
SKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesreferences/common-mistakes.mddoc9,003 bytesreferences/cost-and-pricing-models.mddoc8,045 bytesreferences/governance-and-team-setup.mddoc7,543 bytesreferences/mcp-capability-comparison.mddoc6,018 bytesreferences/migration-playbook.mddoc8,243 bytesreferences/multi-platform-orchestration.mddoc7,159 bytesreferences/platform-decision-matrix.mddoc6,525 bytes
Read SKILL.md
# Experimentation Platform Orchestrator
A senior product and engineering leader's playbook for making the experimentation platform decision and recovering from making it wrong.
Picking an experimentation platform is one of those decisions that looks easy at the start and compounds for years afterward. The wrong choice costs you in lost experiments (because the team avoids the painful workflow), in cost (because the wrong pricing model penalizes your usage shape), in vendor lock-in (because migration is real engineering work, not a config change), and in cultural drift (because the platform's defaults shape what your team thinks experimentation is).
This skill is the discipline that makes the decision well the first time and the migration plan when you didn't.
When to use this skill: choosing a platform from scratch, evaluating whether to switch, deciding whether to consolidate from multi-platform to single, or planning a migration that has already been approved.
---
## What this skill is for
feature-flagging
When your agent uses it
Operational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy, lifecycle, governance, stale flag management, and the technical debt patterns that bite teams who weren't deliberate about it.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
5,370 tokensWhen the skill is activated
Reference documents
9,530 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The five flag types
- Flag naming conventions
- The flag lifecycle
- Targeting rules and segmentation
- Rollout strategies
- Stale flag management
- Governance and permissions
- Flag dependencies and conflicts
- Performance considerations
- Testing flag-gated code
- Rollback discipline
- Observability on flags
- Common failures (rapid-fire)
- The framework: 14 considerations for sustainable feature flagging
- If required data is unavailable
- Reference files
- Closing: when to remove a flag
Files
SKILL.mdcore25,796 bytesSKILL.mdcore25,796 bytesSKILL.mdcore25,796 bytesreferences/flag-lifecycle-checklist.mddoc5,006 bytesreferences/flag-naming-conventions.mddoc5,094 bytesreferences/flag-rollout-strategies.mddoc7,061 bytesreferences/flag-types-reference.mddoc6,712 bytesreferences/governance-and-permissions.mddoc6,954 bytesreferences/stale-flag-cleanup-playbook.mddoc6,154 bytesreferences/targeting-rule-patterns.mddoc6,706 bytes
Read SKILL.md
# Feature Flagging
A senior engineer's playbook for using feature flags well, not just frequently.
Feature flags are infrastructure. Treated as such, they enable kill switches, gradual rollouts, A/B experiments, permission gates, and operational toggles without redeploys. Treated casually, they become the largest accumulating technical debt in your codebase: thousands of dead flags, conflicting evaluation logic, brittle targeting, and a permission surface no one fully understands.
This skill is the discipline that prevents the second outcome. It assumes you have a feature flag platform (LaunchDarkly, Flagsmith, Split.io, VWO FME, GrowthBook, Statsig, PostHog, Optimizely; the platform does not matter for the principles). It assumes your engineering team can implement targeting rules and SDK integration. The hard part is the operational discipline, and that is what is here.
When to use this skill: any time you are about to introduce a flag, modify a flag, audit existing flags, or design a flag-related governance policy.
---
## What this skill is for
feature-launch-playbook
When your agent uses it
The operational playbook for launching a feature well. Positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring with pre-defined rollback triggers, post-launch measurement against spec hypotheses, and the discipline that distinguishes shipping from releasing from actually launching. Triggers on launch plan, feature launch, launch checklist, ship vs release, rollout strategy, gradual rollout, sales enablement, support readiness, launch announcement, post-launch measurement, launch failure, declared victory too early. Also triggers when planning a launch (any size, any segment), auditing an existing launch process, fixing the we shipped it but the metric did not move problem, or building a launch checklist for the team.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
5,441 tokensWhen the skill is activated
Reference documents
18,158 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Ship vs release vs launch
- Launch tiers
- Pre-launch: positioning
- Pre-launch: internal alignment
- Pre-launch: customer comms plan
- Pre-launch: sales enablement (B2B)
- Pre-launch: support readiness
- Launch day: rollout strategy
- Launch day: monitoring
- Launch day: comms execution
- Post-launch: measurement against spec hypotheses
- Post-launch: iteration and follow-ups
- Common failure modes
- The framework: 12 considerations for a real launch
- If required data is unavailable
- Reference files
- Closing: most failed launches are unlaunched
Files
SKILL.mdcore26,290 bytesSKILL.mdcore26,290 bytesreferences/common-launch-failures.mddoc11,194 bytesreferences/customer-comms-playbook.mddoc8,102 bytesreferences/internal-alignment-checklist.mddoc7,355 bytesreferences/launch-tier-decision.mddoc6,987 bytesreferences/monitoring-readiness-checklist.mddoc8,429 bytesreferences/positioning-canvas.mddoc8,542 bytesreferences/post-launch-measurement-framework.mddoc9,449 bytesreferences/rollout-strategy-patterns.mddoc8,971 bytesreferences/sales-enablement-template.mddoc8,314 bytesreferences/support-readiness-checklist.mddoc7,719 bytes
Read SKILL.md
# Feature Launch Playbook
A veteran PM-leader's playbook for launching features well, not just shipping them.
Most teams conflate shipping, releasing, and launching. Shipping means engineering work is complete. Releasing means users can access it, even if it is behind a flag at 1 percent. Launching is the discipline of positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring, and post-launch measurement that turns "feature exists" into "feature lands."
A feature that ships without launching costs you the same engineering investment but captures a fraction of the value. Sales does not know how to sell it. Support does not know how to help with it. Customers do not notice it. The metric you said you would move does not move because nobody knows the feature is there.
This skill is the operational playbook. It assumes you have already written the spec (`pm-spec-writing`), prioritized it onto the roadmap (`roadmap-planning`), instrumented it (`product-analytics-setup`), and possibly tested it (`experiment-design`). The launch is the next discipline: how to actually get the feature in front of the right users, with the right context, in a way that lets you measure whether it worked.
When to use this skill: planning a launch (any size, any segment), auditing an existing launch process, fixing the "we shipped it but the metric did not move" problem, or building a launch checklist for the team.
---
form-strategy
When your agent uses it
Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are low or spam is overwhelming.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
2,521 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,441 bytesSKILL.mdcore11,441 bytesreferences/form-anatomy-checklist.mddoc9,144 bytes
Read SKILL.md
# Form Strategy
Forms are where intent becomes action. Design them well or lose conversions, frustrate users, and drown in spam. Stack-agnostic.
---
## When to use
- Designing or redesigning a form
- Conversion is dropping on a key form
- Spam volume is overwhelming the inbox or database
- Auditing forms across a site
- Planning validation logic
- Choosing form tooling (form service, custom build, no-code)frontend-component-build
When your agent uses it
Build production-ready frontend components with accessible markup, sensible props, defined states, and tested behavior. Use this skill whenever the user wants to build a component from scratch, refactor an existing one, design a component API, or implement a UI element with proper states and accessibility. Triggers on build a component, create a button, create a modal, create a form input, component API, props design, component states, refactor component, accessible component. Also triggers when implementing UI from a design that needs to be reusable.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
1,921 tokensWhen the skill is activated
Reference documents
5,809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore8,657 bytesreferences/accessibility-patterns.mddoc8,072 bytesreferences/component-api-patterns.mddoc8,038 bytesreferences/component-spec-template.mddoc7,070 bytes
Read SKILL.md
# Frontend Component Build
Build production-ready components. Stack-agnostic principles. Most patterns translate to React, Vue, Svelte, or vanilla web components.
This skill is about implementing a component well. For broader system design see `design-system`. For day-to-day visual decisions see `design-standards`.
---
## When to use
- Building a new component from scratch
- Refactoring an existing component
- Designing a component API (props, slots, events)
- Adding accessibility to an existing componentfunnel-flow-architecture
When your agent uses it
Architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. Honest about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience-and-stage) patterns. Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, multi-tool funnel orchestration. Also triggers when the team's growth tools are working individually but not together, when audience segments share one nurture path, or when a funnel is being architected from scratch.
What it loads into context
Frontmatter
198 tokensAlways available to the agent
SKILL.md
4,363 tokensWhen the skill is activated
Reference documents
16,383 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Silo-funnels vs kitchen-sink-funnels vs matched-funnels
- Audience and stage segmentation
- Entry-point architecture
- Tool-to-funnel mapping
- Nurture sequence architecture
- Cross-tool data flow
- Funnel measurement
- Funnel iteration discipline
- Architecture anti-patterns
- The framework: 12 considerations for funnel flow architecture
- If required data is unavailable
- Reference files
- Closing: funnels are architecture, not collections
- Closing: funnels earn investment when they compose
Files
SKILL.mdcore22,328 bytesSKILL.mdcore22,328 bytesreferences/architecture-anti-patterns.mddoc8,941 bytesreferences/audience-and-stage-segmentation.mddoc9,391 bytesreferences/common-funnel-architecture-failures.mddoc8,080 bytesreferences/cross-tool-data-flow-patterns.mddoc10,099 bytesreferences/entry-point-architecture-patterns.mddoc8,906 bytesreferences/funnel-iteration-discipline.mddoc8,491 bytesreferences/funnel-measurement-patterns.mddoc9,505 bytesreferences/nurture-sequence-architecture.mddoc10,947 bytesreferences/tool-to-funnel-mapping.mddoc9,924 bytes
Read SKILL.md
# Funnel Flow Architecture
A senior growth practitioner's playbook for architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. The discipline of building a funnel architecture, not just collecting tools.
Most growth programs accumulate tools without architecture. A chatbot, a calculator, a quiz, a lead magnet, a newsletter signup, a demo CTA. Each tool works individually; none of them work together. Visitors hit one tool, leave, and never enter the broader nurture sequence. The funnel is a collection of orphans.
The growth programs that compound do something different. They architect the funnel deliberately. Different entry points lead to different nurture sequences. Different stages get different CTAs. Different tools serve different segments. Each tool is part of a larger architecture, not a standalone artifact.
This skill is the architecture skill that orchestrates the other 5 growth-tooling skills (lead-magnet-design, calculator-design, quiz-and-assessment-design, multi-step-form-design, chatbot-flow-design). Where those skills zoom into specific tool design, this skill zooms out to the cross-tool architecture that determines whether the tools compound.
The voice is the senior growth practitioner who has watched funnels architecture compound and watched siloed funnel collections produce engagement metrics with no business impact. Practical, opinionated about the difference between collecting tools and architecting funnels, willing to call out when a team's growth program needs architecture rather than another tool.
When to use this skill: architecting a funnel from scratch, auditing a growth program where tools work individually but conversion is flat, designing the cross-tool data flow that captures audience signal across touchpoints, or deciding which segments warrant which funnel paths.
incident-response
When your agent uses it
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,183 tokensWhen the skill is activated
Reference documents
1,981 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Roles during an incident
- Decision-making during an incident
- Status page communication patterns
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,957 bytesSKILL.mdcore9,957 bytesreferences/incident-playbook.mddoc9,180 bytes
Read SKILL.md
# Incident Response
Manage active production incidents from detection to resolution. Stack-agnostic. Tool-agnostic.
This skill is for active incidents and incident process. For after-the-fact analysis, use `after-action-report`. For planned launches, use `launch-runbook`.
---
## When to use
- An active incident is happening
- Building incident response procedures
- Defining severity levels
- Setting up on-call rotationsinformation-architecture
When your agent uses it
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system level. Triggers on sitemap, site structure, navigation, IA, information architecture, URL structure, content types, taxonomy, categorization, breadcrumbs, hub pages, faceted navigation, site search, labeling. Also triggers when content is being created without a structural plan, or when an existing site's structure is being audited or restructured.
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
2,251 tokensWhen the skill is activated
Reference documents
3,871 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,456 bytesSKILL.mdcore10,456 bytesreferences/ia-document-template.mddoc7,519 bytesreferences/url-pattern-library.mddoc8,047 bytes
Read SKILL.md
# Information Architecture
Design the structure that holds the content. Stack-agnostic. Applies to marketing sites, product surfaces, knowledge bases, e-commerce, and editorial content.
A well-designed IA makes the rest of the project easier. A poorly-designed IA forces every downstream decision to fight the structure.
---
## When to use
- Designing a new site or major section from scratch
- Restructuring an existing site
- Adding a new content type or category
- Designing site navigation or menu systemsintegration-orchestrator
When your agent uses it
Generate a phased delivery orchestration plan for creative-direction-driven work: which skills run when, what locks at which gate, how handoffs occur, and how the cadence implements in the team's tools (Jira, Linear, Notion, Figma, GitHub) with AI agents via MCP and CLI. A temporal map of phases, lock points, handoff specs, gate definitions, and QA verification gates. Distinct from `creative-brief` (static project brief) and `creative-direction` (aesthetic direction). Triggers on integration orchestrator, delivery cadence, project orchestration, when does the brief lock, how to phase creative direction, design-development handoff, QA gate, agent-driven QA, and when a creative-direction project is starting, mid-flight with broken cadence, or integrating AI agents into PM workflow. Does NOT fire for project scoping (use `creative-brief`), aesthetic direction (use `creative-direction`), or general project management without a creative-direction throughline.
What it loads into context
Frontmatter
240 tokensAlways available to the agent
SKILL.md
4,371 tokensWhen the skill is activated
Reference documents
18,404 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is
- When to use
- When NOT to use
- Required inputs
- The framework: 7 considerations for orchestration
- Common project-type cadences
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore21,008 bytesSKILL.mdcore21,008 bytesreferences/automation-and-qa-tooling.mddoc12,839 bytesreferences/cadence-patterns.mddoc11,589 bytesreferences/example-orchestration.mddoc15,949 bytesreferences/gate-definitions.mddoc9,868 bytesreferences/handoff-protocols.mddoc12,110 bytesreferences/platform-implementation.mddoc17,271 bytesreferences/team-size-modulation.mddoc7,938 bytes
Read SKILL.md
# Integration Orchestrator
A brief tells a team what to make. Creative direction tells them what it should feel like. Neither tells them when each decision locks, who reviews what, or what stops the next phase from starting before the prior one is done. That is the gap this skill fills.
The output is a phased orchestration plan the PM can paste into a calendar Monday morning and start running Tuesday. Phases, gates, lock points, handoffs, QA verification rules, and a platform-specific implementation guide for whatever stack the team actually uses (Jira, Linear, Notion, Figma, GitHub, agile sprints).
---
## What this skill is
A creative-direction project has three layers. The brief layer defines scope, audience, deliverables, constraints, success criteria. The direction layer defines tone, aesthetic, relationship, and sensory ambition. Both produce written artifacts. Neither answers the temporal question: when does the brief lock, when does identity lock, when does copy lock, who reviews each, what gets blocked while a gate is open, what happens when a downstream task discovers the brief is wrong, and what makes "Done" mean tested rather than self-reported.
This skill produces that temporal layer. Most teams have briefs and creative direction but no orchestration plan. The result, by week 3, is everyone working in parallel with no shared sense of which decisions are still open and which are locked. Brief drift. Re-work. Identity tokens shifted after copy was already drafted against the old ones. Engineering shipping before design had a chance to review. "Done" tickets that were never actually verified.
interactive-product-tour
When your agent uses it
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of need), and contextual-when-needed (surfaces help at the moment friction occurs) patterns. Triggers on product tour, in-product tooltip, contextual help, walkthrough, feature tour, hint system, in-app guidance, tour platform. Also triggers when feature adoption is low, when users miss key product capabilities, or when an in-product help system is being scoped for the first time.
What it loads into context
Frontmatter
210 tokensAlways available to the agent
SKILL.md
3,677 tokensWhen the skill is activated
Reference documents
12,998 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The tour decision: when tours earn vs when documentation suffices
- Tooltip-spam vs one-and-done vs contextual-when-needed
- Trigger logic: event-based vs time-based vs state-based
- Tour architecture: single tour vs branched vs library of micro-tours
- Contextual placement: where help appears, how it dismisses
- Completion tracking and re-trigger logic
- Power-user vs new-user differentiation
- Common failure modes
- The framework: 12 considerations for product tour design
- Reference files
- Closing: tours earn the user's attention by being absent until needed
Files
SKILL.mdcore17,715 bytesreferences/common-tour-failures.mddoc5,873 bytesreferences/completion-tracking-and-re-trigger.mddoc7,291 bytesreferences/contextual-placement-patterns.mddoc6,927 bytesreferences/dismissal-and-non-intrusion-patterns.mddoc7,153 bytesreferences/power-user-vs-new-user-patterns.mddoc7,350 bytesreferences/tour-anti-patterns.mddoc7,293 bytesreferences/tour-architecture-patterns.mddoc6,595 bytesreferences/tour-decision-criteria.mddoc6,966 bytesreferences/trigger-logic-patterns.mddoc7,198 bytes
Read SKILL.md
# Interactive Product Tour
A senior product marketing director's playbook for designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. The discipline of building help systems that surface at moments of need and disappear when not needed.
Most product tours fail in one of two ways. They paint every button, link, and feature with "click for tour" hints until the visual noise is so great that users develop blindness to the dots. Or they show a single first-login tour the user skips or skims, after which the same help never re-surfaces when the user actually hits a moment of friction. Help that is invisible at the moment of need is help that does not exist.
The tours that work do something different. They trigger when the user is at a moment of friction, not all the time. They surface contextual hints when the user enters a section they have not explored, clicks into a feature requiring setup, or returns after a long absence. The system knows what the user knows and surfaces help at the right moment.
The voice is the senior product marketing director who has watched feature adoption double when tours were redesigned and watched it collapse when more tooltips were piled onto every surface. Practical, opinionated about the trigger logic that distinguishes useful help from visual noise, willing to call out when no in-product tour at all is the right answer.
When to use this skill: scoping an in-product help system for the first time, auditing a tour system that produces engagement metrics with no adoption lift, designing the trigger logic that decides when help surfaces, or deciding which features warrant tours vs documentation.
---
internationalization
When your agent uses it
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled internationalization rollout. Triggers on internationalization, i18n, localization, l10n, hreflang, multi-language, translation workflow, RTL, locale, ccTLD, subfolder vs subdomain, language switcher. Also triggers when international audiences underperform or translations are stale.
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
2,672 tokensWhen the skill is activated
Reference documents
2,029 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesreferences/locale-checklist.mddoc8,829 bytes
Read SKILL.md
# Internationalization
Add languages and regions in a way that works for users, search engines, and the team maintaining the content. Stack-agnostic.
---
## When to use
- Adding the first non-English (or non-default) language
- Adding additional locales to an existing internationalized site
- Choosing URL structure for languages
- Implementing hreflang tags
- Designing translation workflow
- Handling currency, date, time, and number formatsjourney-mapping
When your agent uses it
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the user experience, or visualize touchpoints and pain points. Triggers on customer journey, journey map, service blueprint, user journey, experience map, touchpoint analysis, friction map, journey audit, end-to-end experience, customer experience map. Also triggers when the team has departmental views of users but no shared map of what the experience actually feels like.
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
2,143 tokensWhen the skill is activated
Reference documents
1,721 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 deliverables
- Common phases by product type
- How to gather the inputs
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,007 bytesSKILL.mdcore10,007 bytesreferences/journey-map-template.mddoc6,875 bytes
Read SKILL.md
# Journey Mapping
Build journey maps and service blueprints that surface friction, align teams, and identify opportunities. Stack-agnostic. Tool-agnostic.
This skill is for mapping the experience. For testing specific touchpoints, use `usability-testing`. For broader generative research, use `ux-research`. For analyzing conversion, use `cro-optimization`.
---
## When to use
- Departments have different mental models of the customer experience
- Customer experience feels disjointed across touchpoints
- Specific friction or drop-off points need diagnosis
- Strategic planning needs a shared view of the userjtbd-framing
When your agent uses it
The Jobs-to-be-Done framework as applied product methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity (discovery, prioritization, positioning) and where it becomes performative ritual (job-statement workshops that do not drive decisions, persona-theater disguised as JTBD). Triggers on jobs-to-be-done, JTBD, job statements, struggling moments, hire criteria, fire criteria, switch triggers, functional emotional social jobs, outcome-driven innovation. Also triggers when a team is over-relying on feature-request lists or persona archetypes that do not drive product decisions, when a positioning conversation needs the framing JTBD provides, or when discovery is producing outputs that do not connect to product strategy.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
4,378 tokensWhen the skill is activated
Reference documents
16,384 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Feature-request-list vs persona-theater vs job-framing
- The job statement structure
- Identifying struggling moments
- Hire and fire criteria
- Functional, emotional, and social dimensions of jobs
- Where JTBD adds clarity vs where it becomes ritual
- Applying JTBD to discovery, prioritization, positioning
- Common failure modes
- The framework: 12 considerations for JTBD framing
- If required data is unavailable
- Reference files
- Closing: jobs over features
Files
SKILL.mdcore21,757 bytesSKILL.mdcore21,757 bytesreferences/applying-jtbd-to-discovery.mddoc10,969 bytesreferences/applying-jtbd-to-positioning.mddoc10,319 bytesreferences/applying-jtbd-to-prioritization.mddoc11,069 bytesreferences/common-jtbd-failures.mddoc11,018 bytesreferences/functional-emotional-social-dimensions.mddoc10,358 bytesreferences/hire-and-fire-criteria.mddoc10,674 bytesreferences/identifying-struggling-moments.mddoc9,877 bytesreferences/job-statement-structure-patterns.mddoc9,309 bytes
Read SKILL.md
# Jobs-to-be-Done Framing
A senior product leader's playbook for the Jobs-to-be-Done framework as applied methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity and where it becomes performative ritual.
JTBD has become one of the more cited and less practiced frameworks in product. Teams cite it in strategy docs, run job-statement workshops, produce wall-sized artifacts, and continue building from feature requests and persona archetypes the next quarter. The methodology gets the credit; the practice gets skipped.
This skill is JTBD as applied product methodology. The framework's actual contribution: surfacing what users are trying to ACCOMPLISH (the job) rather than treating users as preference-aggregators (feature requests) or demographic archetypes (persona theater). When the framing is grounded in struggling moments and hire/fire criteria, it produces decisions; when it stops at the job-statement worksheet, it produces ritual.
This skill is honest about both modes. JTBD genuinely earns its keep in discovery, prioritization, and positioning when applied with rigor. It becomes ceremony when teams treat job statements as deliverables rather than as analytical tools.
The voice is the senior product leader who has used JTBD well and watched plenty of teams use it badly. Concrete, opinionated about what the framework actually contributes, willing to call out where it gets oversold.
When to use this skill: applying JTBD to a discovery cycle, replacing persona-driven prioritization with job-driven prioritization, reframing positioning around what users hire the product to do, or auditing whether existing JTBD work in the org is driving decisions.
landing-page-copy
When your agent uses it
Write landing page copy with attention to the hero, value proposition, social proof, objection handling, and conversion-focused CTAs. Use this skill whenever the user wants to write a landing page, sales page, hero section, or any conversion-focused web copy. Triggers on landing page, sales page, hero copy, value proposition, headline, subheadline, hero section, CTA copy, conversion copy, opt-in page, squeeze page. Also triggers when the user has a marketing campaign or product launch needing dedicated conversion copy. Use `cro-optimization` instead when the page already exists and the ask is to lift its conversion rate through testing rather than to write the copy.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
2,506 tokensWhen the skill is activated
Reference documents
3,999 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 sections
- The CTA itself
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,807 bytesSKILL.mdcore10,807 bytesreferences/hero-formulas.mddoc7,286 bytesreferences/objection-library.mddoc10,581 bytes
Read SKILL.md
# Landing Page Copy
Write copy for pages with a single conversion goal: signup, purchase, demo request, download, lead capture. Stack-agnostic.
This skill is narrower than `content-and-copy`. Landing pages exist to drive a specific action, not to inform broadly.
---
## When to use
- Writing a hero section for a homepage or product page
- Writing a sales page or long-form sales letter
- Drafting opt-in or lead-capture page copy
- Campaign-specific landing pageslaunch-runbook
When your agent uses it
Plan and execute a launch runbook covering pre-launch verification, go-live procedures, DNS cutover, post-launch monitoring, and rollback procedures. Use this skill whenever the user is preparing to launch a website or product, planning a DNS cutover, building a go-live checklist, or executing a launch day. Triggers on launch runbook, go-live, launch day, DNS cutover, deploy to production, site launch, product launch, cutover plan, launch checklist, deployment procedure. Also triggers when a launch is approaching and the team needs structured coordination, even if 'runbook' is not explicitly stated.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
1,769 tokensWhen the skill is activated
Reference documents
2,124 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Roles and responsibilities
- Rollback criteria
- Communication plan
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore7,870 bytesreferences/runbook-template.mddoc8,785 bytes
Read SKILL.md
# Launch Runbook
Plan and execute the launch of a website, product, or major release. The runbook is the document everyone uses on launch day. Stack-agnostic.
This skill is for the launch event. For pre-launch QA, use `qa-testing`. For post-launch incident handling, use `incident-response`.
---
## When to use
- Launching a new website or major redesign
- Migrating from one platform to another
- Releasing a major product or feature
- Coordinating cross-team launcheslead-magnet-design
When your agent uses it
Designing lead magnets that earn the email. The discipline of building gated content (ebooks, templates, checklists, swipe files, mini-courses, free tools) that delivers genuine standalone value while qualifying the lead and warming them for what comes next. Honest about thin-bait (overpromises, underdelivers), kitchen-sink-resource (everything, helps with nothing), and earned-value-magnet (delivers standalone value while qualifying the lead). Triggers on lead magnet, gated content, opt-in offer, ebook, checklist, template, swipe file, mini-course, free tool, content upgrade, freebie, opt-in, list-building offer. Also triggers when an audience is being asked for an email and the offer attached to that ask needs design discipline, when previous lead magnets converted but did not produce qualified leads, or when a lead magnet is being scoped for the first time.
What it loads into context
Frontmatter
254 tokensAlways available to the agent
SKILL.md
5,157 tokensWhen the skill is activated
Reference documents
19,206 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The lead magnet decision: when to build one, when not to
- Thin-bait vs kitchen-sink-resource vs earned-value-magnet
- Format selection
- The "would they pay for this" test
- Audience-fit qualification
- Title and presentation discipline
- Delivery and follow-up sequence design
- Format-specific quality gates
- Common failure modes
- The framework: 12 considerations for lead magnet design
- If required data is unavailable
- Reference files
- Closing: magnets earn the email when they earn the reader's afternoon
Files
SKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesreferences/audience-fit-qualification.mddoc10,332 bytesreferences/common-lead-magnet-failures.mddoc10,585 bytesreferences/delivery-and-follow-up-sequences.mddoc10,478 bytesreferences/format-selection-patterns.mddoc10,248 bytesreferences/format-specific-quality-gates.mddoc11,226 bytesreferences/lead-magnet-anti-patterns.mddoc10,160 bytesreferences/lead-magnet-decision-criteria.mddoc9,683 bytesreferences/title-and-presentation-discipline.mddoc10,262 bytesreferences/would-they-pay-for-this-test.mddoc9,875 bytes
Read SKILL.md
# Lead Magnet Design
A senior growth practitioner's playbook for designing lead magnets that earn the email. Templates, checklists, swipe files, mini-courses, free tools, ebooks. The discipline of building gated content that delivers genuine standalone value while qualifying the lead and warming them for the next conversation.
Most lead magnets are bait. A vague headline, a thin PDF, an email gate, a follow-up sequence the reader resents. Conversion-rate metrics look fine because the form converted; the email list grows; and the unsubscribe rate climbs because the magnet was a transaction the reader regrets the moment they download.
The lead magnets that work as compounding assets do something different. They deliver value the reader would have paid for if they had to. They qualify the lead by audience-fit, so the list that grows is the right list. They set up the next conversation honestly, so the follow-up sequence is a continuation rather than an apology.
This skill is the parent-frame methodology for the growth tooling track. Calculators (`calculator-design`) and quizzes (`quiz-and-assessment-design`) are specific lead-magnet types covered as their own skills. This skill provides the methodology for deciding WHAT to build before deciding WHAT TYPE.
The voice is the senior growth practitioner who has watched lead magnets earn long-term subscribers and watched them burn list trust within a single send. Practical, opinionated about format selection, willing to tell the reader when a lead magnet is the wrong investment for the goal.
When to use this skill: scoping a lead magnet for the first time, auditing a lead magnet that converts but does not qualify, deciding which format fits a specific audience and offer, or designing the post-download sequence that turns the magnet into a relationship.
logo-design
When your agent uses it
Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from `brand-identity`, which produces the complete system (logo plus color, type, voice, applications). Goes deep on the logo specifically: typographic register, symbol approach, application-context discipline (16px favicon, embroidery, signage, motion), and production specs (SVG-ready, single-color, reverse). Triggers on logo design, design a logo, wordmark, monogram, lockup, mark variants, logo iterations, redesign or refine the logo, logo refresh, letterform-as-symbol, and exploring mark variants for an established brand. Does NOT fire for full brand identity (use `brand-identity`), positioning or strategy (use `brand-discovery`), project-wide creative direction (use `creative-direction`), or one-off illustration.
What it loads into context
Frontmatter
244 tokensAlways available to the agent
SKILL.md
4,918 tokensWhen the skill is activated
Reference documents
25,010 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 considerations for logo design
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore23,396 bytesreferences/application-contexts.mddoc17,153 bytesreferences/architectures-explained.mddoc14,068 bytesreferences/category-conventions.mddoc24,902 bytesreferences/client-package.mddoc10,036 bytesreferences/example-variant-spec.mddoc9,457 bytesreferences/symbol-approaches.mddoc20,630 bytesreferences/typographic-registers.mddoc20,910 bytes
Read SKILL.md
# Logo Design
A logo is a system of marks, not a single drawing. This skill produces multiple production-grade variants exploring different architectural approaches, each with rationale, application specs, and a clear position on what it signals and rejects.
The output is decision material, not a finished logo. The brand owner selects from the variants and the skill produces production refinement on the chosen direction.
---
## When to use
- The brand has a name and tonal direction; the deliverable is logo work specifically
- Generating 6 to 12 variants for client review and selection
- Refining a wordmark to production: kerning, optical adjustments, weight selection
- Exploring symbol options to pair with an existing wordmarklong-form-content-frameworks
When your agent uses it
Patterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guides, manifestos, ebooks, long-form tutorials. The structural disciplines that distinguish publication-quality long-form from bloggy-long padding or academic bloat. Different from pillar-content-architecture (which covers hub structure); this skill covers individual deep-dive pieces. Triggers on long-form content, case study writing, whitepaper, research report, definitive guide, ebook, manifesto, long-form tutorial, deep-dive article, anchor piece, foundational article, structural archetypes. Also triggers when a piece is over 3,000 words and the team is unsure how to structure it, when a long-form draft feels padded or saggy, or when a flagship asset needs the depth to actually earn the length.
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
6,281 tokensWhen the skill is activated
Reference documents
19,723 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Bloggy-long vs academic-bloat vs publication-quality
- Long-form formats and when each fits
- Structural archetypes
- Section weight calibration
- Lede patterns for long-form
- Sustaining attention across 5,000+ words
- Citations and source authority
- Visualization and breakouts
- Closing patterns
- Distribution implications for long-form
- Common failure modes
- The framework: 12 considerations for long-form content
- If required data is unavailable
- Reference files
- Closing: long-form earns its length or it does not
Files
SKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesreferences/attention-sustaining-techniques.mddoc9,928 bytesreferences/breakouts-and-visualization.mddoc10,656 bytesreferences/citation-and-source-authority.mddoc10,608 bytesreferences/closing-patterns.mddoc12,274 bytesreferences/common-long-form-failures.mddoc11,920 bytesreferences/format-decision-framework.mddoc10,895 bytesreferences/lede-patterns-for-long-form.mddoc10,091 bytesreferences/section-weight-calibration.mddoc9,590 bytesreferences/structural-archetype-patterns.mddoc10,668 bytes
Read SKILL.md
# Long-Form Content Frameworks
A senior editorial leader's playbook for individual long-form content pieces. The structural disciplines that distinguish publication-quality work from bloggy-long padding or academic bloat.
Long-form is where most content programs lose their nerve or lose their way. Teams either stretch a 1,500-word post to 5,000 with filler (the bloggy-long failure mode), or they over-document the topic with no editorial spine (the academic-bloat failure mode). The pieces that earn their length are the ones where each section justifies its weight, the lede sets a thesis the body actually delivers, and the closing leaves the reader with something specific.
This skill covers the individual long-form piece: the case study, the whitepaper, the research report, the manifesto, the ebook chapter or full ebook, the definitive guide, the long-form tutorial. Different from `pillar-content-architecture` (which covers HUB architecture: how a pillar plus cluster system fits together), this skill covers the long-form PIECE itself, regardless of whether it sits at the center of a hub or stands alone.
The voice is the senior editorial leader who has shipped dozens of flagship long-form assets and watched plenty of others fail. Honest about which formats earn their length, which structural archetypes fit which problems, and where long-form most often goes wrong.
When to use this skill: planning a flagship long-form piece, structuring a draft that feels saggy, reviewing a long-form piece that is technically correct but emotionally flat, or auditing a content library to find the long-form pieces that should have been blog posts.
---
media-asset-management
When your agent uses it
Plan and run a media pipeline for images, video, and downloadable assets. Use this skill when designing image storage and delivery, choosing formats (WebP, AVIF), setting up responsive images, picking a video host, organizing a brand asset library, or auditing a slow image pipeline. Triggers on image pipeline, asset library, DAM, image optimization, WebP, AVIF, responsive images, video hosting, image CDN, asset workflow, media management. Also triggers when images are slow, broken, or scattered across systems.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
2,722 tokensWhen the skill is activated
Reference documents
2,796 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Format reference
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesreferences/responsive-image-patterns.mddoc10,442 bytes
Read SKILL.md
# Media Asset Management
Design how images, video, and downloadable files get stored, processed, organized, and served. Stack-agnostic. The principles apply whether you're running a custom pipeline or using a hosted service.
---
## When to use
- Designing or redesigning the image and media pipeline
- Choosing a media CDN or image service
- Setting up responsive image delivery
- Planning a digital asset management (DAM) system
- Auditing media performance issues
- Picking video hosting and embedding strategymonitoring-and-alerting
When your agent uses it
Design and run a monitoring system for a website or web app. Use this skill when setting up uptime checks, defining SLOs, configuring error tracking, choosing what to alert on, designing on-call rotations, or fixing alert fatigue. Triggers on monitoring, alerts, uptime, SLO, SLA, error rate, on-call, pager, alert fatigue, observability, dashboards, what should we monitor. Also triggers when an incident reveals a gap in monitoring.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,426 tokensWhen the skill is activated
Reference documents
2,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- SLOs and error budgets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,455 bytesSKILL.mdcore10,455 bytesreferences/slo-design-guide.mddoc9,231 bytes
Read SKILL.md
# Monitoring and Alerting
Decide what to watch, what to alert on, and how to make sure the right person finds out when things break.
---
## When to use
- Setting up monitoring on a new site or service
- Defining SLOs (service level objectives) and error budgets
- Choosing which alerts page someone vs which go to a quiet channel
- Designing or fixing on-call rotation
- Diagnosing alert fatigue
- Filling monitoring gaps revealed by an incidentmulti-step-form-design
When your agent uses it
Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent. Honest about kitchen-sink-single-page (overwhelms before the user starts), progress-theater (steps without genuine staging), and genuinely-staged (each step earns its own page) patterns. Triggers on multi-step form, multi-page form, form wizard, signup wizard, lead form, application form, intake form, configurator, onboarding form. Also triggers when a long form is converting poorly, when an audience is dropping off mid-form, or when a multi-step form is being scoped for the first time.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
4,502 tokensWhen the skill is activated
Reference documents
18,460 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The multi-step decision: when to break into steps vs keep single-page
- Kitchen-sink-single-page vs progress-theater vs genuinely-staged
- Step architecture: what belongs on each step
- Progress indicator design
- Conditional logic
- Save-and-resume mechanics
- Validation strategy
- Drop-off measurement and remediation
- Form anti-patterns
- Common failure modes
- The framework: 12 considerations for multi-step form design
- If required data is unavailable
- Reference files
- Closing: multi-step forms earn completion when each step earns its place
Files
SKILL.mdcore21,950 bytesSKILL.mdcore21,950 bytesreferences/common-multi-step-form-failures.mddoc9,115 bytesreferences/conditional-logic-patterns.mddoc9,842 bytesreferences/drop-off-measurement-and-remediation.mddoc10,513 bytesreferences/form-anti-patterns.mddoc9,904 bytesreferences/multi-step-decision-criteria.mddoc9,397 bytesreferences/progress-indicator-patterns.mddoc9,529 bytesreferences/save-and-resume-mechanics.mddoc10,296 bytesreferences/step-architecture-patterns.mddoc10,195 bytesreferences/validation-strategy-patterns.mddoc10,607 bytes
Read SKILL.md
# Multi-Step Form Design
A senior growth practitioner's playbook for designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent.
Most multi-step forms are either kitchen-sink-single-pages dressed up as steps or arbitrary chunking that adds friction without adding clarity. The form looks more sophisticated; the completion rate does not move; the audience is no better served than before.
The multi-step forms that work do something different. Each step represents a coherent unit of cognitive work the user can complete with confidence. Progress indicators reinforce momentum. Conditional logic responds to earlier answers and removes irrelevant fields. The form feels like a guided process, not an obstacle course.
The voice is the senior growth practitioner who has watched multi-step forms convert at twice the single-page rate and watched them collapse to half. Practical, opinionated about when steps add value and when they add friction, willing to call out arbitrary chunking that does not earn its complexity.
When to use this skill: scoping a multi-step form for the first time, auditing a long single-page form that converts poorly, deciding when to break a form into steps and when to keep it on one page, or designing the conditional logic that makes the form feel adaptive.
---
okr-design
When your agent uses it
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition with quarterly accountability). Triggers on OKR design, OKR setting, key result design, OKR scoring, mid-quarter recalibration, OKR cascading, outcomes vs outputs, quarterly planning, goal setting. Also triggers when a team's OKRs are always hit and producing no learning, when OKRs are demoralizing because they were set as fantasy, or when the team uses OKR vocabulary but the practice has decayed.
What it loads into context
Frontmatter
231 tokensAlways available to the agent
SKILL.md
4,861 tokensWhen the skill is activated
Reference documents
18,538 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Sandbagged vs aspirational-fantasy vs stretch
- Objective design
- Key result design
- Cascading OKRs across the org
- Scoring discipline
- Mid-quarter recalibration
- The OKR review cadence
- OKRs vs roadmap items vs metrics
- Common failure modes
- The framework: 12 considerations for OKR design
- If required data is unavailable
- Reference files
- Closing: OKRs are accountability infrastructure
Files
SKILL.mdcore22,458 bytesSKILL.mdcore22,458 bytesreferences/cascading-okrs-decisions.mddoc9,261 bytesreferences/common-okr-failures.mddoc9,801 bytesreferences/key-result-design-patterns.mddoc10,108 bytesreferences/mid-quarter-recalibration.mddoc9,998 bytesreferences/objective-design-patterns.mddoc9,503 bytesreferences/okr-anti-patterns.mddoc10,791 bytesreferences/okrs-vs-roadmap-vs-metrics.mddoc9,051 bytesreferences/review-cadence-templates.mddoc9,910 bytesreferences/scoring-discipline.mddoc9,650 bytes
Read SKILL.md
# OKR Design
A senior product leader's playbook for OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the practical disciplines that distinguish OKRs from quarterly to-do lists or impossible-fantasy goal-setting.
OKRs are accountability infrastructure. When designed well, they produce a quarterly rhythm of ambitious goal-setting, mid-quarter learning, end-of-quarter scoring, and adjustment for the next quarter. When designed badly, they become a tax on the team that produces no signal: sandbagged OKRs that always hit 100% (no ambition, no learning), aspirational fantasy OKRs that nobody can hit (demoralizing, ignored after week 2), or vague OKRs that the team scores generously regardless of outcome.
This skill is OKR design as practical methodology. The teams that benefit from OKRs are the ones that hold the discipline: outcomes over outputs, key results that actually measure the outcome, scoring honestly even when uncomfortable, recalibrating mid-quarter when warranted, and using the OKR review cadence to drive learning rather than performance theater.
The voice is the senior product leader who has run OKRs in healthy organizations and watched the practice decay in others. Concrete, opinionated about what actually works, willing to call out the failure modes that conference talks gloss over.
When to use this skill: designing OKRs for the next quarter, auditing why current OKRs are not driving decisions, recalibrating an OKR practice that has decayed, or onboarding a team to OKRs that has never used them.
---
onboarding-wizard-design
When your agent uses it
Designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. Honest about tutorial-overload (dump everything upfront), skip-friendly-empty (skipped onboarding leads to abandoned product), and earned-progressive-disclosure (right things at the right moments) patterns. Triggers on onboarding wizard, product onboarding, first-run experience, signup flow, activation flow, FRX, time-to-value, ah-ha moment design. Also triggers when activation rates are low, when users skip onboarding and never return, when onboarding flows are being scoped for the first time, or when audience research shows users not finding key features.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
4,250 tokensWhen the skill is activated
Reference documents
13,942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The wizard decision: when wizards earn vs when contextual help suffices
- Tutorial-overload vs skip-friendly-empty vs earned-progressive-disclosure
- Step architecture: what belongs in each step, sequence logic
- The ah-ha moment design
- Progressive disclosure patterns
- Skip and resume mechanics
- Drop-off measurement and remediation
- Wizard variations by user type
- Common failure modes
- The framework: 12 considerations for onboarding wizard design
- Reference files
- Closing: wizards earn the user's first session
Files
SKILL.mdcore20,722 bytesreferences/ah-ha-moment-engineering.mddoc8,665 bytesreferences/common-onboarding-failures.mddoc6,305 bytesreferences/drop-off-measurement-templates.mddoc7,421 bytesreferences/progressive-disclosure-patterns.mddoc7,744 bytesreferences/skip-and-resume-mechanics.mddoc8,137 bytesreferences/step-architecture-patterns.mddoc8,267 bytesreferences/user-type-variation-patterns.mddoc6,413 bytesreferences/wizard-anti-patterns.mddoc7,636 bytesreferences/wizard-decision-criteria.mddoc7,484 bytes
Read SKILL.md
# Onboarding Wizard Design
A senior product marketing director's playbook for designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. The discipline of building an onboarding sequence the user actually completes.
Most product onboarding wizards fail in one of two ways. They cram every feature into a 12-step intro the user has not earned the patience for. Or they offer a "skip onboarding" button so prominent that users skip into an empty product with no context, and then churn the next day because they never found the value. The activation rate is the metric that matters, and most wizards are optimizing for the wrong thing.
The wizards that work do something different. Each step earns the user one step closer to value. The wizard surfaces the right thing at the right moment, not everything upfront. Skip exists but is balanced against staying engaged. The user reaches the ah-ha moment with a sense that the product respected their time.
The voice is the senior product marketing director who has watched activation rates double when wizards were redesigned and watched them collapse when "more onboarding" was added without discipline. Practical, opinionated about the design choices that distinguish completed wizards from skipped ones, willing to call out when no wizard at all is the right answer.
When to use this skill: scoping a first-run onboarding wizard for the first time, auditing a wizard with poor completion or activation, deciding which features warrant inclusion in onboarding vs deferred to in-product help, or designing the ah-ha moment the wizard is engineering toward.
---
oss-contribution-research
When your agent uses it
Research and prepare an outside contribution to an open-source repo, then stop at a queue item for a human to approve: policy check, intake, duplicate check, reproduction, patch, the repo's own checks, an independent critic rerun, and a disclosed, hashed draft of the exact text to post. Use this skill whenever the user wants to contribute to someone else's repo, fix an upstream bug, pick up a good-first-issue, draft an AI-assisted pull request for an outside project, follow up on their own outside PR, or run a gated contribution pipeline. Triggers on open source contribution, contribute to this repo, upstream fix, outside PR, external PR, good first issue, fix this issue in their repo, contribution research, AI-assisted PR, disclose AI in PR, reply to review on my PR. Also triggers when the user names an issue in a repo they do not maintain and asks for a fix, even if they do not say contribute.
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
4,438 tokensWhen the skill is activated
Reference documents
6,201 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: gates in order, stop at the first fail
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesreferences/example-intake-item.mddoc3,366 bytesreferences/policy-classification.mddoc5,088 bytesreferences/pr-description-template.mddoc5,476 bytesreferences/queue-item-template.mddoc6,802 bytesreferences/repro-record-template.mddoc4,985 bytes
Read SKILL.md
# OSS Contribution Research
Prepare one outside contribution to an open-source repo, gate by gate, and stop at a queue item a human approves. The agent running this skill never posts.
---
## When to use
- Picking up an existing issue or confirmed bug in a repo the user does not maintain
- Checking whether a repo accepts AI-assisted pull requests before any work starts
- Asking a maintainer for a go-ahead before writing a patch (an intake comment)
- Turning a fix into a small, disclosed pull request draft that a human approves
- Following up on the user's own outside pull request: a review reply, the 14-day ping, or the 28-day close
- Running a contribution pipeline with an approval queue and a per-repo registrypaid-media-strategy
When your agent uses it
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media strategy, ad budget allocation, channel selection, paid media plan, audit my Google Ads, audit my Meta Ads, scale paid media, kill underperforming campaign, paid media hypothesis, ad spend strategy, attribution reality, performance marketing strategy. Also triggers when a team is asking how to scale paid media, or whether to add a new channel, or how to reallocate spend across channels.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
4,664 tokensWhen the skill is activated
Reference documents
10,603 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hypothesis discipline for paid spend
- Channel selection: when to use which platform
- Budget allocation: brand vs performance, baseline vs test
- Audience targeting: prospecting vs retargeting vs exclusion
- Bid strategy: when each fits
- Campaign types
- What NOT to spend on
- Creative testing: within campaign vs across campaign
- Frequency capping
- Attribution mismatch: platform-reported vs actual
- Common failures
- The framework: 11 considerations for sustainable paid media
- If required data is unavailable
- Reference files
- Closing: when in doubt, kill the campaign
Files
SKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesreferences/ads-platform-comparison.mddoc7,238 bytesreferences/audience-segmentation-patterns.mddoc6,779 bytesreferences/bid-strategy-reference.mddoc6,441 bytesreferences/budget-allocation-templates.mddoc5,725 bytesreferences/campaign-type-reference.mddoc8,243 bytesreferences/channel-decision-matrix.mddoc5,956 bytesreferences/common-failures.mddoc8,642 bytes
Read SKILL.md
# Paid Media Strategy
A senior performance marketer's playbook for running paid media that produces real outcomes.
The default state of paid media is wasted spend. Most accounts have campaigns running because they always have, audiences targeting because the rep suggested it, bid strategies on auto because manual is hard, creative not refreshed because there is no system. The cost compounds. A 20% efficiency gain on a $500K-per-year account is $100K back to the business. A 50% gain on a $5M-per-year account is $2.5M.
This skill is the discipline that produces those gains. It assumes you have a paid media platform (Google Ads, Meta, LinkedIn, TikTok, or aggregators like Synter) connected. It assumes you have working analytics and conversion tracking. The hard part is the strategic discipline behind the spend, and that is what is here.
When to use this skill: any time you are designing a paid media plan, evaluating whether to scale or kill a campaign, allocating budget across channels, or auditing an existing account.
---
## What this skill is for
performance-optimization
When your agent uses it
Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
2,449 tokensWhen the skill is activated
Reference documents
5,168 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: Core Web Vitals
- Beyond Core Web Vitals
- Workflow
- Tools
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,763 bytesSKILL.mdcore10,763 bytesSKILL.mdcore10,763 bytesreferences/audit-template.mddoc5,602 bytesreferences/optimization-checklist.mddoc5,634 bytesreferences/optimization-playbook.mddoc9,303 bytes
Read SKILL.md
# Performance Optimization
Diagnose web performance issues and produce a remediation plan. Stack-agnostic. Anchored to Core Web Vitals and standard browser performance patterns.
This skill goes deeper than the performance checks in `qa-testing` and `seo-technical`. Use this when performance itself is the goal.
---
## When to use
- Fixing Core Web Vitals (LCP, INP, CLS)
- Diagnosing slow page loads
- Reducing JavaScript bundle size
- Optimizing images, fonts, and other assetspillar-content-architecture
When your agent uses it
How to design a content hub that earns topical authority. Pillar topic selection, cluster planning, internal linking architecture, URL structure, pillar and cluster page anatomy, topical authority signals for SEO and AEO/GEO, and the maintenance discipline that distinguishes intentional hubs from accidental orphans. Triggers on pillar content, content hub, topic cluster, topical authority, content architecture, hub and spoke, pillar page, cluster page, content silo, internal linking strategy. Also triggers when a content set is not ranking despite individual piece quality, when a pillar was launched without a cluster, or when content has accumulated without an architecture.
What it loads into context
Frontmatter
177 tokensAlways available to the agent
SKILL.md
4,719 tokensWhen the skill is activated
Reference documents
15,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Pillar vs cluster vs orphan content
- Topic selection for pillar pages
- Cluster planning
- Internal linking architecture
- URL structure and information architecture
- Pillar page anatomy
- Cluster piece anatomy
- Topical authority signals
- Maintenance and refresh patterns
- Common failure modes
- The framework: 12 considerations for hub architecture
- If required data is unavailable
- Reference files
- Closing: architecture is the moat
Files
SKILL.mdcore22,093 bytesSKILL.mdcore22,093 bytesreferences/cluster-piece-anatomy.mddoc6,439 bytesreferences/cluster-planning-patterns.mddoc6,294 bytesreferences/common-pillar-failures.mddoc9,390 bytesreferences/content-refresh-patterns.mddoc7,972 bytesreferences/internal-linking-architecture.mddoc7,222 bytesreferences/pillar-cluster-decision.mddoc5,860 bytesreferences/pillar-page-anatomy.mddoc7,443 bytesreferences/topic-selection-criteria.mddoc6,377 bytesreferences/topical-authority-signals.mddoc7,006 bytesreferences/url-structure-patterns.mddoc6,327 bytes
Read SKILL.md
# Pillar Content Architecture
A senior content architect's playbook for designing content hubs that earn topical authority.
Most content programs accumulate accidentally. Pieces ship one at a time, internal linking happens (or does not) in editing, similar topics get covered by multiple pieces with no coordination, and six months later the team has a content set that looks like a sitemap but feels like a yard sale. Search engines see disconnected pages; AI engines see scattered citations; readers cannot tell which piece is the entry point and which is the reference.
This skill is the discipline of intentional hub architecture. It assumes you have decided which topic areas to invest in (see `content-strategy`) and have keyword data (see `seo-keyword`). It does not write any individual piece (see `content-brief-authoring` for per-piece work and `content-and-copy` for execution). What it does is design the structure: which topic gets a pillar, which subtopics get cluster pieces, how the pieces link to each other, where they live in the URL hierarchy, and what topical authority signals the architecture is engineered to produce.
When to use this skill: launching a new content hub, restructuring an existing content set into a hub, deciding whether a piece should be a pillar or a cluster, or auditing why a content area is not ranking despite individual piece quality.
---
## What this skill is for
pm-spec-writing
When your agent uses it
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
2,068 tokensWhen the skill is activated
Reference documents
4,248 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,907 bytesSKILL.mdcore8,907 bytesreferences/dev-brief-template.mddoc6,155 bytesreferences/feature-spec-template.mddoc4,691 bytesreferences/prioritization-frameworks.mddoc6,889 bytes
Read SKILL.md
# PM Spec Writing
Take an idea (often vague) and turn it into a specification a developer or AI agent can actually build from. Stack-agnostic. Works for new features, bug fixes, content changes, or infrastructure work.
---
## When to use
- Translating an idea into a buildable feature spec
- Writing a PRD or product requirement document
- Filing a bug report that someone else can act on
- Scoping a project before kickoff
- Prioritizing a backlog of feature requests
- Writing acceptance criteria for an existing featureproduct-analytics-setup
When your agent uses it
How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
4,983 tokensWhen the skill is activated
Reference documents
15,527 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The instrumentation hierarchy
- Event taxonomy design
- Property design: event-level vs user-level
- Naming conventions
- Schema versioning
- Funnel design
- Cohort definitions
- Retention measurement
- North Star and supporting metrics
- The trustable dashboard principle
- Instrumentation debt
- Common failure modes
- The framework: 12 considerations for trustable product analytics
- If required data is unavailable
- Reference files
- Closing: when in doubt, instrument less
Files
SKILL.mdcore23,754 bytesSKILL.mdcore23,754 bytesSKILL.mdcore23,754 bytesreferences/cohort-definition-patterns.mddoc7,519 bytesreferences/common-failures.mddoc9,554 bytesreferences/event-taxonomy-template.mddoc7,741 bytesreferences/funnel-design-templates.mddoc7,741 bytesreferences/instrumentation-audit-checklist.mddoc7,398 bytesreferences/naming-convention-reference.mddoc5,956 bytesreferences/north-star-metric-selection.mddoc8,027 bytesreferences/property-design-patterns.mddoc6,781 bytesreferences/schema-versioning-patterns.mddoc7,061 bytes
Read SKILL.md
# Product Analytics Setup
A senior PM and analyst's playbook for instrumenting product analytics correctly the first time.
Most product analytics setups are some combination of inherited mistakes, dashboard sprawl, and events nobody trusts. The team launches a new feature; instrumentation gets bolted on under deadline pressure; naming drifts; properties are inconsistent; six months later nobody can answer simple questions because the answer depends on which event you trust.
This skill is the discipline that prevents that. It assumes you have answered the strategic questions about what to measure (see `analytics-strategy`). It assumes you have a tool connected (Mixpanel, Heap, PostHog, Amplitude, or warehouse-native via BigQuery, Snowflake, or dbt). The hard part is the systematic execution: naming conventions, property design, schema versioning, funnel construction, cohort definitions, retention measurement.
When to use this skill: setting up product analytics from scratch, auditing an existing instrumentation, fixing a "we have data but cannot trust it" problem, or designing instrumentation for a new feature.
---
## What this skill is for
product-configurator-design
When your agent uses it
Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus meaningful constraints plus escape hatches) patterns. Triggers on configurator design, build-your-own, custom configuration, plan builder, product customizer, configuration tool. Also triggers when users abandon mid-configuration, when configurator conversion is poor, or when a configurator is being scoped for the first time.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
3,262 tokensWhen the skill is activated
Reference documents
8,103 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The configurator decision: when configurators earn investment vs when bundles suffice
- Infinite-options vs canned-bundles-only vs guided-configuration
- Default-configuration design
- Constraint logic
- Real-time pricing and impact display
- Validation and error patterns
- Save-and-share mechanics
- Configurator-to-cart handoff
- Common failure modes
- The framework: 12 considerations for configurator design
- Reference files
- Closing: configurators earn investment when they earn the configuration that ships
Files
SKILL.mdcore16,741 bytesreferences/common-configurator-failures.mddoc5,145 bytesreferences/configurator-anti-patterns.mddoc5,057 bytesreferences/configurator-decision-criteria.mddoc4,204 bytesreferences/configurator-to-cart-handoff.mddoc4,526 bytesreferences/constraint-logic-patterns.mddoc4,485 bytesreferences/default-configuration-design.mddoc2,978 bytesreferences/real-time-pricing-patterns.mddoc4,007 bytesreferences/save-and-share-mechanics.mddoc5,134 bytesreferences/validation-and-error-patterns.mddoc4,810 bytes
Read SKILL.md
# Product Configurator Design
A senior product marketing director's playbook for designing build-your-own product configurators. Tesla-style vehicle configurators, custom-pricing builders, plan-builders, product customizers. Constraint logic, real-time pricing, validation, save-and-share mechanics. The discipline of building a configurator that produces configurations users actually commit to.
Most configurators fail in one of two ways. They expose every parameter at full granularity (47 toggles, 12 sliders) and produce decision paralysis; users abandon halfway through. Or they pretend to be configurators but are actually three pre-built bundles labeled "Custom"; the configurator framing was marketing while the product is bundles.
The configurators that work do something different. Smart defaults that produce a sensible starting configuration; meaningful constraints that prevent invalid combinations and surface why; escape hatches into deeper customization for users who want it; real-time pricing that responds to choices. Users feel guided rather than overwhelmed.
The voice is the senior product marketing director who has watched configurators double conversion when redesigned with smart defaults and watched them collapse when "more options" were added without constraint logic. Practical, opinionated about the constraints that protect users from themselves, willing to call out when canned bundles are the right answer.
When to use this skill: scoping a build-your-own configurator for the first time, auditing a configurator with high abandonment, designing the constraint logic that prevents invalid combinations, or deciding which parameters earn exposure vs which should default.
---
programmatic-seo
When your agent uses it
How to design and run a programmatic SEO program that produces durable traffic instead of penalty-bait. Data source identification, template design, schema patterns, quality control at scale, internal linking architecture, crawl budget management, AEO/GEO for programmatic pages, refresh discipline, and the make-or-break question of whether pSEO is the right answer for your program at all. Triggers on programmatic SEO, pSEO, scaled content, page generation, template SEO, location pages, comparison pages, directory site, listing site, scaled landing pages, programmatic content. Also triggers when a content set is not ranking, has been hit by an algorithm update, or when a team is considering pSEO as a growth lever.
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
5,170 tokensWhen the skill is activated
Reference documents
15,715 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When pSEO is the right answer
- Data source identification
- Template design
- Schema design
- Quality control at scale
- Internal linking across the set
- Crawl budget management
- AEO and GEO for programmatic pages
- Refresh and maintenance at scale
- Common failure modes
- The framework: 12 considerations for programmatic SEO
- If required data is unavailable
- Reference files
- Closing: quality at scale or not at all
Files
SKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesreferences/aeo-geo-for-programmatic-pages.mddoc7,984 bytesreferences/common-pseo-failures.mddoc10,408 bytesreferences/crawl-budget-management.mddoc7,087 bytesreferences/data-source-identification-patterns.mddoc6,693 bytesreferences/internal-linking-at-scale.mddoc7,396 bytesreferences/quality-control-at-scale.mddoc7,880 bytesreferences/refresh-at-scale.mddoc7,454 bytesreferences/schema-design-patterns.mddoc7,817 bytesreferences/template-design-patterns.mddoc6,634 bytesreferences/when-pseo-works-decision.mddoc6,952 bytes
Read SKILL.md
# Programmatic SEO
A senior SEO strategist's playbook for designing and running programmatic SEO programs that produce durable traffic instead of penalty-bait.
Programmatic SEO has a complicated reputation. Sites like Zillow, Airbnb, TripAdvisor, Indeed, and Yelp have built billion-dollar traffic engines on pSEO. Other sites have built pSEO programs that got hit by Google's helpful-content updates and lost 80% of their traffic in a week. The difference is rarely the technique; it is the underlying data quality and the quality control discipline at scale.
This skill is the playbook for getting that distinction right. It assumes you have decided what keyword space to target (see `seo-keyword`) and how the broader content program is shaped (see `content-strategy`). It does not write individual editorial pieces (see `content-and-copy` for that) and does not architect editorial topic hubs (see `pillar-content-architecture` for that). What it does is teach the discipline of generating high-volume pages programmatically from structured data sources without producing thin content, duplicate content, or scale-without-substance pages that get penalized.
When to use this skill: deciding whether pSEO is a fit for the program at all (the most important question), designing a new pSEO system, auditing an existing pSEO set that is not ranking or has been hit by an algorithm update, or building quality-control discipline for a pSEO program that grew faster than its quality processes.
---
## What this skill is for
qa-testing
When your agent uses it
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
3,248 tokensWhen the skill is activated
Reference documents
1,174 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 tiers
- Specific QA snippets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,894 bytesSKILL.mdcore12,894 bytesreferences/qa-report-template.mddoc4,363 bytes
Read SKILL.md
# QA Testing
Verify that a page, feature, or site is working before declaring it shipped. Stack-agnostic. Console-snippet driven for speed.
This skill is faster than `accessibility-audit` (which goes deeper on WCAG) and `performance-optimization` (which goes deeper on Core Web Vitals). Use this skill for general QA. Use the specialists for deep audits.
---
## When to use
- After every deploy (smoke test)
- After launching a new page or feature (standard audit)
- Before a major release (full release matrix)
- Investigating a "something looks off" reportquiz-and-assessment-design
When your agent uses it
Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
4,340 tokensWhen the skill is activated
Reference documents
18,897 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The quiz/assessment decision: when this format earns investment
- Clickbait-quiz vs vanity-result vs actionable-segmentation
- Question architecture
- Scoring algorithms
- Result categorization
- Result-to-recommendation mapping
- Lead capture integration
- Quiz anti-patterns
- Common failure modes
- The framework: 12 considerations for quiz and assessment design
- Reference files
- Closing: quizzes earn engagement when they earn the next step
Files
SKILL.mdcore21,637 bytesSKILL.mdcore21,637 bytesreferences/clickbait-vs-actionable-distinctions.mddoc10,891 bytesreferences/common-quiz-failures.mddoc9,721 bytesreferences/lead-capture-integration-patterns.mddoc10,098 bytesreferences/question-architecture-patterns.mddoc10,502 bytesreferences/quiz-anti-patterns.mddoc10,555 bytesreferences/quiz-investment-criteria.mddoc9,217 bytesreferences/result-categorization-patterns.mddoc10,462 bytesreferences/result-to-recommendation-mapping.mddoc11,699 bytesreferences/scoring-algorithm-patterns.mddoc11,391 bytes
Read SKILL.md
# Quiz and Assessment Design
A senior growth practitioner's playbook for designing quizzes and assessments that produce actionable segmentation rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping. The discipline of building a quiz the audience actually uses to make a decision.
Most quizzes on the web are clickbait. "What kind of pizza are you?" energy applied to brand-building, with results that flatter the taker but drive no specific next step. The quiz captures emails because the format implies fun; the leads are unqualified because the result told them nothing they could act on.
The quizzes that work as compounding assets do something different. They categorize the taker into a defined segment with a specific recommendation matched to that segment. The taker comes away knowing what to do next, not just what they are. The brand becomes the source of the recommendation the audience acted on.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the quiz-specific methodology (scoring algorithms, result categorization, recommendation matching) lives here.
The voice is the senior growth practitioner who has watched quizzes earn long-term subscribers and watched them produce engagement metrics with no downstream impact. Practical, opinionated about the difference between fun-quiz and decision-quiz, willing to call out when a quiz is the wrong format for the goal.
When to use this skill: scoping a quiz or assessment for the first time, auditing a quiz that produces engagement but no qualified leads, designing the result categories that drive specific recommendations, or deciding which inputs warrant the lead-capture step.
roadmap-planning
When your agent uses it
Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next, sequencing, prioritization, OKR planning, capacity planning, what's on the roadmap, plan the year, what to ship next quarter. Also triggers when stakeholders are pulling in different directions and the team needs a defensible plan.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
2,462 tokensWhen the skill is activated
Reference documents
1,766 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,981 bytesreferences/prioritization-frameworks.mddoc8,044 bytes
Read SKILL.md
# Roadmap Planning
Take a pile of ideas, requests, and ongoing work. Produce a defensible plan for what to ship, when, and why. The output is a roadmap document plus the prioritization work that made it credible.
---
## When to use
- Planning the next quarter or the next year
- Sequencing work where some items depend on others
- Balancing new builds, improvements, and maintenance
- Saying no (or "not yet") to specific requests with a defensible reason
- Aligning a team around a single shared plan
- Communicating the plan to stakeholders outside the teamscheduler-and-booking-design
When your agent uses it
Designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic Calendly link. Availability logic, qualification gating, prep automation, follow-up sequencing. Honest about any-time-friction (no qualification, just a booking link), interrogation-gate (so much qualification it scares users off), and qualified-fast-path (just enough qualification to set up the call well) patterns. Triggers on scheduler design, meeting booking, demo scheduling, sales call scheduling, calendar tool, booking page, qualification flow. Also triggers when sales team complains about cold demos, when booking conversion is poor, or when scheduler is being scoped for the first time.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
3,637 tokensWhen the skill is activated
Reference documents
12,565 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The booking-flow decision: scheduler vs forms vs sales-pipeline tools
- Any-time-friction vs interrogation-gate vs qualified-fast-path
- Qualification field design
- Availability logic
- Routing patterns
- Prep automation
- Confirmation and reminder sequences
- Reschedule and no-show handling
- Common failure modes
- The framework: 12 considerations for scheduler and booking design
- Reference files
- Closing: schedulers earn the booking when they earn the better call
Files
SKILL.mdcore17,744 bytesSKILL.mdcore17,744 bytesreferences/availability-logic-patterns.mddoc7,422 bytesreferences/common-scheduler-failures.mddoc5,777 bytesreferences/prep-automation-patterns.mddoc7,162 bytesreferences/qualification-field-design.mddoc7,144 bytesreferences/reminder-sequence-patterns.mddoc6,530 bytesreferences/reschedule-and-no-show-handling.mddoc6,899 bytesreferences/routing-patterns.mddoc6,007 bytesreferences/scheduler-anti-patterns.mddoc5,811 bytesreferences/scheduler-decision-criteria.mddoc7,105 bytes
Read SKILL.md
# Scheduler and Booking Design
A senior growth practitioner's playbook for designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic booking link. Availability logic, qualification gating, prep automation, follow-up sequencing. The discipline of building a scheduler that earns the booking by earning a better call.
Most schedulers fail in one of two ways. Generic booking links produce cold demos where reps know nothing about the person they are about to talk to. Conversion stays at the rate of unqualified raw demos. Or qualification forms with 12 fields scare users off before they can book; drop-off at the form approaches 90 percent; only the leads who happen to survive the form actually convert.
The schedulers that work do something different. Just enough qualification to set up the call well (3-5 strategic fields), context-aware availability (high-fit leads see senior reps; low-fit leads route differently), prep automation that briefs the rep before the call. The booking is honest about who the audience is; the call is set up to succeed.
The voice is the senior growth practitioner who has watched schedulers double demo conversion when redesigned and watched them collapse when more qualification was added. Practical, opinionated about which fields earn their place, willing to call out when the booking flow is the wrong tool.
When to use this skill: scoping a scheduler for the first time, auditing a booking flow with poor conversion or poor downstream call quality, designing the qualification gate that produces context without producing friction, or deciding routing logic that matches leads to the right reps.
---
security-baseline
When your agent uses it
Establish a security baseline for a website or web app. Use this skill when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, doing a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scan, security audit, harden, OWASP, security baseline. Also triggers when a security review is required for compliance or before going live.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,645 tokensWhen the skill is activated
Reference documents
1,999 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Content Security Policy
- Workflow
- Common compliance touchpoints
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,973 bytesSKILL.mdcore11,973 bytesSKILL.mdcore11,973 bytesreferences/headers-checklist.mddoc8,049 bytes
Read SKILL.md
# Security Baseline
Establish the security floor for any production website or web app. Stack-agnostic. Covers the things that should be in place before public launch and verified periodically after.
---
## When to use
- Pre-launch security review
- Setting up a new site or environment
- Periodic security audit (quarterly recommended)
- Onboarding a new vendor or third-party integration
- Responding to a security finding or report
- Hardening after an incidentseo-aeo-geo
When your agent uses it
Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI assistants. Use this skill whenever the user wants to optimize for AI search, get cited by language models, appear in AI overviews, build llms.txt, structure content for AI extraction, or future-proof their SEO for the shift from blue links to AI answers. Triggers on AEO, GEO, AI search, AI SEO, AI overview, generative search, LLM optimization, llms.txt, AI citation, ChatGPT search, Perplexity, Gemini, Claude search, AI assistant optimization, answer engine. Also triggers when the user expresses concern about AI eating their organic traffic or wants to understand how to remain visible as search shifts.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
1,991 tokensWhen the skill is activated
Reference documents
4,184 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,146 bytesSKILL.mdcore9,146 bytesSKILL.mdcore9,146 bytesreferences/extraction-friendly-patterns.mddoc10,550 bytesreferences/llms-txt-guide.mddoc7,985 bytes
Read SKILL.md
# AEO and GEO
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO). Make content discoverable, extractable, and citable by AI search experiences.
This skill encodes principles. AI search products evolve fast. The principles age slower than the products.
---
## When to use
- Optimizing content for AI overviews and generative answer engines
- Building or updating llms.txt
- Structuring content so AI assistants can extract and cite it correctly
- Future-proofing a site as search shifts from blue links to AI answersseo-audit-orchestration
When your agent uses it
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
1,919 tokensWhen the skill is activated
Reference documents
1,517 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases of an end-to-end audit
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesreferences/audit-rollup-template.mddoc5,704 bytes
Read SKILL.md
# SEO Audit Orchestration
Run a complete SEO audit by sequencing the sibling audit skills in a defined order. Stack-agnostic. Assumes the Ahrefs MCP is connected. Produces a single rollup report that synthesizes findings across backlinks, keywords, content, traffic, technical health, and rankings.
---
## When to use
- Running a full SEO audit (quarterly, biannual, annual)
- Pre-acquisition SEO due diligence
- Post-migration verification (after content move, replatform, or domain change)
- Onboarding a new client or new property
- Building a baseline before a major SEO investment
- Diagnosing chronic underperformanceseo-backlink-audit
When your agent uses it
Audit a backlink profile using Ahrefs MCP data: profile health, anchor text distribution, toxic link identification, lost link reclamation, and gap analysis against competitors. Use this skill when reviewing backlink health, scoping a disavow project, recovering from a manual action, planning link building, or doing M&A due diligence on a property's link equity. Triggers on backlink audit, link profile, toxic links, disavow, anchor text analysis, lost links, link reclamation, referring domains, link gap. Also triggers when traffic decline correlates with link loss or when an unnatural link warning appears in Search Console.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,718 tokensWhen the skill is activated
Reference documents
1,339 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions of a backlink profile
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,804 bytesSKILL.mdcore7,804 bytesSKILL.mdcore7,804 bytesreferences/toxic-link-criteria.mddoc5,888 bytes
Read SKILL.md
# SEO Backlink Audit
Audit a backlink profile using data pulled from the Ahrefs MCP. Stack-agnostic. Produces a profile health assessment, a toxic link list (if needed), a reclamation list, and a gap analysis against competitors.
---
## When to use
- Periodic backlink health check (quarterly or biannual)
- Recovering from a Google manual action or unnatural link warning
- Scoping a disavow file
- Pre-acquisition due diligence on link equity
- Planning a link building campaign (need a baseline)
- Investigating ranking drops correlated with link lossseo-competitor
When your agent uses it
Run a competitive SEO analysis comparing the user's site to chosen competitors across SERP overlap, content depth, backlink profiles, technical posture, and brand presence. Use this skill whenever the user wants to analyze competitors, find content gaps, identify backlink opportunities, understand why competitors outrank them, or benchmark against the rest of their category. Triggers on competitor analysis, competitive analysis, SERP analysis, content gap, backlink gap, why is X ranking, who is winning the SERP, beat my competitor, benchmark, market positioning. Also triggers when planning a content strategy and the question 'what are competitors doing' is implicit.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
1,527 tokensWhen the skill is activated
Reference documents
3,031 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 angles
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,164 bytesSKILL.mdcore7,164 bytesreferences/competitive-audit-template.mddoc3,764 bytesreferences/content-gap-method.mddoc8,556 bytes
Read SKILL.md
# SEO Competitor Analysis
Compare a site to its competitors and find the gaps worth closing. Stack-agnostic. Tool-friendly but tool-optional.
---
## When to use
- Identifying which competitors to study
- Finding content gaps (topics they cover, you do not)
- Finding backlink gaps (sites linking to them, not you)
- Understanding why a specific competitor outranks the user
- Benchmarking authority, technical posture, and content depth
seo-content-audit
When your agent uses it
Audit existing content across a site to decide what to keep, update, merge, redirect, or delete. Use this skill whenever the user wants to audit existing content, fix content decay, resolve keyword cannibalization, prune underperforming pages, prioritize content updates, or apply a keep/update/merge/redirect/delete framework to a content library. Triggers on content audit, content decay, content refresh, cannibalization, keyword cannibalization, prune content, delete pages, redirect old pages, content inventory, what to keep, what to update, content scorecard, evergreen refresh. Also triggers when traffic is dropping site-wide and the cause might be content quality, even if 'audit' is not said explicitly.
What it loads into context
Frontmatter
181 tokensAlways available to the agent
SKILL.md
1,894 tokensWhen the skill is activated
Reference documents
3,415 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 actions
- Scoring inputs
- Decision matrix
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,585 bytesSKILL.mdcore8,585 bytesreferences/audit-template.mddoc8,633 bytesreferences/cannibalization-resolution.mddoc6,603 bytes
Read SKILL.md
# Content Audit
Inventory existing content, score it, and decide for each piece: keep, update, merge, redirect, or delete. Stack-agnostic. Works on blogs, marketing sites, knowledge bases, and product content.
---
## When to use
- Inheriting a content library you did not create
- Diagnosing site-wide traffic decline
- Resolving cannibalization (two pages competing for the same query)
- Pre-migration cleanup
- Annual or semi-annual content health check
- Pruning before a redesign or replatformseo-content-gap-audit
When your agent uses it
Audit content gaps and decay using Ahrefs MCP data: missing topics, thin coverage, outdated content, and decaying pages. Use this skill when planning a content roadmap, refreshing a stale catalog, building topical authority, or identifying which existing pages need update versus replacement. Triggers on content gap, content audit, content refresh, content roadmap, decaying content, content decay, topical authority, what topics should we cover, where is competitor content stronger. Also triggers when organic traffic is flat despite consistent publishing.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
1,923 tokensWhen the skill is activated
Reference documents
1,750 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of content opportunity
- Workflow
- The action decision matrix
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,117 bytesSKILL.mdcore9,117 bytesreferences/content-decision-matrix.mddoc7,756 bytes
Read SKILL.md
# SEO Content Gap Audit
Find content gaps and decay using Ahrefs MCP data. Stack-agnostic. Produces a roadmap of create, update, merge, and prune actions across the existing content catalog and identified topic gaps.
---
## When to use
- Planning the next quarter or half of content investment
- Refreshing a stale or underperforming content catalog
- Building topical authority in a target space
- Identifying decaying pages before they tank traffic
- Audit prep before a major site redesign or migration
- Diagnosing why content investment is not driving organic growthseo-keyword
When your agent uses it
Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production. Use this skill whenever the user asks to do keyword research, find target keywords, identify ranking opportunities, classify search intent, build a topical map, or plan a content strategy around what people search for. Triggers on keyword research, keyword strategy, search intent, keyword clustering, topic clusters, keyword difficulty, search volume, ranking opportunity, content gap, what should I write about, target keyword, primary keyword, secondary keyword, long-tail. Also triggers when planning a content calendar or new site without keywords yet defined.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
1,783 tokensWhen the skill is activated
Reference documents
3,183 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,013 bytesSKILL.mdcore8,013 bytesreferences/intent-classification-guide.mddoc10,815 bytesreferences/keyword-research-template.mddoc3,039 bytes
Read SKILL.md
# Keyword Research
Find the queries worth ranking for, classify them by intent, cluster them into topics, and prioritize what to produce. Stack-agnostic. Tool-agnostic (works with any keyword tool).
---
## When to use
- Starting a new site or content section
- Planning a content calendar
- Looking for ranking opportunities on an existing site
- Understanding search intent before writing
- Building topic clusters for internal linking
- Identifying content gaps vs competitorsseo-keyword-gap-audit
When your agent uses it
Find keywords competitors rank for that the target property does not, and prioritize them by opportunity. Uses Ahrefs MCP for keyword and competitor data. Use this skill when planning content investment, identifying quick wins, building a content calendar against a competitor set, or scoping a market entry. Triggers on keyword gap, content gap, competitor keywords, opportunity keywords, what should we target, where are competitors winning, keyword opportunity. Also triggers when planning content for a new market or after losing organic share to a specific competitor.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
1,741 tokensWhen the skill is activated
Reference documents
1,983 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: the gap matrix
- Opportunity scoring
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,882 bytesSKILL.mdcore7,882 bytesreferences/opportunity-scoring-rubric.mddoc7,013 bytes
Read SKILL.md
# SEO Keyword Gap Audit
Find keyword opportunities by comparing the target property's organic footprint against a competitor set, using Ahrefs MCP data. Stack-agnostic. Produces a prioritized list of keywords to target with new or improved content.
---
## When to use
- Planning content investment for the next quarter
- Identifying quick-win keywords for fast organic gains
- Scoping market entry into a new vertical
- Refreshing a stale content strategy
- Diagnosing why a competitor is gaining organic share
- Pre-acquisition due diligence on growth ceilingseo-offpage
When your agent uses it
Plan and execute off-page SEO including link building, digital PR, brand mentions, citation building, and external authority signals. Use this skill whenever the user wants to build backlinks, plan a digital PR campaign, list local citations, run guest post outreach, develop linkable assets, recover lost links, or audit a backlink profile for risk. Triggers on link building, backlinks, digital PR, brand mentions, citation building, guest post, outreach, linkable asset, broken link building, HARO, podcast outreach, off-page SEO, anchor text, link velocity, toxic backlinks, disavow. Also triggers when the user is trying to grow domain authority or earn coverage.
What it loads into context
Frontmatter
171 tokensAlways available to the agent
SKILL.md
1,731 tokensWhen the skill is activated
Reference documents
4,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 strategies
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,116 bytesSKILL.mdcore8,116 bytesreferences/linkable-assets-guide.mddoc11,668 bytesreferences/outreach-templates.mddoc6,138 bytes
Read SKILL.md
# Off-Page SEO
Build the external signals that earn rankings: backlinks, brand mentions, citations, and trusted sources pointing back to the site. Stack-agnostic.
---
## When to use
- Planning a link-building strategy
- Running digital PR or earned-media campaigns
- Building citations for a local business
- Developing linkable assets (research, tools, calculators)
- Recovering lost backlinks after a migration or audit
- Auditing a backlink profile for spam or toxicityseo-onpage
When your agent uses it
Run a comprehensive on-page SEO audit or optimization pass covering title tags, meta descriptions, header structure, content quality, internal links, image optimization, URL hygiene, and on-page schema. Use this skill whenever the user asks to optimize a page, audit on-page SEO, fix titles or meta tags, review header structure, check internal linking, improve a single URL's search performance, or write SEO-friendly copy. Triggers on on-page SEO, page audit, title tag, meta description, H1, header structure, internal links, image alt, URL slug, page optimization, optimize this page, SEO this page. Also triggers for any single-page review where ranking, click-through, or relevance signal quality is the goal, even if the user does not say 'SEO' explicitly.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
1,601 tokensWhen the skill is activated
Reference documents
3,582 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 8 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore6,885 bytesreferences/audit-template.mddoc2,216 bytesreferences/onpage-checklist.mddoc2,663 bytesreferences/title-and-meta-patterns.mddoc9,878 bytes
Read SKILL.md
# On-Page SEO
Optimize a single page for search relevance, click-through, and crawler comprehension. Stack-agnostic. Works on any CMS, framework, or static site.
---
## When to use
- Auditing or optimizing a single page (homepage, product page, article, landing page)
- Writing or reviewing title tags and meta descriptions
- Fixing header structure or content hierarchy
- Reviewing internal links from or to a page
- Improving a page's CTR from search results
seo-rank-tracking
When your agent uses it
Set up and run rank tracking using Ahrefs MCP: pick the right keywords to track, segment them by purpose, set baselines, and define alert thresholds. Use this skill when starting a new tracking project, baselining for a campaign, choosing what to monitor, or building a rank reporting cadence. Triggers on rank tracking, keyword tracking, monitor rankings, track positions, what should we track, ranking dashboard, baseline rankings, alert thresholds. Also triggers when a stakeholder wants weekly or monthly ranking visibility.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
2,181 tokensWhen the skill is activated
Reference documents
1,784 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: tracking taxonomy
- Selection criteria
- Segmentation beyond buckets
- Baselines
- Alert thresholds
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,307 bytesSKILL.mdcore10,307 bytesreferences/dashboard-template.mddoc7,392 bytes
Read SKILL.md
# SEO Rank Tracking
Set up and run an ongoing rank tracking program using Ahrefs MCP data. Stack-agnostic. Produces a tracked keyword set, segmentation, baseline, alert thresholds, and a review cadence.
---
## When to use
- Starting rank tracking for a new property or section
- Baselining before a campaign, content launch, or major site change
- Deciding what keywords are worth tracking
- Setting up a ranking dashboard for stakeholders
- Establishing alert thresholds for ranking drops
- Reviewing whether the current tracked set is still meaningfulseo-site-health-audit
When your agent uses it
Triage technical SEO findings from Ahrefs Site Audit (and similar crawlers) by SEO impact, not just severity. Use this skill when reviewing crawl results, prioritizing technical fixes, scoping a technical SEO sprint, or after running any site-wide crawl. Triggers on site audit results, technical fix list, crawl errors, technical SEO triage, prioritize technical issues, what should we fix first, broken links, redirect chains. Also triggers when a long list of crawler issues is creating decision paralysis.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
2,320 tokensWhen the skill is activated
Reference documents
2,074 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: triage by SEO impact, not severity
- The triage matrix
- Workflow
- High-leverage clusters worth looking for
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,000 bytesSKILL.mdcore10,000 bytesSKILL.mdcore10,000 bytesreferences/issue-impact-table.mddoc8,612 bytes
Read SKILL.md
# SEO Site Health Audit
Triage technical SEO findings from Ahrefs Site Audit (or any equivalent crawler) by impact on rankings and traffic, not by raw issue count or severity label. Stack-agnostic. Produces a prioritized backlog of fixes mapped to business impact.
---
## When to use
- After running an Ahrefs Site Audit or other site-wide crawl
- Reviewing a long list of technical issues and needing to prioritize
- Scoping a technical SEO sprint
- Pre-launch or post-migration technical verification
- Quarterly technical health check
- When developer time is limited and you must pick the highest-leverage fixesseo-technical
When your agent uses it
Run a comprehensive technical SEO audit covering crawlability, indexability, rendering, site architecture, structured data, page experience, security, and internationalization. Use this skill whenever the user asks about technical SEO, crawl issues, indexing problems, sitemaps, robots.txt, canonical tags, schema markup, page speed, Core Web Vitals, hreflang, redirects, or site-wide search performance. Triggers on technical SEO, site audit, crawlability, indexability, sitemap, robots.txt, canonical, redirect chain, schema, JSON-LD, Core Web Vitals, page speed, hreflang, mobile usability, HTTPS, security headers, render-blocking, JavaScript SEO. Also triggers when a site has indexing problems, traffic drops, or migration concerns, even if 'technical SEO' is not said explicitly.
What it loads into context
Frontmatter
204 tokensAlways available to the agent
SKILL.md
1,630 tokensWhen the skill is activated
Reference documents
3,610 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore7,361 bytesSKILL.mdcore7,361 bytesreferences/audit-template.mddoc9,991 bytesreferences/migration-checklist.mddoc5,020 bytes
Read SKILL.md
# Technical SEO
Audit and fix the layer beneath the content: how search engines crawl, render, index, and trust a site. Stack-agnostic.
---
## When to use
- Site-wide audit before or after a migration
- Investigating indexing or ranking drops
- Setting up SEO foundations on a new site
- Auditing Core Web Vitals or page experience signals
- Fixing crawl waste, redirect chains, or canonical issues
- Setting up multilingual or multi-regional sitesseo-traffic-diagnosis
When your agent uses it
Diagnose organic traffic changes (drops, stalls, or unexpected wins) using Ahrefs MCP plus Search Console data. Use this skill when traffic suddenly dropped, has been flat despite investment, after an algorithm update, after a migration or deploy, or when a competitor seems to be taking share. Triggers on traffic dropped, traffic decline, traffic stalled, organic decline, lost rankings, why is traffic down, algorithm update, post-migration traffic loss, traffic diagnosis. Also triggers when stakeholders are panicking about an organic traffic number they cannot explain. A panic about tracking, event, or dashboard setup is a measurement problem, not a traffic problem: route those to `analytics-strategy`.
What it loads into context
Frontmatter
182 tokensAlways available to the agent
SKILL.md
1,903 tokensWhen the skill is activated
Reference documents
1,720 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers of diagnosis
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore8,870 bytesSKILL.mdcore8,870 bytesSKILL.mdcore8,870 bytesreferences/diagnosis-checklist.mddoc7,863 bytes
Read SKILL.md
# SEO Traffic Diagnosis
Diagnose why organic traffic moved (down, flat, or unexpectedly up) using Ahrefs MCP combined with Search Console and analytics data. Stack-agnostic. Produces a root-cause diagnosis and an action plan.
---
## When to use
- Organic traffic dropped sharply
- Organic traffic has been flat for months despite content investment
- After a known Google algorithm update
- After a migration, replatform, or domain change
- After a deploy that touched routing, redirects, or rendering
- When a competitor is visibly taking organic shareskill-creation-walkthrough
When your agent uses it
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not triggering or not loading the right context, when you are auditing a skill that is underperforming, or when you want to publish a skill for others. Also triggers when someone asks "how do I make a skill" or "what makes a good skill". Useful for individuals, teams, and anyone publishing skills publicly.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
3,061 tokensWhen the skill is activated
Reference documents
4,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: how skills work
- Workflow
- Deep dive: description anatomy
- Deep dive: worked example
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore13,937 bytesreferences/description-cookbook.mddoc9,417 bytesreferences/methodology-vs-implementation.mddoc7,734 bytesreferences/skill-template.mddoc5,760 bytes
Read SKILL.md
A walkthrough for designing, writing, and maintaining your own Claude Skills. Covers when a skill is the right shape for your problem, how to write a description that actually triggers, how to structure SKILL.md and references, and how to test and iterate.
## When to use
- You catch yourself writing the same prompt or instructions repeatedly.
- You want to package a workflow or framework for reuse.
- An existing skill of yours is not triggering when it should.
- You are publishing skills for others to use.
- You want to teach Claude a domain-specific way of working.
- You are reviewing a skill someone wrote and need a quality bar.
## When NOT to use
- For one-off prompts (just write the prompt).sprint-operations
When your agent uses it
Run the measurement and ceremony layer of a delivery team: the metric set, estimation and capacity, the five sprint ceremonies, and the sprint report and quarterly rollup. Use this skill whenever the user is acting as PMO or scrum lead, planning a sprint, running standup, refinement, review, or retro, measuring velocity, cycle time, or throughput, checking capacity, or reporting on how a team is doing. Triggers on PMO, sprint planning, plan the sprint, standup, refinement, backlog grooming, sprint review, retro, velocity, capacity, cycle time, lead time, throughput, WIP, burndown, carryover, sprint report, story points to hours, how is the team doing, delivery metrics, agent lanes. Also triggers when the user asks how much work fits in a sprint or whether a team is on track, even if they never say sprint or PMO.
What it loads into context
Frontmatter
224 tokensAlways available to the agent
SKILL.md
2,659 tokensWhen the skill is activated
Reference documents
6,507 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 parts
- Workflow
- Deep dive: measuring agent lanes
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore12,181 bytesSKILL.mdcore12,181 bytesreferences/capacity-checklist.mddoc2,800 bytesreferences/example-sprint-report.mddoc4,357 bytesreferences/metrics-reference.mddoc6,079 bytesreferences/planning-template.mddoc1,947 bytesreferences/refinement-template.mddoc2,030 bytesreferences/retro-template.mddoc2,512 bytesreferences/review-template.mddoc1,577 bytesreferences/sprint-report-template.mddoc2,370 bytesreferences/standup-template.mddoc1,790 bytes
Read SKILL.md
# Sprint Operations
Run the measurement and ceremony layer of a delivery team so planning is grounded in history and reporting is derived from the tracker, not typed in. Tracker-agnostic: works with Jira, Linear, GitHub Issues, or your tracker of choice.
---
## When to use
- Setting up the metric set for a new or inherited team
- Planning a sprint and checking it against real capacity
- Running standup, refinement, review, or retro with a consistent template
- Answering "how is the team doing?" with numbers instead of adjectives
- Writing the sprint report or the quarterly rollup
- Deriving a points-to-hours ratio for financestakeholder-communication
When your agent uses it
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on stakeholder update, status report, executive summary, exec review, manage up, communicate bad news, project comms, status meeting, weekly update. Also triggers when a project is going off track and the team needs to communicate it.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
2,572 tokensWhen the skill is activated
Reference documents
2,551 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 questions
- The structure: the inverted pyramid
- Update templates
- Tone and register
- Workflow
- Cadence design
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore11,369 bytesreferences/update-templates.mddoc9,864 bytes
Read SKILL.md
# Stakeholder Communication
Get the right information to the right people at the right time, in a form they can act on. Stack-agnostic. Applies to any team operating with cross-functional stakeholders.
---
## When to use
- Writing weekly or monthly status updates
- Preparing for an executive review or board update
- Sharing a technical decision with a non-technical audience
- Communicating a delay, miss, or quality problem
- Asking for help, resources, or decisions
- Managing up to a manager or sponsorteam-onboarding-playbook
When your agent uses it
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also triggers when one person owns all the tribal knowledge and you need to capture it, when you keep losing people in their first 90 days, or when a new project has many fresh members joining at once. Useful for engineering, design, product, marketing, and operations roles.
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
2,126 tokensWhen the skill is activated
Reference documents
1,695 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework
- The 30/60/90 plan
- The role-specific overlay
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore9,151 bytesreferences/onboarding-checklist.mddoc6,967 bytes
Read SKILL.md
A repeatable framework for building an onboarding playbook that ramps new team members predictably without burning out the people training them.
## When to use
- A new hire is joining and you do not have a written onboarding plan.
- An existing onboarding process is informal and inconsistent.
- A team is growing fast and onboarding is the bottleneck.
- A contractor or agency partner needs to ramp up quickly.
- A team member is leaving and their knowledge needs capturing.
- Onboarding currently takes too long and you want to reduce it.
## When NOT to use
- For ongoing performance management (different problem).ticket-authoring
When your agent uses it
Write complete, ready-to-pull work items for an issue tracker: bugs, tasks, stories, spikes, and epics, each with the fields, attachments, and done test its type requires. Use this skill whenever the user wants to write a ticket, create a Jira issue, Linear issue, or GitHub issue, file a bug report, write a user story or acceptance criteria, scope a spike, open an epic, or break work into tasks. Triggers on write a ticket, create an issue, file a bug, bug report, user story, spike, epic, task breakdown, turn this into tickets, break this down, acceptance criteria, definition of ready, ready for dev, backlog item, capitalization stage. Also triggers when the user pastes a PRD, a spec, or a bug description and asks what to do with it, even if they never say the word ticket.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
2,385 tokensWhen the skill is activated
Reference documents
7,022 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: five types, one definition of ready each
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore10,484 bytesSKILL.mdcore10,484 bytesSKILL.mdcore10,484 bytesreferences/bug-template.mddoc4,010 bytesreferences/capitalization-guide.mddoc5,934 bytesreferences/definition-of-ready-checklist.mddoc3,423 bytesreferences/epic-template.mddoc2,474 bytesreferences/example-bug-and-story.mddoc5,925 bytesreferences/spike-template.mddoc2,348 bytesreferences/story-template.mddoc2,862 bytesreferences/task-template.mddoc2,802 bytes
Read SKILL.md
# Ticket Authoring
Turn specs, bug reports, and loose requests into work items someone can pull and start without asking a question. Tracker-agnostic: works in Jira, Linear, GitHub Issues, or your tracker of choice.
---
## When to use
- Turning a PRD or spec into a set of tickets
- Filing a bug that someone else will fix
- Writing a user story with checkable acceptance criteria
- Scoping a spike so it ends in a decision, not a shrug
- Opening an epic with a goal, a metric, and a way to kill it
- Auditing a backlog for tickets that are not ready to pullupgrade-flow-design
When your agent uses it
Designing free-to-paid conversion flows for SaaS products. Trigger moments, paywall design, value demonstration, upsell vs downsell, win-back flows, churn prevention. Honest about paywall-everywhere (gates everything aggressively), free-forever-trap (no upgrade path surfaces), and value-triggered-upgrade (paywall surfaces at moments of demonstrated value) patterns. Triggers on upgrade flow, paywall, free-to-paid, freemium conversion, trial conversion, plan upgrade, subscription upgrade, win-back flow, churn prevention. Also triggers when free-to-paid conversion is low, when paywalls are blocking the wrong moments, or when upgrade flows are being scoped for the first time.
What it loads into context
Frontmatter
218 tokensAlways available to the agent
SKILL.md
3,906 tokensWhen the skill is activated
Reference documents
13,470 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The free-tier decision: freemium vs free-trial vs no-free
- Paywall-everywhere vs free-forever-trap vs value-triggered-upgrade
- Trigger-moment design: where paywalls earn their interruption
- Paywall presentation: modal vs banner vs inline
- Upsell vs downsell logic
- Win-back flow design
- Churn prevention upstream of upgrade
- Plan structure: tier count, feature gating, pricing-page design
- Common failure modes
- The framework: 12 considerations for upgrade flow design
- Reference files
- Closing: upgrade flows earn revenue when they earn the user's yes
Files
SKILL.mdcore18,370 bytesreferences/churn-prevention-upstream.mddoc7,181 bytesreferences/common-upgrade-failures.mddoc6,254 bytesreferences/free-tier-decision-criteria.mddoc7,823 bytesreferences/paywall-presentation-patterns.mddoc7,977 bytesreferences/plan-structure-patterns.mddoc7,806 bytesreferences/trigger-moment-design.mddoc7,389 bytesreferences/upgrade-flow-anti-patterns.mddoc6,384 bytesreferences/upsell-vs-downsell-logic.mddoc6,514 bytesreferences/win-back-flow-patterns.mddoc7,244 bytes
Read SKILL.md
# Upgrade Flow Design
A senior product marketing director's playbook for designing free-to-paid conversion flows in SaaS products. Trigger moments, paywall design, value demonstration, upsell vs downsell, win-back flows, churn prevention. The discipline of asking for the upgrade at the moment the user has a reason to say yes.
Most upgrade flows fail in one of two ways. They block meaningful product use behind paywalls so aggressively that users churn before reaching the moment that would justify paying. Or they offer a generous free tier with no upgrade path that ever surfaces; users get everything they need; conversion stays at single-digit percentages indefinitely.
The upgrade flows that work do something different. They surface paywalls at moments where the user has demonstrably gotten value. The user has hit a usage threshold, completed a flow, or otherwise demonstrated they are getting the product's promise. The upgrade ask is honest about what they get next; the user is positioned to say yes because the value is fresh.
The voice is the senior product marketing director who has watched conversion rates double when paywalls were re-timed and watched them collapse when more aggressive paywalls were added. Practical, opinionated about the moments that earn the upgrade ask, willing to call out when the product's free tier is too generous to convert.
When to use this skill: scoping a free-to-paid conversion flow for the first time, auditing paywalls that block conversion or never surface, designing the trigger moments that earn upgrade asks, or deciding plan structure that supports upgrades over time.
---
usability-testing
When your agent uses it
Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task completion. Triggers on usability test, usability testing, moderated test, unmoderated test, task script, think aloud, prototype testing, user testing, design validation, task completion. Also triggers when the user has built something and wants to know if real users can use it before shipping.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,163 tokensWhen the skill is activated
Reference documents
2,423 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore9,553 bytesSKILL.mdcore9,553 bytesreferences/task-script-patterns.mddoc10,751 bytes
Read SKILL.md
# Usability Testing
Plan and run tests that find usability problems before users hit them in production. Stack-agnostic. Tool-agnostic.
This skill is for testing existing designs or prototypes. For broader discovery research, use `ux-research`. For conversion testing in production, use `cro-optimization`.
---
## When to use
- Before launching a new flow or major redesign
- After a redesign to verify it doesn't introduce new problems
- When analytics show drop-off but you don't know why
- When customer support tickets pattern around specific UI areasuser-feedback-aggregation
When your agent uses it
Collecting and synthesizing user feedback across channels (support tickets, NPS, in-app feedback, sales calls, social mentions, customer councils) into a continuous signal that informs product decisions. The triage discipline that distinguishes loudest-voice (whoever complains most wins) from averaged-noise (every signal weighted equally) from triaged-synthesis (signal weighted by source quality, frequency, and decision relevance). Triggers on user feedback, customer feedback aggregation, NPS, support ticket analysis, customer councils, feedback synthesis, voice of customer, feedback triage, in-app feedback. Also triggers when feedback channels overflow with volume that does not produce decisions, when the loudest-voice problem is steering roadmap, or when continuous feedback streams need synthesis discipline.
What it loads into context
Frontmatter
228 tokensAlways available to the agent
SKILL.md
4,010 tokensWhen the skill is activated
Reference documents
17,557 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Loudest-voice vs averaged-noise vs triaged-synthesis
- Feedback channels and what each surfaces
- Channel-source weighting
- Categorization and tagging discipline at scale
- Frequency vs intensity
- From feedback to product decision
- Closing the loop with users
- Detecting drift in feedback patterns over time
- Feedback aggregation tooling considerations
- Common failure modes
- The framework: 12 considerations for feedback aggregation
- Reference files
- Closing: feedback as continuous signal, not periodic survey
Files
SKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesSKILL.mdcore20,891 bytesreferences/categorization-and-tagging-at-scale.mddoc9,921 bytesreferences/channel-source-weighting.mddoc11,159 bytesreferences/channel-types-and-what-each-surfaces.mddoc11,456 bytesreferences/closing-the-loop-with-users.mddoc9,771 bytesreferences/common-feedback-aggregation-failures.mddoc10,499 bytesreferences/detecting-drift-in-feedback.mddoc9,679 bytesreferences/frequency-vs-intensity.mddoc9,855 bytesreferences/from-feedback-to-product-decision.mddoc10,028 bytesreferences/tooling-considerations.mddoc9,072 bytes
Read SKILL.md
# User Feedback Aggregation
A senior product leader's playbook for collecting and synthesizing user feedback across channels into continuous decision signal. Support tickets, NPS surveys, in-app feedback, sales calls, social mentions, customer councils, all aggregated into a triaged synthesis the team can actually act on.
Most product programs accumulate feedback they do not use. Channels overflow with submissions; CSAT and NPS scores get reported in monthly updates; customer council meetings produce notes that nobody references. The loudest voices steer roadmap because they are easiest to hear; quieter signal that matters more goes unaddressed.
This skill is the triage discipline that turns continuous feedback streams into continuous decision signal. Each channel surfaces different signal at different reliability. Each signal type warrants different weight in different decisions. The team that aggregates feedback well makes better decisions; the team that drowns in feedback makes the same decisions they would have made without the feedback.
Different from `discovery-research-synthesis`, which covers one-off research projects (a defined batch of artifacts, a defined synthesis output). This skill covers the always-on streams: feedback that arrives every day, every week, every month, and that the team must continuously triage and synthesize.
The voice is the senior product leader who has watched feedback aggregation work and watched it fail. Concrete, opinionated about which channels matter for which decisions, willing to call out where loudest-voice or averaged-noise patterns produce bad outcomes.
When to use this skill: building a feedback aggregation system, auditing a feedback program that is producing volume without decisions, deciding which feedback channels matter for the program, or designing the synthesis cadence for ongoing feedback streams.
ux-research
When your agent uses it
Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design interviews, recruit participants, conduct discovery, run formative research, or synthesize qualitative findings. Triggers on user research, UX research, user interviews, discovery research, generative research, formative research, qualitative research, user insights, research synthesis, recruitment, interview guide, jobs to be done. Also triggers when product decisions are being made without user input and the user wants to fix that.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,357 tokensWhen the skill is activated
Reference documents
1,836 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore10,944 bytesSKILL.mdcore10,944 bytesreferences/interview-guide-template.mddoc8,034 bytes
Read SKILL.md
# UX Research
Plan and execute user research that produces decisions, not just decks. Stack-agnostic. Tool-agnostic.
This skill is for generative and discovery research. For testing existing designs, use `usability-testing`. For mapping the full customer experience, use `journey-mapping`.
---
## When to use
- Starting a new product or major feature without sufficient user understanding
- Diagnosing why something isn't working without clear data signals
- Generating new opportunity hypotheses
- Validating a strategic direction before significant investmentvendor-evaluation
When your agent uses it
Evaluate, select, and contract with vendors and SaaS tools. Use this skill when comparing alternatives, running an RFP, scoring vendors against criteria, negotiating contracts, planning a switch, or assessing a vendor's risk. Triggers on vendor evaluation, RFP, vendor selection, build vs buy, SaaS evaluation, vendor scorecard, vendor comparison, contract negotiation, vendor switch, procurement. Also triggers when a renewal is coming up or when a tool isn't meeting expectations.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,497 tokensWhen the skill is activated
Reference documents
1,748 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
SKILL.mdcore11,358 bytesSKILL.mdcore11,358 bytesSKILL.mdcore11,358 bytesSKILL.mdcore11,358 bytesreferences/evaluation-rubric.mddoc6,889 bytes
Read SKILL.md
# Vendor Evaluation
Pick the right tool or service, negotiate fair terms, and avoid the lock-in traps. Stack-agnostic. Applies to SaaS, infrastructure providers, agencies, and any external dependency.
---
## When to use
- Selecting a tool or vendor for a new need
- Evaluating alternatives to a current vendor
- Build vs buy analysis
- Renewal coming up: should we stay or switch?
- Running a formal RFP or RFI
- Comparing finalists in a vendor selectionvertical-site-conventions
When your agent uses it
Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that reads as generic or off-vertical, build to an experience bar produced by competitor-experience-audit, or compose pages with the merchandising, density, and layout conventions a credible site in the category is expected to carry. Triggers on vertical conventions, storefront layout, ecommerce layout, retail conventions, merchandising layout, category page composition, site composition, build to the experience bar, make it look like the vertical, off-vertical, looks generic, build conventions for a vertical, site grammar. Also triggers when a build that is technically clean reads wrong for its category, and the cause is composition, not visual taste.
What it loads into context
Frontmatter
219 tokensAlways available to the agent
SKILL.md
4,001 tokensWhen the skill is activated
Reference documents
14,114 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: build to the seven dimensions
- How the skill consumes an experience bar
- Stays in its lane (load-bearing)
- Workflow
- Failure patterns
- Output format
- Reference files
Files
SKILL.mdcore19,128 bytesreferences/shape-b2b-manufacturer.mddoc14,698 bytesreferences/shape-conventions-checklist.mddoc6,411 bytesreferences/shape-directory-marketplace.mddoc1,515 bytesreferences/shape-ecommerce-catalog.mddoc13,007 bytesreferences/shape-ecommerce-standout.mddoc1,794 bytesreferences/shape-hospitality-experience.mddoc1,728 bytesreferences/shape-hospitality-food.mddoc11,002 bytesreferences/shape-institution-mission.mddoc1,911 bytesreferences/shape-inventory-listing.mddoc1,511 bytesreferences/shape-local-service-booking.mddoc11,284 bytesreferences/shape-subscription-app.mddoc1,524 bytes
Read SKILL.md
# Vertical Site Conventions
Compose pages and whole sites to the layout, density, and merchandising conventions that make a build read as a credible member of its vertical. Stack-agnostic. Works on any framework that can express server-rendered pages and component composition.
This skill owns vertical-level composition: which modules go where, how dense the page is, how much of the catalog or offering is surfaced, and which paths the navigation serves. It routes the day-to-day visual decisions to `design-standards`, the aesthetic register to `creative-direction`, the site-structure modeling to `information-architecture`, and the component implementation to `frontend-component-build`. It does not duplicate any of them; it composes their outputs into a vertical-correct site.
It is the build-side counterpart to `competitor-experience-audit`. The audit measures the field on seven dimensions; this skill builds to those same seven, dimension by dimension. The two are deliberately structured as two sides of one standard so an experience bar produced by the audit maps one-to-one onto what this skill builds.
---
## When to use
- Building a new site in a vertical you have not built in before
- Fixing a build that reads as generic or off-vertical even though it is technically clean (the SEO, accessibility, and component implementation are correct, but the page does not read like its category)accessibility-audit
When your agent uses it
Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
2,441 tokensWhen the skill is activated
Reference documents
8,456 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: WCAG's 4 principles
- Audit methodology
- Workflow
- Severity classification
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc1,719 bytesSKILL.mdcore11,456 bytesSKILL.mdcore11,456 bytesSKILL.mdcore11,456 bytesreferences/aria-patterns.mddoc18,175 bytesreferences/audit-report-template.mddoc5,175 bytesreferences/wcag-quick-reference.mddoc8,655 bytes
Read SKILL.md
# Accessibility Audit
Run a thorough accessibility audit and produce a remediation plan. Stack-agnostic. Anchored to WCAG 2.1 AA, with notes on AAA where relevant.
This skill goes deeper than the accessibility checks in `qa-testing` and `design-standards`. Use this when accessibility itself is the goal.
---
## When to use
- Pre-launch accessibility verification
- Compliance preparation (ADA, EN 301 549, AODA, Section 508)
- Remediation after an audit finding or complaint
- Annual or quarterly accessibility health checkads-creative-development
When your agent uses it
How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
4,527 tokensWhen the skill is activated
Reference documents
9,961 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Performance vs brand creative
- Hook patterns: the first 3 seconds
- Format selection
- Video pacing
- Variation systems
- Sequential testing methodology
- Creative fatigue detection
- Brand-voice alignment without conversion dilution
- Platform-specific creative norms
- Common failures
- The framework: 10 considerations for sustainable creative production
- Reference files
- Closing: the hook is the whole game
Files
README.mddoc365 bytesSKILL.mdcore21,341 bytesreferences/brand-voice-performance-balance.mddoc7,397 bytesreferences/creative-variation-templates.mddoc5,621 bytesreferences/fatigue-detection-checklist.mddoc6,431 bytesreferences/format-decision-matrix.mddoc4,791 bytesreferences/hook-pattern-library.mddoc7,100 bytesreferences/platform-creative-norms.mddoc6,827 bytesreferences/testing-cadence-playbook.mddoc6,034 bytes
Read SKILL.md
# Ads Creative Development
A senior creative strategist's playbook for producing ad creative that performs.
Performance creative is a different discipline from brand creative. Brand work optimizes for memorability, emotional resonance, and distinctive identity. Performance creative optimizes for stopping the scroll, communicating value in three seconds, and producing a click. Both matter. Mixing them up costs money. Brand creative running as performance ads bleeds budget; performance creative running as brand ads erodes equity.
This skill is the discipline that produces performance creative without diluting brand. It assumes you know your audience and offer (see `paid-media-strategy`). It assumes you have brand-voice guidance (see `brand-voice`). The hard part is the systematic production of variations that test cleanly and ship without manual approval bottlenecks, and that is what is here.
When to use this skill: producing ad creative for paid campaigns, planning a creative testing cycle, diagnosing creative fatigue, or auditing why creative is not converting.
---
## What this skill is for
ads-performance-analytics
When your agent uses it
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
5,133 tokensWhen the skill is activated
Reference documents
11,620 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every paid media platform should expose
- Platform-reported vs reality
- Attribution models in practice
- Multi-platform reconciliation
- ROAS vs LTV: the time horizon trap
- Cohort analysis vs daily metrics
- Statistical noise in performance metrics
- Incrementality testing
- Geo experiments and holdouts
- Platform self-attribution bias
- Common interpretation failures
- The framework: 12 considerations for trustworthy paid media interpretation
- If required data is unavailable
- Reference files
- Closing: the courage to call it incremental zero
Files
README.mddoc366 bytesSKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesSKILL.mdcore24,770 bytesreferences/attribution-model-comparison.mddoc7,456 bytesreferences/cohort-analysis-templates.mddoc6,603 bytesreferences/common-interpretation-failures.mddoc9,164 bytesreferences/dashboard-reconciliation-patterns.mddoc6,692 bytesreferences/incrementality-testing-playbook.mddoc7,127 bytesreferences/metric-definitions-glossary.mddoc6,677 bytesreferences/platform-reporting-quirks.mddoc8,963 bytes
Read SKILL.md
# Ads Performance Analytics
A data-team-mentor's playbook for interpreting paid media dashboards without fooling yourself.
The dashboard is the moment of truth for paid media decisions. The numbers on it determine whether you scale, hold, or kill. They also expose every platform's self-attribution bias, every modeled-conversion shortcut, every cross-platform double-count. Most "scale this campaign" decisions trace back to misreading the dashboard.
This skill is the discipline that prevents misreading. It assumes the campaign was strategically sound (see `paid-media-strategy`). It assumes the creative was tested properly (see `ads-creative-development`). The hard part is knowing what each number actually means, what it does not, and how to reconcile platform-reported metrics with the truth in your warehouse.
When to use this skill: any time you are about to scale, kill, or rebudget a campaign based on platform metrics; reconciling platform reports with revenue data; evaluating an agency's reporting; or building a paid media dashboard that will not lie to you.
---
## What this skill is for
after-action-report
When your agent uses it
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
2,231 tokensWhen the skill is activated
Reference documents
2,217 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: blameless analysis
- The framework: 6 sections
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc360 bytesSKILL.mdcore9,902 bytesSKILL.mdcore9,902 bytesSKILL.mdcore9,902 bytesreferences/aar-template.mddoc8,344 bytes
Read SKILL.md
# After-Action Report
Run a structured retrospective on a launch, incident, or completed project. Produce actionable lessons, not just a document.
This skill is for after-the-fact analysis. For active incident response, use `incident-response`. For planning launches, use `launch-runbook`.
---
## When to use
- After any incident (any severity)
- After every major launch
- At the end of a project (sprint retro, quarterly retro, project closeout)
- When a recurring issue has happened enough times to demand investigationai-content-collaboration
When your agent uses it
How humans and AI compose in content workflows. Where AI legitimately participates, where humans must own, hybrid workflow patterns, voice ownership preservation, the AI slop problem, disclosure and transparency, team calibration, and the ethics of intellectually honest AI-assisted content production. Triggers on AI content workflow, AI-assisted writing, hybrid content production, AI in editorial, AI slop, AI disclosure, AI usage policy, AI content ethics, voice preservation with AI, team AI calibration. Also triggers when content feels generic despite quality tools, when team AI usage has drifted into inconsistency, or when a regulated or trust-sensitive context requires explicit AI policy.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
4,638 tokensWhen the skill is activated
Reference documents
16,226 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Humans own, AI accelerates
- Where AI legitimately participates
- Where humans must own
- Hybrid workflow patterns
- Voice ownership preservation
- The AI slop problem
- Disclosure and transparency
- Team training and calibration
- Ethics: training data, attribution, intellectual honesty
- Common failure modes
- The framework: 12 considerations for AI content collaboration
- Reference files
- Closing: collaboration, not replacement
Files
README.mddoc365 bytesSKILL.mdcore22,585 bytesSKILL.mdcore22,585 bytesSKILL.mdcore22,585 bytesreferences/ai-participation-boundaries.mddoc7,481 bytesreferences/ai-slop-detection-and-avoidance.mddoc8,587 bytesreferences/common-collaboration-failures.mddoc10,479 bytesreferences/disclosure-and-transparency-patterns.mddoc9,437 bytesreferences/ethics-and-intellectual-honesty.mddoc10,412 bytesreferences/hybrid-workflow-patterns.mddoc8,302 bytesreferences/quality-calibration-with-ai-in-loop.mddoc9,077 bytesreferences/team-training-and-calibration.mddoc8,499 bytesreferences/voice-ownership-preservation.mddoc8,373 bytes
Read SKILL.md
# AI Content Collaboration
A senior editorial leader's playbook for how humans and AI compose in content workflows. Pragmatic, tool-agnostic, honest about both what AI in the loop enables and what it threatens.
Most content programs in 2026 use AI somewhere in the workflow. Pretending otherwise is dishonest; treating AI as a magic content factory is the failure mode this skill exists to prevent. The discipline is in between: knowing where AI legitimately accelerates, where humans must own, what hybrid patterns produce work that earns reader trust, and what crosses the line into AI slop or intellectual dishonesty.
This skill is the WORKFLOW layer that composes with every other content skill. Briefs can be AI-assisted; hub architectures can be AI-assisted; programmatic SEO is almost always AI-involved; editorial QA now includes AI-content audit by necessity. The collaboration discipline applies to all production stages, not to a single artifact type.
The voice is pragmatic and tool-agnostic deliberately. The methodology applies whether the AI in your loop is one of the major commercial models, an open-source model, or whatever ships next quarter. What stays constant is the workflow shape, the participation boundaries, the voice ownership question, and the ethical frame. What changes is which specific tool you reach for, which is implementation work that varies by team and budget.
When to use this skill: building or refining an AI-content workflow, calibrating a team on consistent AI usage, addressing the "we use AI but our work feels generic" problem, designing disclosure policies, or working through the ethics of AI-assisted content production for a regulated or trust-sensitive context.
---
analytics-strategy
When your agent uses it
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement. Triggers on analytics strategy, measurement plan, event taxonomy, tracking plan, KPI framework, dashboard design, north star metric, attribution model, conversion tracking, GA4 setup, Mixpanel setup, analytics audit. Also triggers when the user has data but no clear way to use it, or wants to make decisions but doesn't know what to track.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
2,033 tokensWhen the skill is activated
Reference documents
2,387 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- The tracking plan document
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc359 bytesSKILL.mdcore9,470 bytesreferences/event-taxonomy-template.mddoc9,896 bytes
Read SKILL.md
# Analytics Strategy
Design measurement frameworks that produce decisions, not just dashboards. Stack-agnostic. Tool-agnostic.
This skill is for measurement planning. For conversion optimization, use `cro-optimization`. For SEO measurement specifically, use `seo-onpage` and adjacent SEO skills.
---
## When to use
- Setting up analytics on a new product or site
- Auditing existing analytics setup
- Designing dashboards for a team or business
- Defining KPIs and a north star metricart-direction
When your agent uses it
Direct visual and creative work for campaigns, photography, illustration, video, and branded experiences. Use this skill whenever the user wants to brief a photographer, direct illustrators, plan a creative campaign, develop visual concepts, or evaluate creative work for fit. Triggers on art direction, photo brief, photography brief, illustration brief, campaign concept, creative concept, visual direction, mood board, look and feel, visual treatment, video direction. Also triggers when the user has approved brand identity but needs to extend it into specific creative deliverables. Use `creative-direction` instead when the ask is the project-wide aesthetic brief that this skill consumes as input.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
2,059 tokensWhen the skill is activated
Reference documents
5,105 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc354 bytesSKILL.mdcore9,611 bytesreferences/creative-brief-template.mddoc6,077 bytesreferences/illustration-brief.mddoc7,946 bytesreferences/photo-shoot-brief.mddoc6,424 bytes
Read SKILL.md
# Art Direction
Direct creative work that extends the brand into specific deliverables. Photography, illustration, video, motion, campaigns, environmental design.
This skill assumes brand identity is approved (`brand-identity` complete). Art direction is about applying and extending it, not defining it.
---
## When to use
- Briefing photographers, illustrators, videographers
- Developing campaign creative concepts
- Directing in-house creative teams
- Writing creative direction documents for vendorsbackup-and-disaster-recovery
When your agent uses it
Plan and run backups, set recovery objectives, and run disaster recovery drills. Use this skill when defining RPO/RTO targets, designing backup architecture, deciding what to back up and how often, planning for full-region or platform outages, or running a restoration drill. Triggers on backup, restore, RPO, RTO, disaster recovery, DR, business continuity, what if the database is gone, what if our hosting goes down, recovery drill, ransomware planning. Also triggers when an incident reveals a gap in restoration capability.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,406 tokensWhen the skill is activated
Reference documents
1,436 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 questions
- Workflow
- Special topics
- Failure patterns
- Output format
- Reference files
Files
README.mddoc369 bytesSKILL.mdcore10,870 bytesSKILL.mdcore10,870 bytesreferences/restore-runbook-template.mddoc5,525 bytes
Read SKILL.md
# Backup and Disaster Recovery
Plan for the worst case: the database is gone, the host is down for a week, the deploy was poisoned, ransomware encrypted everything. The skill is in advance preparation, not reaction.
---
## When to use
- Setting up backups for a new system
- Reviewing and validating backup architecture
- Defining RPO (recovery point objective) and RTO (recovery time objective)
- Running a disaster recovery drill
- Diagnosing gaps after an incident
- Planning for ransomware, data corruption, or insider threatsbeta-program-management
When your agent uses it
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria). Triggers on beta program, alpha test, beta cohort, beta participant, beta feedback, beta to GA decision, design partner, early access program, closed beta, open beta, RC release. Also triggers when a feature is approaching launch and the team needs structured pre-GA validation, when prior betas produced noise rather than signal, or when the team has soft-launched before but wants more structured feedback this time.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
4,942 tokensWhen the skill is activated
Reference documents
18,341 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Soft-launch vs kitchen-sink vs structured-beta
- Beta type decisions
- Participant selection criteria
- Beta cohort sizing
- Onboarding beta participants
- Feedback collection patterns
- Mid-beta triage and iteration
- Beta-to-GA decision criteria
- Beta wind-down and participant communication
- Common failure modes
- The framework: 12 considerations for beta program management
- If required data is unavailable
- Reference files
- Closing: betas earn their keep with structure
Files
README.mddoc364 bytesSKILL.mdcore24,454 bytesSKILL.mdcore24,454 bytesreferences/beta-onboarding-templates.mddoc10,602 bytesreferences/beta-to-ga-graduation-criteria.mddoc11,663 bytesreferences/beta-type-decisions.mddoc10,326 bytesreferences/beta-wind-down-communication.mddoc9,512 bytesreferences/cohort-sizing-patterns.mddoc8,928 bytesreferences/common-beta-failures.mddoc10,373 bytesreferences/feedback-collection-patterns.mddoc10,916 bytesreferences/mid-beta-triage-and-iteration.mddoc9,669 bytesreferences/participant-selection-criteria.mddoc10,154 bytes
Read SKILL.md
# Beta Program Management
A senior product leader's playbook for running betas that produce real signal. Closed and open betas, alpha programs, design partner programs, early access. Participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria).
Most betas underperform. Teams ship a beta because they think they should run a beta; participants are recruited loosely or open-flooded; feedback is collected ad-hoc through whatever channels exist; the decision to graduate to GA happens on calendar rather than on signal. The beta produced activity but not learning; the team launches with the same uncertainty they had before the beta.
This skill is the discipline that turns betas into decision input. Calibrated cohorts who match the post-launch user profile. Structured feedback that captures what the team needs to know. Mid-beta triage that uses what is being learned. Graduation criteria that distinguish "ready" from "we are tired of running the beta." The discipline is not bureaucratic; it is the difference between a beta that informs the GA launch and a beta that produces noise.
The voice is the senior product leader who has run betas with real signal and watched plenty of betas produce nothing. Concrete, opinionated about what produces signal, willing to call out where beta programs slide into ceremony.
When to use this skill: planning a beta for an upcoming launch, auditing why prior betas have not produced actionable signal, designing the beta participant experience, or deciding whether a feature is ready to graduate from beta to GA.
---
brand-archetype-system
When your agent uses it
Apply pre-composed aesthetic archetype defaults to jumpstart brand design work covering color, typography, layout, voice, and imagery direction. Use this skill whenever the user wants a starting point for brand visual and verbal direction, references a brand they want to design near (for example 'something like Stripe' or 'editorial like Linear'), needs to converge faster from many directions to one, or wants known-good defaults for a specific industry vertical. Triggers on archetype, design archetype, brand archetype, near to (brand), in the style of, similar aesthetic, design starting point, brand template, vertical-typical, industry-typical. Also triggers when the user has a brief and wants to map it to a known aesthetic family rather than design from first principles.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
32,809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: 12 core archetypes plus 18 vertical applications
- The 12 core archetypes
- The 18 vertical applications
- Trademark and attribution
- The four creative-direction axes (reference)
- Reference files
Files
README.mddoc363 bytesSKILL.mdcore7,664 bytesreferences/00-archetype-system-overview.mddoc3,231 bytesreferences/01-how-to-apply-an-archetype.mddoc3,898 bytesreferences/by-vertical/01-b2b-saas-developer-tools.mddoc3,609 bytesreferences/by-vertical/02-b2b-saas-business-productivity.mddoc3,547 bytesreferences/by-vertical/03-b2b-saas-marketing-sales.mddoc3,408 bytesreferences/by-vertical/04-b2b-saas-data-analytics.mddoc3,255 bytesreferences/by-vertical/05-fintech-consumer.mddoc3,264 bytesreferences/by-vertical/06-fintech-enterprise.mddoc3,438 bytesreferences/by-vertical/07-dtc-fashion.mddoc3,520 bytesreferences/by-vertical/08-dtc-beauty.mddoc3,447 bytesreferences/by-vertical/09-dtc-home-lifestyle.mddoc3,493 bytesreferences/by-vertical/10-dtc-food-beverage.mddoc3,513 bytesreferences/by-vertical/11-consumer-health-wellness.mddoc3,502 bytesreferences/by-vertical/12-hospitality-travel.mddoc3,308 bytesreferences/by-vertical/13-media-publishing.mddoc3,279 bytesreferences/by-vertical/14-edtech.mddoc3,608 bytesreferences/by-vertical/15-gaming-entertainment.mddoc3,438 bytesreferences/by-vertical/16-marketplace.mddoc3,474 bytesreferences/by-vertical/17-crypto-web3.mddoc3,443 bytesreferences/by-vertical/18-real-estate-proptech.mddoc3,648 bytesreferences/core-archetypes/01-editorial-restrained.mddoc6,292 bytesreferences/core-archetypes/02-technical-precise.mddoc6,632 bytesreferences/core-archetypes/03-warm-conversational.mddoc6,988 bytesreferences/core-archetypes/04-bold-confident.mddoc6,347 bytesreferences/core-archetypes/05-playful-energetic.mddoc6,623 bytesreferences/core-archetypes/06-luxe-considered.mddoc6,956 bytesreferences/core-archetypes/07-clinical-trustworthy.mddoc7,397 bytesreferences/core-archetypes/08-rugged-utilitarian.mddoc6,933 bytesreferences/core-archetypes/09-retro-nostalgic.mddoc7,336 bytesreferences/core-archetypes/10-minimal-essentialist.mddoc6,995 bytesreferences/core-archetypes/11-vibrant-saturated.mddoc6,758 bytesreferences/core-archetypes/12-documentary-honest.mddoc7,119 bytes
Read SKILL.md
# Brand Archetype System
Pre-composed aesthetic archetype defaults that jumpstart brand design work. Each archetype bundles color tendencies, type pairings, layout patterns, voice samples, and imagery direction for a recognizable aesthetic family. Stack-agnostic. Tool-agnostic.
This is a starting-point library, not a methodology library. The agent applies archetype defaults to a specific brief; the archetypes themselves provide anchor points, not endpoints.
---
## When to use
- The user wants a starting point rather than designing from first principles
- The user references a brand or aesthetic family they want to design near
- Need to converge faster from many directions to one
- The user wants vertical-typical defaults (for example fintech consumer, B2B developer tools)brand-discovery
When your agent uses it
Run upstream brand discovery covering audience research, competitive landscape, category dynamics, problem space, and positioning territory exploration. Use this skill at the very start of a brand or website project when the user needs to understand who they're for, who they compete with, what the audience actually needs, and where the brand could plausibly stand. Triggers on brand discovery, audience research, market research, competitive scan, category research, customer research, who is this for, who are we, positioning research, intake, kickoff. Also triggers when a creative brief is requested but the upstream inputs (audience, competitors, problem space) are not yet clear.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
2,088 tokensWhen the skill is activated
Reference documents
2,639 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc356 bytesSKILL.mdcore9,702 bytesSKILL.mdcore9,702 bytesreferences/discovery-report-template.mddoc4,597 bytesreferences/interview-guide.mddoc6,923 bytes
Read SKILL.md
# Brand Discovery
Upstream of every brief, identity, and content plan. Discovery answers four questions: who the brand is for, what they need, who else is competing for that need, and where the brand could plausibly stand that competitors do not.
---
## When to use
- The very first phase of a new brand or website project
- Understanding an audience before any creative work begins
- Mapping competitors and category dynamics
- Surfacing the problem space the brand will operate in
- Generating positioning territories before brief or ideation
- When a creative brief was requested but the inputs are missingbrand-ideation
When your agent uses it
Generate, evaluate, and narrow brand concepts during early ideation including positioning territories, naming candidates, mood directions, and narrative angles. Use this skill whenever the user is in the early phase of brand creation, exploring brand directions, brainstorming names, building moodboards, generating positioning options, or trying to choose between multiple brand directions. Triggers on brand ideation, brand concept, naming, brand name, name candidates, positioning, brand positioning, mood board, brand directions, exploring brands, early brand work, brand exploration, brand brainstorm, brand options. Also triggers when the user has multiple half-formed brand ideas and needs help converging on one, even if they do not say 'ideation' explicitly.
What it loads into context
Frontmatter
176 tokensAlways available to the agent
SKILL.md
2,205 tokensWhen the skill is activated
Reference documents
2,831 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc355 bytesSKILL.mdcore9,612 bytesSKILL.mdcore9,612 bytesreferences/ideation-output-template.mddoc4,755 bytesreferences/naming-evaluation-rubric.mddoc6,497 bytes
Read SKILL.md
# Brand Ideation
Generate and converge on brand directions before committing to identity work. This is upstream of `brand-identity` (the visual system) and `brand-style-guide` (the documentation). It is the divergent-then-convergent thinking phase where ideas are cheap and direction matters more than polish.
---
## When to use
- Generating naming options for a new brand or product
- Exploring positioning territories before committing
- Building moodboards and visual direction options
- Drafting narrative or origin-story angles
- Helping the user converge from many half-ideas to one direction
- Stress-testing an existing brand idea before investing in identity workbrand-identity
When your agent uses it
Design or evaluate a brand visual identity system covering logo, color, typography, imagery direction, iconography, and motion principles. Use this skill whenever the user wants to design a logo, build a visual identity, define brand colors, choose brand typography, develop iconography, plan brand imagery, or evaluate an existing identity for cohesion. Triggers on logo design, brand identity, visual identity, brand mark, wordmark, monogram, color palette, brand colors, brand typography, type system, iconography, brand imagery, motion design, brand system, identity system. Also triggers when the user has a brand direction approved and now needs the visual artifacts that express it.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
2,393 tokensWhen the skill is activated
Reference documents
3,506 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 elements
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc355 bytesSKILL.mdcore10,632 bytesSKILL.mdcore10,632 bytesSKILL.mdcore10,632 bytesreferences/contrast-and-accessibility.mddoc6,761 bytesreferences/identity-system-spec.mddoc6,266 bytes
Read SKILL.md
# Brand Identity
Design or evaluate the visual artifacts that express a brand: logo system, color, typography, imagery, iconography, and motion. Stack-agnostic. Tool-agnostic.
This skill assumes a brand direction is already approved (positioning, mood, name). If not, run `brand-ideation` first.
---
## When to use
- Designing a logo system
- Defining a brand color palette
- Choosing brand typography
- Developing iconography or illustration stylebrand-style-guide
When your agent uses it
Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style guide for completeness, or produce the artifact that other teams will reference for years. Triggers on style guide, brand guidelines, brand book, brand standards, brand manual, style sheet, brand documentation, brand reference. Also triggers when the brand identity is finished and needs to be documented for handoff to designers, developers, vendors, or future team members.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,866 tokensWhen the skill is activated
Reference documents
3,988 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 8 sections
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesreferences/maintenance-playbook.mddoc7,873 bytesreferences/style-guide-template.mddoc7,669 bytes
Read SKILL.md
# Brand Style Guide
Document the brand system so other people can use it without ambiguity. This is the artifact that lives longest. Designers, developers, agencies, and vendors will reference it for years. Build it like a reference manual, not a presentation.
This skill assumes the brand identity is designed (run `brand-identity` first if not). The output of this skill is the canonical reference document.
---
## When to use
- Creating brand guidelines for a finished identity
- Documenting an existing brand that has no formal guide
- Auditing an existing style guide for gaps or inconsistencies
- Building a brand book to hand to vendors, partners, or new team membersbrand-voice
When your agent uses it
Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
1,993 tokensWhen the skill is activated
Reference documents
3,531 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc1,085 bytesSKILL.mdcore8,904 bytesreferences/voice-document-template.mddoc5,656 bytesreferences/voice-frameworks.mddoc7,630 bytes
Read SKILL.md
# Brand Voice
Define how a brand sounds in writing. Document it in a way that anyone (writer, designer, founder, AI assistant) can apply it consistently.
This skill produces a standalone voice document that can either live in the brand style guide or feed into it.
---
## When to use
- Defining brand voice for the first time
- Auditing existing copy for voice consistency
- Training a team, freelancer, or AI assistant on the brand voice
- Refining a voice that exists but is inconsistent across applicationscalculator-design
When your agent uses it
Designing interactive calculators (ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments) that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. Honest about vanity-calculator (no real value), lead-trap (hides the answer behind email), and transparent-decision-tool (gives the result and earns the email through tiered value) patterns. Triggers on calculator, ROI calculator, pricing estimator, savings calculator, custom calculator, interactive tool, decision tool, financial calculator. Also triggers when an audience needs a calculation-driven lead magnet, when a vanity calculator is producing leads but no qualified ones, or when a calculator is being scoped for the first time.
What it loads into context
Frontmatter
215 tokensAlways available to the agent
SKILL.md
4,787 tokensWhen the skill is activated
Reference documents
19,557 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The calculator decision: when calculators earn investment
- Vanity-calculator vs lead-trap vs transparent-decision-tool
- Input design
- Calculation logic transparency
- Result presentation
- Email-capture decision
- Tiered-value structures
- Calculator anti-patterns
- Common failure modes
- The framework: 12 considerations for calculator design
- If required data is unavailable
- Reference files
- Closing: calculators earn the email when they would have been worth paying for
Files
README.mddoc358 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesSKILL.mdcore23,782 bytesreferences/calculation-logic-transparency.mddoc11,693 bytesreferences/calculator-anti-patterns.mddoc10,366 bytesreferences/calculator-investment-criteria.mddoc10,002 bytesreferences/common-calculator-failures.mddoc9,313 bytesreferences/email-capture-decision-tree.mddoc10,868 bytesreferences/input-design-patterns.mddoc10,986 bytesreferences/methodology-disclosure-templates.mddoc10,700 bytesreferences/result-presentation-patterns.mddoc10,900 bytesreferences/tiered-value-structures.mddoc10,560 bytes
Read SKILL.md
# Calculator Design
A senior growth practitioner's playbook for designing interactive calculators that deliver real decision-support value while serving as lead magnets and qualified-traffic generators. ROI calculators, pricing estimators, savings projections, mortgage calculators, custom assessments. The discipline of building a tool the audience actually trusts.
Most calculators on the web are bait. Random multipliers behind official-looking math; an "Industry Average" number that does not cite a source; the result hidden behind a contact-sales form. The calculator captures emails because the format implies calculation; the leads are unqualified because the calculator did not actually help anyone decide anything.
The calculators that work as compounding assets do something different. They give the audience a result they can defend to a stakeholder. They show the methodology so the result is interrogatable. They capture leads through value (a PDF report, a save-and-compare account, a custom analysis) rather than through manipulation.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the calculator-specific methodology (calculation transparency, tiered value, methodology disclosure) lives here.
The voice is the senior growth practitioner who has watched calculators earn long-term credibility and watched them burn it within weeks of launch. Practical, opinionated about transparency, willing to say when a calculator is the wrong investment for the goal.
When to use this skill: scoping a calculator for the first time, auditing a calculator that converts but does not qualify, designing the methodology disclosure that earns audience trust, or deciding which features warrant the email gate.
chatbot-flow-design
When your agent uses it
Designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. Honest about scripted-bot (rigid trees, fail edge cases), hallucinating-bot (LLM without structure, makes things up), and structured-guided-conversation (LLM-powered with intent architecture and fallback discipline) patterns. Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION (engineering and platform work). Triggers on chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding. Also triggers when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time.
What it loads into context
Frontmatter
236 tokensAlways available to the agent
SKILL.md
4,164 tokensWhen the skill is activated
Reference documents
17,582 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The chatbot decision: when chatbots earn deployment
- Scripted-bot vs hallucinating-bot vs structured-guided-conversation
- Intent architecture
- Knowledge-base grounding
- Branching and conditional logic
- Fallback patterns
- Escalation to human
- Conversation analytics
- Common failure modes
- The framework: 12 considerations for chatbot flow design
- Reference files
- Closing: chatbots earn deployment when they know what they don't know
Files
README.mddoc360 bytesSKILL.mdcore20,622 bytesSKILL.mdcore20,622 bytesreferences/branching-and-conditional-logic.mddoc9,490 bytesreferences/chatbot-anti-patterns.mddoc9,772 bytesreferences/chatbot-decision-criteria.mddoc9,562 bytesreferences/common-chatbot-failures.mddoc8,438 bytesreferences/conversation-analytics-patterns.mddoc10,047 bytesreferences/escalation-to-human-patterns.mddoc9,193 bytesreferences/fallback-pattern-design.mddoc9,859 bytesreferences/intent-architecture-patterns.mddoc10,376 bytesreferences/knowledge-base-grounding-patterns.mddoc10,778 bytes
Read SKILL.md
# Chatbot Flow Design
A senior growth practitioner's playbook for designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. The discipline of building a bot that knows what it knows and routes appropriately when it does not.
Most chatbots on the web fail in one of two ways. Scripted bots break the moment a user phrases something the script did not anticipate; the user gets pushed through a decision tree that does not fit their situation. LLM-powered bots without structure hallucinate; they confidently answer questions about pricing, policy, or capabilities and frequently make up answers, creating support burden and trust damage.
The chatbots that work do something different. They have an intent architecture that defines what the bot can and cannot handle. They ground their responses in a knowledge base so they do not invent facts. They have explicit fallback paths for unclear or out-of-scope intents. They escalate to humans cleanly when the bot's job is done. The audience trusts the bot because the bot is honest about its scope.
The voice is the senior growth practitioner who has watched chatbots become trusted brand surfaces and watched them become liability risks. Practical, opinionated about the architecture that distinguishes the two outcomes, willing to call out when a chatbot is the wrong investment or when an existing chatbot needs to be redesigned rather than tuned.
When to use this skill: scoping a chatbot for the first time, auditing a chatbot that hallucinates or fails edge cases, designing the intent architecture and fallback patterns, or deciding when to escalate to humans.
---
code-review-web
When your agent uses it
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
2,322 tokensWhen the skill is activated
Reference documents
5,182 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 review dimensions
- Common bug patterns (stack-agnostic)
- Workflow
- Failure patterns
- Debugging workflow
- Output format
- Reference files
Files
README.mddoc1,444 bytesSKILL.mdcore10,703 bytesreferences/nextjs-patterns.mddoc8,960 bytesreferences/review-template.mddoc3,090 bytesreferences/wordpress-headless-patterns.mddoc8,259 bytes
Read SKILL.md
# Code Review for Web
Review and debug web application code with a focus on the patterns that actually break production. Stack-agnostic principles in SKILL.md. Stack-specific patterns in references.
---
## When to use
- Reviewing a pull request before merging
- Debugging a production issue
- Investigating a build failure
- Auditing security or performance of existing code
- Investigating environment variable or configuration issues
- Triaging a "the site is broken" reportcomparison-tool-design
When your agent uses it
Designing side-by-side comparison tools (plan-compare, product-compare, alternative-compare) that help users decide rather than just listing features. Axis selection, default-comparison logic, recommendation discipline. Honest about feature-list-dump (every feature in a row, no decision support), hidden-recommendation (biased comparison pretending to be neutral), and honest-comparison-with-guidance (genuine comparison plus opinionated recommendation) patterns. Triggers on comparison tool, plan compare, product compare, alternative compare, vs page, decision support tool. Also triggers when conversion through comparison stages is poor, when users are abandoning at the comparison step, or when a comparison tool is being scoped for the first time.
What it loads into context
Frontmatter
222 tokensAlways available to the agent
SKILL.md
3,355 tokensWhen the skill is activated
Reference documents
10,268 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The comparison-tool decision: when comparison tools earn investment
- Feature-list-dump vs hidden-recommendation vs honest-comparison-with-guidance
- Axis selection: which dimensions matter, which are noise
- Default-comparison logic
- Recommendation engine design
- Filter and toggle UX
- Comparison-fatigue patterns
- Common failure modes
- The framework: 12 considerations for comparison tool design
- If required data is unavailable
- Reference files
- Closing: comparison tools earn the choice when they earn the user's trust
Files
README.mddoc363 bytesSKILL.mdcore16,793 bytesSKILL.mdcore16,793 bytesreferences/axis-selection-patterns.mddoc4,706 bytesreferences/common-comparison-failures.mddoc5,720 bytesreferences/comparison-anti-patterns.mddoc5,991 bytesreferences/comparison-fatigue-patterns.mddoc5,906 bytesreferences/comparison-tool-decision-criteria.mddoc4,643 bytesreferences/default-comparison-logic.mddoc5,752 bytesreferences/filter-and-toggle-patterns.mddoc6,237 bytesreferences/honest-recommendation-discipline.mddoc6,823 bytesreferences/recommendation-engine-design.mddoc5,157 bytes
Read SKILL.md
# Comparison Tool Design
A senior product marketing director's playbook for designing side-by-side comparison tools that help users decide rather than just listing features. Plan-compare, product-compare, alternative-compare. Axis selection, default-comparison logic, recommendation discipline. The discipline of building a comparison tool that earns the user's trust.
Most comparison tools fail in one of two ways. They dump every feature into a giant grid (4 options × 40 features = 160 cells) and ask the user to weigh everything against everything. The user leaves without choosing. Or they pretend to be neutral comparisons but are actually sales pitches with biased defaults and weighted framing; the user catches the bias and trust collapses.
The comparison tools that work do something different. Genuine like-for-like comparison plus an explicit opinionated recommendation. "For X audience, choose Y." The recommendation is visible, defended, and not the only path; users can override. The tool helps the user decide rather than asking them to decide alone.
The voice is the senior product marketing director who has watched comparison tools double conversion when redesigned with honest recommendations and watched them collapse when feature grids grew without decision support. Practical, opinionated about which axes matter, willing to call out when the comparison is decoration.
When to use this skill: scoping a comparison tool for the first time, auditing a feature-grid comparison that produces no conversion lift, designing recommendation logic that is honest about the recommendation, or deciding which axes earn placement in a comparison tool.
---
competitor-experience-audit
When your agent uses it
Audit the brand, UX, and site design of the leading sites in a vertical as a set of observable cross-site patterns, producing the experience bar a new build must meet or beat. Use this skill whenever the user wants to assess the competitive design field, capture vertical conventions, identify the design and UX bar of a category, or set the experience standard before a build. Triggers on competitor experience audit, UX audit, site design audit, brand audit, design conventions, what makes these sites good, vertical conventions, storefront patterns, merchandising patterns, layout density, primary task, design bar, category conventions, retail vs marketing register, what does the field do. Also triggers when an audit of the competitive field has captured technical signals (SEO, accessibility) but never named the brand, UX, or design conventions, and the build downstream will read as off-vertical without that bar.
What it loads into context
Frontmatter
210 tokensAlways available to the agent
SKILL.md
3,052 tokensWhen the skill is activated
Reference documents
2,781 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 experience dimensions
- The honesty guardrail (load-bearing)
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc368 bytesSKILL.mdcore14,437 bytesreferences/audit-template.mddoc4,750 bytesreferences/experience-dimensions-checklist.mddoc7,203 bytes
Read SKILL.md
# Competitor Experience Audit
Capture the brand, UX, and site design that the leading sites in a vertical observably share, and where they fall short. The output is the experience bar a new build must meet or beat, grounded in cross-site patterns rather than aesthetic opinion.
Stack-agnostic. Works on any SiteShape (ecommerce-catalog, inventory-listing, hospitality-food, b2b-manufacturer, and so on). Auto-parts catalogs are the first test case, not the only target.
This skill is the brand / UX / design counterpart to a technical audit like `seo-onpage` or `accessibility-audit`. Technical findings are objective (a missing canonical is missing). Design is more subjective, so this skill is deliberately written to make the subjective assessable: every dimension is judged by observable questions about what the leading sites actually do, reported as patterns and gaps, and marked `not_assessable` whenever the evidence does not support a judgment.
---
## When to use
- Setting the experience bar for a new build in a vertical you have not built in before
- Capturing the design and UX conventions a credible site in the category is expected to carrycontent-and-copy
When your agent uses it
Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog post, draft an article, write copy for, edit this, rewrite this, write content, write a guide, draft a how-to, write web copy. Also triggers when content has been outlined and now needs to be written, or when existing content needs voice or clarity edits.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
1,892 tokensWhen the skill is activated
Reference documents
3,630 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc357 bytesSKILL.mdcore8,236 bytesreferences/content-brief-template.mddoc7,426 bytesreferences/content-edit-checklist.mddoc7,284 bytes
Read SKILL.md
# Content and Copy
Write or edit content that serves a specific reader and goal. Stack-agnostic. This skill is for general content production. Specialized skills exist for landing pages (`landing-page-copy`) and email (`email-sequences`).
---
## When to use
- Writing a blog post or article
- Drafting website copy (homepage sections, about, services)
- Editing existing content for voice or clarity
- Writing how-to guides, listicles, or explainers
- Producing knowledge base or help center articles
- Adapting brand voice to a specific piececontent-brief-authoring
When your agent uses it
How to author a content brief that actually guides a writer (human or AI) to produce a piece that ranks, converts, or both. Per-piece editorial brief: target keyword and cluster, search intent, audience and JTBD, heading structure, entity coverage for AEO/GEO, internal linking strategy, success criteria. The middle path between thin briefs (a keyword and a deadline) and thick briefs (a 4-page document nobody reads). Triggers on content brief, brief the writer, brief the article, brief authoring, content brief template, brief audit, per-piece brief, editorial brief, target keyword brief, search intent brief. Also triggers when briefing a human writer or an AI agent on a single content piece.
What it loads into context
Frontmatter
204 tokensAlways available to the agent
SKILL.md
4,885 tokensWhen the skill is activated
Reference documents
11,172 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Thin vs thick vs effective briefs
- The 12 fields of an effective brief
- Search intent classification
- Heading structure design
- Entity coverage for AEO and GEO
- Internal linking strategy
- Brief templates by content type
- The brief-to-writer handoff
- Brief governance
- Common failure modes
- The framework: 12 considerations for brief authoring
- If required data is unavailable
- Reference files
- Closing: the brief is the contract
Files
README.mddoc364 bytesSKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesSKILL.mdcore22,534 bytesreferences/brief-governance-patterns.mddoc6,083 bytesreferences/brief-templates.mddoc7,826 bytesreferences/common-brief-failures.mddoc7,803 bytesreferences/entity-coverage-checklist.mddoc5,700 bytesreferences/heading-structure-patterns.mddoc5,438 bytesreferences/internal-linking-strategy.mddoc5,650 bytesreferences/search-intent-classification.mddoc4,799 bytesreferences/writer-handoff-protocols.mddoc6,094 bytes
Read SKILL.md
# Content Brief Authoring
A senior content strategist's playbook for authoring per-piece content briefs that actually guide writers to produce content worth publishing.
Most content briefs are some flavor of broken. The thin version is a keyword, a word count, and a deadline; the writer fills in everything else from scratch and the output is generic. The thick version is a 4-page document nobody reads, that the writer skims for the headline and the outline and ignores the rest. Either way, the brief failed at its job: making the writer's work easier and the output more predictable.
This skill is the middle path. It defines the 12 fields that earn their keep in a content brief, the fields that bloat without helping, and the discipline of writing briefs that route a writer (human or AI) toward a content piece that ranks for its target keyword, gets cited by AI engines, converts the right reader, or whatever the success criteria say. It assumes you have decided what to write (see `content-strategy` for program-level decisions) and now you are briefing each piece. The piece itself gets written separately (see `content-and-copy`).
When to use this skill: briefing a writer (human or AI) on an individual content piece, auditing existing briefs that are not producing good content, building a brief template for a content program, or running a brief-generation pipeline through Frase, AirOps, or another tool.
---
## What this skill is for
content-distribution
When your agent uses it
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel matching, distribution cadence. Triggers on content distribution, channel strategy for content, owned earned paid channels, content amplification, content promotion, audience-channel matching, content-channel matching, distribution cadence, syndication strategy, organic distribution. Also triggers when content is publishing but reach is low, when the team is distributing on every channel without strategy, or when the content program needs a distribution discipline rather than just publication.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
5,032 tokensWhen the skill is activated
Reference documents
19,003 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hope-and-pray vs spam-everywhere vs channel-fit
- Channel taxonomy
- Audience-channel matching
- Content-channel matching
- Distribution cadence
- Owned-channel discipline
- Earned-channel work
- Paid promotion of organic content
- Distribution measurement
- Common failure modes
- The framework: 12 considerations for content distribution
- If required data is unavailable
- Reference files
- Closing: distribution is half the work
Files
README.mddoc361 bytesSKILL.mdcore25,964 bytesSKILL.mdcore25,964 bytesreferences/audience-channel-matching.mddoc10,402 bytesreferences/channel-taxonomy.mddoc13,084 bytesreferences/common-distribution-failures.mddoc11,960 bytesreferences/content-channel-matching.mddoc9,399 bytesreferences/distribution-cadence-patterns.mddoc10,644 bytesreferences/distribution-measurement.mddoc11,013 bytesreferences/earned-channel-work.mddoc11,074 bytesreferences/owned-channel-discipline.mddoc11,261 bytesreferences/paid-promotion-patterns.mddoc11,630 bytes
Read SKILL.md
# Content Distribution
A senior editorial leader's playbook for content distribution as a discipline. Owned, earned, and paid channels matched to audience and content type, with the channel-fit decisions that distinguish strategic distribution from spam-everywhere or hope-and-pray.
Content distribution is half the work and gets a fraction of the attention. Most programs spend 90% of capacity on production and 10% on distribution; the resulting ratio of effort-to-reach is consistently poor. The teams producing content that reaches audiences are the ones who treat distribution as a real discipline: channels chosen for fit, cadence calibrated to audience attention, owned-earned-paid balance set by program strategy, and effectiveness measured per channel.
This skill is the channel discipline. Different from `content-repurposing` (which turns one piece into many formats), this skill is about getting content TO audiences via the right channels. The two skills compose: repurpose first, then distribute the right format on the right channel.
The voice is the senior editorial leader who has watched programs underperform because distribution was treated as posting-after-publishing rather than as the equal half of the work.
When to use this skill: building a distribution discipline for a content program, auditing why content publishes consistently but reach is low, calibrating owned-earned-paid balance, designing channel-fit decisions for a multi-format program.
---
content-migration
When your agent uses it
Move content between platforms, domains, or URL structures while preserving SEO equity, user bookmarks, and integrations. Use this skill when planning a CMS migration, replatforming, consolidating sites, changing URL structures, or merging content from multiple sources. Triggers on content migration, replatform, CMS migration, domain migration, URL restructure, redirect map, site merge, content consolidation, migration plan, post-migration drop. Also triggers when planning a launch that involves moving existing content.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
2,447 tokensWhen the skill is activated
Reference documents
2,304 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesSKILL.mdcore10,851 bytesreferences/migration-runbook.mddoc9,515 bytes
Read SKILL.md
# Content Migration
Move content from one platform, domain, or URL structure to another without breaking SEO, user bookmarks, or downstream integrations. Stack-agnostic.
---
## When to use
- Migrating from one CMS to another (e.g., WordPress to a headless setup)
- Consolidating multiple sites into one
- Splitting one site into multiple
- Changing URL structures
- Domain migration (one brand to another, mergers, rebrands)
- Migrating from a custom build to a platform (or vice versa)content-refresh-system
When your agent uses it
Systematic content refresh discipline. Quarterly audits, refresh prioritization (which pieces, when, how deep), refresh-vs-merge-vs-delete decisions, the lifecycle that distinguishes intentional refresh from set-and-forget decay. Builds on the refresh sections of pillar-content-architecture and editorial-qa with a program-level discipline. Triggers on content refresh, content decay, content audit, refresh prioritization, content lifecycle, refresh strategy, traffic decay, ranking drop, content freshness, evergreen content, content maintenance. Also triggers when traffic is eroding silently across an aging content library, when teams cannot decide which pieces to refresh, or when refresh work is happening but the impact is unclear.
What it loads into context
Frontmatter
194 tokensAlways available to the agent
SKILL.md
5,210 tokensWhen the skill is activated
Reference documents
19,245 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Refresh-everything vs refresh-nothing vs triaged-refresh
- Refresh signals
- The audit cadence
- Refresh prioritization
- Refresh depth options
- Refresh vs merge vs delete decisions
- Refresh execution patterns
- Re-promotion after refresh
- Refresh tracking and effectiveness measurement
- Common failure modes
- The framework: 12 considerations for content refresh
- If required data is unavailable
- Reference files
- Closing: refresh is content's immune system
Files
README.mddoc363 bytesSKILL.mdcore25,907 bytesSKILL.mdcore25,907 bytesreferences/audit-cadence-patterns.mddoc10,396 bytesreferences/common-refresh-failures.mddoc11,774 bytesreferences/effectiveness-measurement.mddoc11,055 bytesreferences/re-promotion-after-refresh.mddoc10,690 bytesreferences/refresh-depth-decision.mddoc10,655 bytesreferences/refresh-execution-patterns.mddoc10,036 bytesreferences/refresh-prioritization-matrix.mddoc11,361 bytesreferences/refresh-signals-checklist.mddoc10,605 bytesreferences/refresh-vs-merge-vs-delete.mddoc10,295 bytes
Read SKILL.md
# Content Refresh System
A senior editorial leader's playbook for systematic content refresh. The discipline that distinguishes intentional refresh programs from set-and-forget decay, and the prioritization framework that prevents both over-refresh (refresh-everything-on-calendar) and under-refresh (refresh-nothing-until-traffic-collapses).
Content decays. Search behavior shifts; SERP intent reshapes; facts go stale; competitors publish stronger pieces; the brand's own positioning evolves past what older pieces represent. Programs that ignore this reality watch traffic erode silently across the library. Programs that overreact (rewriting everything on calendar) burn editorial capacity that should be producing new flagship work. The discipline is in the middle: refresh what matters when signals say so, and document the decisions so the program is auditable.
This skill is the program-level refresh discipline across the whole content library. It builds on `pillar-content-architecture`'s hub-level refresh consideration (refresh as ONE consideration in hub design) and `editorial-qa`'s pre-publish quality gate (this skill is post-publish lifecycle, not pre-publish QA). Together those skills cover content quality at the moments quality decisions get made; this skill covers the moments between, when content is in the field and decaying or holding.
The voice is the senior editorial leader who has watched refresh programs fail in both directions and who has shipped the systems that produced durable refresh discipline.
When to use this skill: building a refresh program from scratch, auditing why refresh work is happening but traffic is not responding, designing the prioritization that keeps refresh tractable across a 200-piece or 2,000-piece library, or fixing a refresh program that is eating editorial capacity without clear results.
---
content-repurposing
When your agent uses it
Cross-format content adaptation. Turning one substantial piece into many derivative formats (blog series, email sequences, social posts, webinars, podcasts, video shorts) without losing the original's value or producing AI-slop variants. The discipline of adaptation per medium rather than mass-blast distribution. Triggers on content repurposing, content adaptation, cross-format content, content atomization, content multiplication, content distribution across formats, source-piece-to-derivative, video shorts from blog, email from whitepaper, podcast from article, blog series from research. Also triggers when a flagship piece is shipping but the team has not planned how to extend it across formats, when repurposing is happening but the derivatives feel mass-produced, or when AI-assisted repurposing is producing slop variants of strong source pieces.
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
4,928 tokensWhen the skill is activated
Reference documents
20,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- One-and-done vs mass-blast vs adapt-by-format
- Source-piece selection
- Format adaptation patterns
- Per-format constraints
- Voice consistency across formats
- Sequencing and cadence
- Cross-promotion across derivatives
- Repurposing for AI search visibility
- Common failure modes
- The framework: 12 considerations for content repurposing
- If required data is unavailable
- Reference files
- Closing: adaptation is craft, not duplication
Files
README.mddoc360 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesSKILL.mdcore24,284 bytesreferences/aeo-extraction-patterns.mddoc10,691 bytesreferences/common-repurposing-failures.mddoc10,731 bytesreferences/cross-promotion-patterns.mddoc9,690 bytesreferences/format-adaptation-patterns.mddoc13,696 bytesreferences/per-format-constraints.mddoc10,774 bytesreferences/repurposing-pipeline-templates.mddoc11,655 bytesreferences/sequencing-and-cadence-patterns.mddoc11,444 bytesreferences/source-piece-selection-criteria.mddoc11,167 bytesreferences/voice-consistency-across-formats.mddoc10,950 bytes
Read SKILL.md
# Content Repurposing
A senior editorial leader's playbook for cross-format content adaptation. The discipline of turning one substantial piece into many derivative formats without losing the original's value or producing slop variants.
Most content programs underspend on repurposing. A flagship piece costs 40-80 hours to produce; the program publishes it once, shares it on three channels, and moves on. The same piece could have produced a blog series, an email sequence, a webinar, a podcast episode, a dozen social posts, video shorts, and FAQ extractions for AI search visibility. The work to extend the source piece across formats is small relative to the value extracted; programs that skip repurposing leave most of the value unrealized.
The failure mode in the other direction is mass-blast: the same content reposted across channels without adaptation. A blog post pasted into LinkedIn as a long-text post; the email newsletter is the blog's first three paragraphs with "read more" tacked on; the YouTube video is a slideshow of the article text read aloud. Mass-blast respects neither the medium nor the audience. AI-assisted repurposing has made mass-blast cheap; the result is a wave of derivative content that performs poorly across every channel because it was adapted to none of them.
This skill is the discipline of adaptation per medium. Each format has constraints, conventions, and reader expectations the source piece does not have. Repurposing that respects those constraints produces work that earns engagement on the new format; repurposing that ignores them produces filler.
When to use this skill: planning the extension of a flagship piece across formats, auditing a repurposing pipeline that is producing low-engagement derivatives, calibrating an AI-assisted repurposing workflow that is producing slop, or designing the cross-format adaptation conventions for a content program.
---
content-strategy
When your agent uses it
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align content production with broader brand and SEO goals. Triggers on content strategy, content plan, editorial strategy, content pillars, content calendar, editorial calendar, topical authority, topic clusters, content governance, content roadmap, content production. Also triggers when the user is about to start producing content without a strategic plan.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
2,301 tokensWhen the skill is activated
Reference documents
3,584 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc357 bytesSKILL.mdcore10,530 bytesSKILL.mdcore10,530 bytesreferences/content-strategy-template.mddoc6,745 bytesreferences/editorial-calendar-template.mddoc7,906 bytes
Read SKILL.md
# Content Strategy
Plan what content to produce, why, when, and how. Stack-agnostic. Works for blogs, knowledge bases, marketing sites, newsletters, and product content surfaces.
This skill is the strategic layer. Tactical execution sits in `content-and-copy`, `landing-page-copy`, and `email-sequences`. SEO-driven content planning sits in `seo-keyword`. This skill stitches those together into a coherent program.
---
## When to use
- Planning a new content program or relaunching an existing one
- Defining editorial positioning and content pillars
- Building an editorial calendar
- Structuring topic clusters and content hubscost-optimization
When your agent uses it
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
2,658 tokensWhen the skill is activated
Reference documents
2,090 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 levers
- Workflow
- Common opportunities by category
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesSKILL.mdcore12,217 bytesreferences/cloud-audit-checklist.mddoc8,556 bytes
Read SKILL.md
# Cost Optimization
Audit cloud, SaaS, and infrastructure spend. Cut what's not earning its keep. Rightsize what's oversized. Negotiate what's negotiable. Without breaking what works.
---
## When to use
- Quarterly or annual cost review
- Finance flags rising spend
- Vendor contract renewal coming up
- Budget cut required
- New leadership wants the numbers
- Migrating between providers (cost is part of the case)creative-brief
When your agent uses it
Create or refine a creative brief that bridges discovery and execution. Use this skill whenever the user is starting a new project, kicking off a website, beginning a brand build or redesign, briefing a designer or developer or AI agent, or trying to align a team before building. Triggers on creative brief, design brief, brand brief, project kickoff, kicking off, briefing the team, project intake, design direction, brief the designer, brief the dev, where do we start, how do we start, write a brief, project overview, scope this project, align on direction. Also triggers when the user has a vague idea and needs to make it concrete enough to hand off, even if they do not say 'brief' explicitly.
What it loads into context
Frontmatter
180 tokensAlways available to the agent
SKILL.md
1,897 tokensWhen the skill is activated
Reference documents
4,680 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: brief structure
- Eliciting missing info
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc355 bytesSKILL.mdcore8,293 bytesreferences/creative-brief-template.mddoc3,956 bytesreferences/example-brief.mddoc7,985 bytesreferences/voice-and-tone-guide.mddoc6,978 bytes
Read SKILL.md
# Creative Brief
Bridges discovery and execution. Translates "we want a website" into a brief a designer, developer, or AI agent can actually run with.
---
## When to use
- Starting a new project (website, app, brand, campaign)
- Kicking off a redesign or rebrand
- Handing work to a designer, developer, or AI agent
- Aligning a team that has drifted off course
- Turning a vague idea into something buildable
creative-brief-selector
When your agent uses it
Produce a creative brief grounded in live reference sites and deliberately distinct from existing demos, for any new brand build. Composes with brand-archetype-system and creative-direction. Use this skill at the start of any brand or microsite build when the result needs to land in a specific aesthetic position and not drift into a default house style. Triggers on creative brief, design brief, build brief, brand direction, where should this brand sit, what should this site look like, reference sites for, archetype for, distinct from our other brands, divergence from prior, not the same as. Also triggers when prior builds have come out as siblings and a systematic divergence approach is needed.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
2,137 tokensWhen the skill is activated
Reference documents
22,997 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- How this composes with other skills
- The framework: five steps, three rules, one hybrid bank
- The hybrid references model
- The divergence schema
- Trademark and attribution
- If required data is unavailable
- Reference files
Files
README.mddoc364 bytesSKILL.mdcore10,044 bytesSKILL.mdcore10,044 bytesreferences/00-overview.mddoc5,349 bytesreferences/01-process.mddoc9,538 bytesreferences/02-brief-template.mddoc8,976 bytesreferences/03-divergence-check.mddoc12,675 bytesreferences/04-shipped-demos-signatures-example.mddoc8,664 bytesreferences/05-section-shapes-vocabulary.mddoc10,893 bytesreferences/reference-bank/README.mddoc7,350 bytesreferences/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.mddoc3,849 bytesreferences/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.mddoc4,837 bytesreferences/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.mddoc3,196 bytesreferences/reference-bank/editorial-restrained-literary-quarterly.mddoc3,606 bytesreferences/reference-bank/heritage-local-service-barbershop.mddoc1,888 bytesreferences/reference-bank/hospitality-experience-balloon-ride.mddoc1,891 bytesreferences/reference-bank/luxe-considered-curated-stays-directory.mddoc6,244 bytesreferences/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.mddoc3,636 bytesreferences/reference-bank/minimal-essentialist-documentary-honest-trades-directory.mddoc6,645 bytesreferences/reference-bank/premium-dtc-maker-western-boots.mddoc1,889 bytesreferences/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.mddoc3,427 bytes
Read SKILL.md
# Creative Brief Selector
A starting-point selector for brand and microsite builds. Given a business spec (name, vertical, shape, one-line vibe, optional list of shipped demos), produces a creative brief grounded in three things:
1. An archetype position from `brand-archetype-system`, picked or composed to be deliberately distinct from the shipped demos.
2. A small set of live reference sites for that archetype-and-vertical combination, drawn from a curated bank plus optional per-build discovery.
3. A divergence check against the shipped demos that flags palette, voice, structural pattern, and section-shape overlap before the brief is handed off.
The brief output is concrete tokens, not abstract families, including explicit section-shape choices (hero shape and footer shape) as first-class outputs alongside palette and voice. It is meant to be loaded by downstream build skills as the single creative artifact for the build.
---
## When to use
creative-direction
When your agent uses it
Walk the user through four directional axes (tone register, aesthetic philosophy, audience relationship, sensory ambition) and produce a structured aesthetic brief that downstream content, copy, design, and art-direction skills consume as required input. The aesthetic depth layer, distinct from `creative-brief` (operational kickoff: scope, audience, deliverables, constraints). Use when a project needs aesthetic coherence across many small decisions and the user has only a vague feeling, or when multiple downstream aesthetic-producing skills need a shared brief. Triggers on creative direction, aesthetic direction, set the aesthetic, define the visual direction, what's the vibe, what's the tone, the four axes. Does NOT fire for a general kickoff brief (use `creative-brief`), tactical single-piece work, already-documented direction, purely functional output, or locked production-stage work.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
2,349 tokensWhen the skill is activated
Reference documents
4,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 directional axes
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc359 bytesSKILL.mdcore11,645 bytesreferences/axes-explained.mddoc12,970 bytesreferences/brief-template.mddoc2,049 bytesreferences/example-aesthetic-brief.mddoc6,306 bytes
Read SKILL.md
# Creative Direction
Frameworks produce competent output. Coherent output requires a brief.
This skill turns vague creative intent into a structured brief that downstream skills can reference. It does not generate taste. It captures direction, so the dozens of small decisions a project requires (word choice, image selection, white space, sequencing, what to leave out) all answer to the same question.
---
> Worked examples for each axis position can be assembled from any reference brand library that documents tone, aesthetic, audience relationship, and sensory ambition consistently. The framework below describes the four axes; the user's own reference set positions each example along the axes during the brief workflow.
---
## When to use
cro-optimization
When your agent uses it
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze test results. Triggers on conversion optimization, CRO, A/B test, split test, multivariate test, hypothesis, conversion funnel, funnel audit, experiment design, statistical significance, lift, optimization. Also triggers when the user has a conversion problem and isn't sure where to start, or when test results are ambiguous and need interpretation.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,411 tokensWhen the skill is activated
Reference documents
2,227 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Statistical foundations
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc357 bytesSKILL.mdcore10,931 bytesSKILL.mdcore10,931 bytesreferences/hypothesis-library.mddoc10,380 bytes
Read SKILL.md
# CRO Optimization
Run conversion rate optimization as a structured discipline: audit → hypothesize → test → decide. Stack-agnostic. Tool-agnostic.
This skill is for running tests against existing pages and flows. For writing landing page copy from scratch, use `landing-page-copy`. For setting up the analytics that make CRO possible, use `analytics-strategy`.
---
## When to use
- Converting traffic at lower rate than expected
- Specific funnel step has high drop-off
- Pages with high traffic that could move the needle if optimized
- A/B testing infrastructure exists (or can be set up)data-warehouse-experimentation
When your agent uses it
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like Statsig and Optimizely. Triggers on warehouse-native experimentation, run experiments in BigQuery, run experiments in Snowflake, dbt experiments, SQL t-test, CUPED variance reduction, exposure log, sample ratio mismatch, sequential testing, mSPRT, doubly robust estimation, build vs buy experimentation. Also triggers when the team is choosing between platform and warehouse, building warehouse-native experiment infrastructure, auditing one, or running an experiment with a custom metric the platform cannot handle.
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
6,083 tokensWhen the skill is activated
Reference documents
15,357 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When warehouse-native is the right call
- The architecture
- Assignment patterns
- The exposure log
- Metric definitions in dbt models
- Statistical analysis in SQL
- Statistical analysis in Python
- Variance reduction: CUPED and beyond
- Pre-experiment power analysis
- Sequential testing patterns
- Common pitfalls
- The framework: 12 considerations for warehouse-native experimentation
- If required data is unavailable
- Reference files
- Closing: the build-vs-buy decision is real
Files
README.mddoc371 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesSKILL.mdcore29,023 bytesreferences/assignment-and-exposure-patterns.mddoc8,125 bytesreferences/common-pitfalls.mddoc10,052 bytesreferences/metric-definitions-in-dbt.mddoc8,099 bytesreferences/power-analysis-calculations.mddoc8,161 bytesreferences/sequential-testing-patterns.mddoc7,762 bytesreferences/statistical-analysis-templates.mddoc7,627 bytesreferences/variance-reduction-techniques.mddoc9,091 bytesreferences/warehouse-vs-platform-decision.mddoc7,976 bytes
Read SKILL.md
# Data Warehouse Experimentation
A senior data scientist's playbook for running experiments natively out of BigQuery, Snowflake, or any modern data warehouse, with metric definitions in dbt and statistical analysis in SQL or Python.
Most companies that run experiments at scale use a dedicated platform. Statsig, Optimizely, LaunchDarkly with experimentation, PostHog, Amplitude Experiment. The platforms are good. They handle assignment, instrumentation, and analysis in one product, and the SQL-savvy data team does not have to reinvent the variance reduction wheel.
There is a different operational model that mature data teams increasingly choose: warehouse-native experimentation. Assignment happens in code or via feature flags. Exposure events fire to the warehouse like any other event. Metrics are defined as dbt models. Statistical analysis runs as SQL or in a Python notebook against warehouse data. The "experiment platform" is just your existing data stack.
This skill covers when warehouse-native is the right call, the architecture, and the specific techniques that make it work: assignment patterns, exposure logging discipline, metric definitions in dbt, t-tests and CUPED in SQL, sequential testing, and the pitfalls that take down homegrown setups.
When to use this skill: deciding between platform vs warehouse-native, building a warehouse-native experiment infrastructure, auditing an existing one, or running a specific experiment when the platform of record cannot handle a custom metric or segmentation.
---
dependency-management
When your agent uses it
Manage third-party libraries, runtimes, and SaaS dependencies. Use this skill when setting an update cadence, responding to security advisories, dealing with deprecated dependencies, evaluating new dependencies, auditing what's installed, or unblocking a dependency upgrade. Triggers on dependency, package update, security patch, lockfile, deprecated, breaking change, supply chain, dependency audit, npm audit, dependabot, renovate. Also triggers when a build breaks after an update or when an advisory is published for a used package.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,401 tokensWhen the skill is activated
Reference documents
2,009 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of dependency
- The framework: 5 risk dimensions
- Workflow
- New dependency evaluation
- Dependency removal
- Failure patterns
- Output format
- Reference files
Files
README.mddoc362 bytesSKILL.mdcore11,004 bytesSKILL.mdcore11,004 bytesSKILL.mdcore11,004 bytesreferences/upgrade-checklist.mddoc8,457 bytes
Read SKILL.md
# Dependency Management
Decide what to depend on, keep dependencies current, respond to advisories, and reduce supply chain risk. Stack-agnostic principles; specifics vary by package manager.
---
## When to use
- Setting up dependency hygiene for a new or existing project
- Responding to a security advisory
- Major version upgrade of a key dependency
- Adding a new dependency (evaluation, decision)
- Removing a dependency (cleanup)
- Audit of what's installed and what's actually useddesign-standards
When your agent uses it
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card, CTA, layout, review the UI, fix the design, design system, design tokens, spacing, typography scale, button standards, mobile design. Also triggers for any production design decision where contrast, accessibility, spacing, or visual hierarchy matters.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
2,178 tokensWhen the skill is activated
Reference documents
6,233 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 standards
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc357 bytesSKILL.mdcore9,597 bytesSKILL.mdcore9,597 bytesreferences/design-tokens-template.mddoc7,347 bytesreferences/preship-checklist.mddoc5,862 bytesreferences/tailwind-patterns.mddoc8,867 bytes
Read SKILL.md
# Design Standards
Production design standards for any web project. Stack-agnostic. Tool-agnostic. Covers tokens, contrast, hierarchy, spacing, mobile rules, and the pre-ship checklist.
This skill complements `brand-identity` (which defines the visual system) and `brand-style-guide` (which documents it). This skill is for the day-to-day work of applying those standards in real components and pages.
---
## When to use
- Building a new page, section, or component
- Reviewing UI for quality, accessibility, or consistency
- Setting up design tokens for a new project
- Fixing layout, contrast, or hierarchy issuesdesign-system
When your agent uses it
Build or audit a design system including component library, design tokens, naming conventions, contribution model, and documentation. Use this skill whenever the user wants to build a design system, audit an existing system, define design tokens at the system level, structure a component library, or set up design system governance. Triggers on design system, component library, design tokens, atomic design, atoms, molecules, organisms, design system documentation, Storybook, Figma library, system governance, design contribution model. Also triggers when teams are inconsistent across products and a system is the answer.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
2,088 tokensWhen the skill is activated
Reference documents
5,876 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc354 bytesSKILL.mdcore9,771 bytesSKILL.mdcore9,771 bytesSKILL.mdcore9,771 bytesreferences/governance-playbook.mddoc8,423 bytesreferences/system-architecture.mddoc10,153 bytesreferences/system-audit-template.mddoc7,412 bytes
Read SKILL.md
# Design System
Build, evolve, or audit a design system. Stack-agnostic in principle. Implementation is stack-specific (Figma, Storybook, code library, etc.) but the structure and governance principles transfer.
This skill is for building the system. For applying a system to specific pages or components, use `design-standards`. For brand visual identity, use `brand-identity`.
---
## When to use
- Building a design system from scratch
- Auditing an existing system for gaps or fragmentation
- Defining design tokens at the system level
- Structuring a component librarydiscovery-research-synthesis
When your agent uses it
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis. Also triggers when a team has done research but cannot turn it into decisions, when synthesis is producing pretty decks but no roadmap movement, or when an upcoming PM decision needs to be grounded in research already conducted.
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
4,929 tokensWhen the skill is activated
Reference documents
18,678 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Data-dump vs insight-theater vs actionable-synthesis
- Discovery research types
- The synthesis sequence
- Tagging and clustering discipline
- Pattern naming
- From pattern to product implication
- Writing for decisions, not deck performance
- The synthesis review and validation loop
- When to halt and gather more data
- Common failure modes
- The framework: 12 considerations for discovery synthesis
- Reference files
- Closing: synthesis is where research earns its keep
Files
README.mddoc369 bytesSKILL.mdcore25,186 bytesreferences/common-discovery-synthesis-failures.mddoc11,581 bytesreferences/from-pattern-to-product-implication.mddoc10,038 bytesreferences/pattern-naming-patterns.mddoc9,029 bytesreferences/research-types-and-when-each-fits.mddoc10,694 bytesreferences/synthesis-review-and-validation.mddoc10,987 bytesreferences/synthesis-sequence-walkthrough.mddoc11,419 bytesreferences/tagging-and-clustering-discipline.mddoc9,507 bytesreferences/when-to-gather-more-data.mddoc11,254 bytesreferences/writing-for-decisions-not-decks.mddoc10,630 bytes
Read SKILL.md
# Discovery Research Synthesis
A senior PM's playbook for turning research artifacts into decisions. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the product direction they are meant to inform.
Most discovery research never produces decisions. The team conducts interviews; the transcripts pile up; a researcher hands product the raw artifacts (data-dump) or builds a polished readout deck (insight-theater); the deck gets a 30-minute review meeting and is never referenced again. Two months later the team is making the same product decisions that the research was supposed to inform, with the same gut-feel inputs the research was supposed to displace.
The discipline is in the synthesis. Synthesis is where research earns its keep: where transcripts become tagged observations, observations cluster into patterns, patterns get named, named patterns surface product implications, and implications drive specific decisions. Without that sequence, research is performance art.
This skill covers one-off discovery research projects: a 12-week customer development sprint, a sales-call review for an onboarding redesign, a support-ticket audit informing a roadmap quarter. Different from `user-feedback-aggregation`, which covers ongoing feedback streams; different from `jtbd-framing`, which is a specific framing technique often applied within synthesis but narrower in scope.
The voice is the senior PM or staff product researcher who has run synthesis well and seen plenty of teams fail at it. Honest about where polish becomes performance and where pattern-naming slides into pattern-fabrication.
When to use this skill: synthesizing a recent batch of customer interviews, auditing why prior research has not produced product decisions, designing the synthesis output for a multi-week discovery sprint, or establishing the synthesis discipline a team currently lacks.
dispatch-authoring
When your agent uses it
Write the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope, specification, verification, delivery rules, and stop conditions, so the agent can execute unattended and return a reviewable draft PR. Use this skill whenever the user wants to hand work to an agent, write an agent brief, write instructions for Claude Code, Codex, or a Cursor agent, queue work to run overnight, or turn a plan into something an AI coder can execute without asking questions. Triggers on dispatch, hand off to an agent, agent brief, agent handoff, task brief for an AI coder, instructions for Claude Code, Codex task, Cursor agent, background agent, run this overnight, give this to an agent, unattended run. Also triggers when the user has a plan or a spec and asks how to get an agent to build it, even if they never say dispatch.
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
1,840 tokensWhen the skill is activated
Reference documents
3,388 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 parts of a dispatch
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc359 bytesSKILL.mdcore8,195 bytesSKILL.mdcore8,195 bytesreferences/dispatch-template.mddoc3,831 bytesreferences/example-dispatch-new-skill.mddoc5,615 bytesreferences/gate-zero-checklist.mddoc3,146 bytesreferences/pr-body-template.mddoc1,802 bytes
Read SKILL.md
# Dispatch Authoring
Write the handoff that lets a coding agent execute a plan unattended and come back with something a human can review. Agent-agnostic: works for Claude Code, Codex, or your coding agent of choice.
---
## When to use
- Handing a planned change to a coding agent to run without supervision
- Queueing work to run overnight or in the background
- Turning a spec or a ticket set into an executable brief for an agent
- Standardizing handoffs so agent runs are comparable and measurable
- Reviewing a draft dispatch before it goes out
documentation-strategy
When your agent uses it
Design and run a documentation system for a team or product. Use this skill when planning what to document, choosing a documentation tool, organizing existing docs, fixing stale documentation, designing a maintenance cadence, or scoping technical writing work. Triggers on documentation, docs, tech writing, knowledge base, wiki, runbook, README, internal docs, doc audit, doc maintenance, stale docs, where do we document. Also triggers when the team is repeatedly answering the same questions or when onboarding takes too long.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
2,938 tokensWhen the skill is activated
Reference documents
2,513 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 categories of documentation
- The framework: 5 tiers of doc
- Workflow
- Specific patterns
- Tooling
- AI-related notes
- Failure patterns
- Output format
- Reference files
Files
README.mddoc363 bytesSKILL.mdcore13,060 bytesSKILL.mdcore13,060 bytesreferences/doc-types-guide.mddoc10,540 bytes
Read SKILL.md
# Documentation Strategy
Decide what gets documented, where, by whom, and how it stays fresh. Stack-agnostic. Applies to internal team docs, product docs, runbooks, READMEs, and knowledge bases.
---
## When to use
- Setting up documentation for a new team or product
- Auditing existing documentation
- Fixing stale or scattered docs
- Choosing a documentation tool or platform
- Defining what gets documented and what doesn't
- Establishing maintenance cadencedomain-strategy
When your agent uses it
Plan, manage, and optimize a domain portfolio. Use this skill for DNS architecture decisions, redirect strategies, registrar choice, parking unused domains, multi-site setups, and domain consolidation or split planning. Triggers on DNS, domain, registrar, redirect, parking, subdomain, apex, www vs non-www, multi-site, portfolio, hreflang setup, domain migration. Also triggers when planning a new site that needs domain decisions made before launch.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
1,983 tokensWhen the skill is activated
Reference documents
2,205 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 decisions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc356 bytesSKILL.mdcore8,799 bytesreferences/dns-record-reference.mddoc7,891 bytes
Read SKILL.md
# Domain Strategy
Decide how domains, subdomains, and DNS work across a portfolio. Stack-agnostic. Works for one site or one hundred.
---
## When to use
- Setting up DNS for a new site (apex vs www, primary vs aliases)
- Choosing or switching registrars
- Planning redirects across multiple domains (parked, retired, consolidated)
- Deciding subdomain vs subfolder vs separate domain for a new product line
- Consolidating multiple sites into one
- Splitting one site into multipleeditorial-qa
When your agent uses it
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
What it loads into context
Frontmatter
249 tokensAlways available to the agent
SKILL.md
4,754 tokensWhen the skill is activated
Reference documents
16,504 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Catch-problems QA vs checkbox QA
- Brief adherence check
- Voice consistency check
- Fact accuracy and citation discipline
- Structure and clarity check
- AI-content audit
- SEO and AEO compliance check
- Internal linking and schema validation
- QA at scale
- The QA workflow
- Common failure modes
- The framework: 12 considerations for editorial QA
- Reference files
- Closing: QA is where quality gets enforced
Files
README.mddoc353 bytesSKILL.mdcore22,411 bytesSKILL.mdcore22,411 bytesreferences/ai-content-audit-patterns.mddoc9,219 bytesreferences/brief-adherence-checklist.mddoc6,950 bytesreferences/common-qa-failures.mddoc9,533 bytesreferences/fact-accuracy-and-citation-discipline.mddoc7,262 bytesreferences/internal-linking-and-schema-validation.mddoc7,152 bytesreferences/qa-at-scale-patterns.mddoc8,389 bytesreferences/qa-workflow-templates.mddoc8,208 bytesreferences/seo-aeo-compliance-checklist.mddoc7,112 bytesreferences/structure-and-clarity-review.mddoc7,106 bytesreferences/voice-consistency-patterns.mddoc6,791 bytes
Read SKILL.md
# Editorial QA
A senior editor's playbook for pre-publish content QA. The discipline that catches problems BEFORE content ships, not after.
Most content QA is broken in one of two directions. The thin version is "did I read it once and is the spelling OK," which catches typos but misses brief drift, voice inconsistency, hallucinated facts, AI tells, and structural problems that reach readers as "this is fine but not memorable." The thick version is a 47-item checklist that nobody completes honestly because it is process theater: checkboxes nobody actually believes catch problems.
This skill is the discipline of catch-problems QA. Each check earns its keep by catching a specific class of failure that would reach readers if missed. Checks that do not catch anything get cut. Checks the production volume cannot sustain get redesigned (sampling instead of full audit, automated instead of manual). The QA framework is what is left when you remove the theater.
The skill covers three production shapes: single editorial pieces (one at a time, full QA), AI-generated drafts (with the AI-content audit that did not exist as prominently 2 years ago), and programmatic SEO sets at scale (sampling discipline, threshold gating). Each needs its own QA shape; the underlying methodology composes across all three.
When to use this skill: building a content QA process from scratch, auditing an existing QA process that ships sloppy work or burns out the team, designing QA gates for an AI-assisted workflow, or building sampling discipline for programmatic SEO sets.
---
email-deliverability
When your agent uses it
Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation strategy, monitoring sender reputation, or hardening against email spoofing. Triggers on email deliverability, SPF, DKIM, DMARC, spam folder, sender reputation, mailbox provider, soft bounces, bounce rate, BIMI, MTA-STS, deliverability audit. Also triggers when a marketing or transactional email isn't reaching users.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,695 tokensWhen the skill is activated
Reference documents
2,360 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 pillars
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc361 bytesSKILL.mdcore11,489 bytesSKILL.mdcore11,489 bytesreferences/dmarc-rollout-playbook.mddoc9,199 bytes
Read SKILL.md
# Email Deliverability
Get email into inboxes, not spam folders. Set up authentication. Monitor reputation. Diagnose problems before they hurt the business.
---
## When to use
- Setting up email for a new domain
- A meaningful percentage of email is going to spam
- Customers report they're not receiving emails
- Setting up DMARC, SPF, or DKIM
- Hardening against domain spoofing
- Migrating email service providersemail-sequences
When your agent uses it
Design and write email campaigns and sequences including onboarding flows, lifecycle campaigns, transactional emails, newsletters, broadcast sends, and launch and announcement emails. Use this skill whenever the user wants to write email copy, plan an email sequence, design an onboarding drip, or set up lifecycle email campaigns. Triggers on email sequence, drip campaign, onboarding email, lifecycle email, welcome email, transactional email, newsletter, email broadcast, launch email, announcement email, nurture sequence, abandoned cart, re-engagement, win-back. Also triggers when planning email automation flows or writing email subject lines for campaigns.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,369 tokensWhen the skill is activated
Reference documents
3,877 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 sequence types
- The 5 components of every email
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc356 bytesSKILL.mdcore10,431 bytesreferences/sequence-templates.mddoc8,158 bytesreferences/subject-line-patterns.mddoc7,559 bytes
Read SKILL.md
# Email Sequences
Plan and write email campaigns. Sequences (multi-message flows triggered by events) and broadcasts (one-off sends). Stack-agnostic. Works with any email service provider.
---
## When to use
- Writing welcome and onboarding email sequences
- Planning lifecycle campaigns (activation, retention, win-back)
- Writing transactional emails (receipts, password resets, notifications)
- Newsletter design and writing
- Abandoned-cart or re-engagement flows
- Writing a one-off broadcast, launch announcement, or news emailevidence-based-reviews
When your agent uses it
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
2,482 tokensWhen the skill is activated
Reference documents
1,529 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: one rule, four evidence tiers
- The methodology block
- Structure discipline the method implies
- Google reviews-system alignment
- FTC alignment
- Schema judgment
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc363 bytesSKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesSKILL.mdcore12,410 bytesreferences/evidence-tiers.mddoc4,193 bytesreferences/methodology-block-template.mddoc2,760 bytes
Read SKILL.md
# Evidence-Based Reviews
Produce product reviews and buying guides whose claims match their evidence. The method is evidence synthesis with a disclosed basis, and one rule anchors everything: never claim hands-on time that did not happen.
Most review sites fail this rule quietly. "We tested" appears above content assembled from spec sheets, and readers have learned to smell it. The honest alternative is stronger, not weaker: synthesis of owner experience at scale, verified specifications, and triangulated expert sources is demonstrable original analysis, and disclosing it builds the trust that fabricated testing destroys.
---
## When to use
- Writing product reviews or buying guides when hands-on access is partial or absent
- Setting up the review methodology for a new review or affiliate site
- Adding evidence disclosure to existing review content
- Auditing review content for claims its evidence cannot supportexperiment-design
When your agent uses it
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.
What it loads into context
Frontmatter
237 tokensAlways available to the agent
SKILL.md
6,363 tokensWhen the skill is activated
Reference documents
12,055 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The framework: 12 considerations for trustworthy experiment results
- Hypothesis discipline
- Sample size and minimum detectable effect
- Test duration
- What NOT to A/B test
- Segment analysis
- Interaction effects
- Ratio metrics and the delta method
- Network effects and two-sided markets
- Sequential testing and the peeking problem
- Pre-commitment vs p-hacking
- Reading results and making the call
- Common failures and fixes
- If required data is unavailable
- Reference files
- Closing: when in doubt
Files
README.mddoc358 bytesSKILL.mdcore31,727 bytesSKILL.mdcore31,727 bytesreferences/common-failures.mddoc10,946 bytesreferences/hypothesis-templates.mddoc8,742 bytesreferences/platform-comparison.mddoc10,392 bytesreferences/post-experiment-decision-framework.mddoc6,436 bytesreferences/pre-experiment-readiness-checklist.mddoc5,457 bytesreferences/results-interpretation-checklist.mddoc7,660 bytesreferences/sample-size-tables.mddoc6,398 bytes
Read SKILL.md
# Experiment Design
A senior product manager's playbook for running experiments that produce trustworthy decisions.
The default state of experimentation in most companies is sloppy. PMs run tests against vague hypotheses, look at results too early, ignore guardrails, stratify into noise, and ship features whose lift is mostly measurement error. The cost is real: ship the wrong thing, kill the right thing, learn the wrong lesson, repeat.
This skill is the discipline that prevents most of those mistakes. It assumes you have a working experimentation platform (Statsig, PostHog, GrowthBook, Optimizely, Amplitude, Eppo, Kameleoon; the platform does not matter for the principles). It assumes you have product-design and engineering pipelines that can deliver real treatment changes. The hard part is the thinking, and that is what is here.
When to use this skill: any time you are about to design or interpret an experiment. Read the relevant section before you start, not after the test is running.
---
## What this skill covers
experimentation-analytics
When your agent uses it
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this skill whenever the user is reading a finished experiment result panel and about to make a ship, kill, or iterate decision, or when an experiment number does not match the dashboard number. Triggers on read experiment results, result panel, ship or kill decision, p-value, confidence interval, statistical significance, multiple testing, peeking, sequential testing, CUPED, variance reduction, heterogeneous treatment effects, ratio metric, network effects, inconclusive test, experiment versus dashboard mismatch. Use `experiment-design` instead when the test has not run yet and the question is hypothesis, sample size, duration, or what to test.
What it loads into context
Frontmatter
228 tokensAlways available to the agent
SKILL.md
7,295 tokensWhen the skill is activated
Reference documents
14,562 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The result panel: what every modern platform should expose
- Confidence intervals: the most important number
- P-values: what they mean and what they do not
- Multiple testing corrections
- Sequential testing math
- CUPED variance reduction
- Heterogeneous treatment effects (HTE) and segments
- Ratio metrics and the delta method
- Bayesian vs frequentist results panels
- Network effects and SUTVA violation
- Dashboard metric vs experiment metric reconciliation
- Long-term effect estimation
- Common interpretation failures
- The framework: 14 considerations for trustworthy experiment interpretation
- Reference files
- Closing: the courage to call it inconclusive
Files
README.mddoc366 bytesSKILL.mdcore35,748 bytesreferences/analytics-platform-comparison.mddoc10,160 bytesreferences/common-interpretation-failures.mddoc13,900 bytesreferences/confidence-interval-cheatsheet.mddoc7,164 bytesreferences/dashboard-vs-experiment-reconciliation.mddoc7,403 bytesreferences/p-value-interpretation-guide.mddoc8,111 bytesreferences/result-presentation-templates.mddoc9,227 bytesreferences/statistical-method-reference.mddoc11,787 bytes
Read SKILL.md
# Experimentation Analytics
A data-team-mentor's playbook for interpreting experiment results without fooling yourself.
The result panel is the moment-of-truth for an experiment. The numbers on it determine whether you ship, kill, or iterate. They also expose every shortcut taken in the design phase: an underpowered test produces wide confidence intervals; a peeked test produces a too-narrow p-value; a ratio metric without delta-method correction produces overconfident lift estimates. Most ship-the-wrong-thing decisions trace back to misreading the result panel.
This skill is the discipline that prevents misreading. It assumes the experiment was designed well (see the `experiment-design` skill). It assumes the platform's results panel is technically correct (most modern platforms are; some older ones are not). It assumes you can read a number off a screen. The hard part is knowing what each number actually means and what it does not, and that is what is here.
When to use this skill: any time you are reading an experiment result panel and about to make a ship, kill, or iterate decision.
---
## What this skill is for
experimentation-platform-orchestrator
When your agent uses it
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
What it loads into context
Frontmatter
218 tokensAlways available to the agent
SKILL.md
5,354 tokensWhen the skill is activated
Reference documents
11,094 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The 7 considerations for the platform decision
- Statsig
- PostHog
- GrowthBook
- Optimizely
- Amplitude
- Eppo
- Kameleoon
- Decision matrix: which platform for which context
- Multi-platform: when warranted, when a mess
- Migration patterns
- The cost reality
- Governance and team fit
- The MCP capability layer
- When to defer the decision
- Common mistakes
- The framework: 11 considerations for sustainable platform choice
- Reference files
- Closing: when in doubt, pick boring
Files
README.mddoc378 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesSKILL.mdcore26,589 bytesreferences/common-mistakes.mddoc9,003 bytesreferences/cost-and-pricing-models.mddoc8,045 bytesreferences/governance-and-team-setup.mddoc7,543 bytesreferences/mcp-capability-comparison.mddoc6,018 bytesreferences/migration-playbook.mddoc8,243 bytesreferences/multi-platform-orchestration.mddoc7,159 bytesreferences/platform-decision-matrix.mddoc6,525 bytes
Read SKILL.md
# Experimentation Platform Orchestrator
A senior product and engineering leader's playbook for making the experimentation platform decision and recovering from making it wrong.
Picking an experimentation platform is one of those decisions that looks easy at the start and compounds for years afterward. The wrong choice costs you in lost experiments (because the team avoids the painful workflow), in cost (because the wrong pricing model penalizes your usage shape), in vendor lock-in (because migration is real engineering work, not a config change), and in cultural drift (because the platform's defaults shape what your team thinks experimentation is).
This skill is the discipline that makes the decision well the first time and the migration plan when you didn't.
When to use this skill: choosing a platform from scratch, evaluating whether to switch, deciding whether to consolidate from multi-platform to single, or planning a migration that has already been approved.
---
## What this skill is for
feature-flagging
When your agent uses it
Operational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy, lifecycle, governance, stale flag management, and the technical debt patterns that bite teams who weren't deliberate about it.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
5,370 tokensWhen the skill is activated
Reference documents
9,626 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The five flag types
- Flag naming conventions
- The flag lifecycle
- Targeting rules and segmentation
- Rollout strategies
- Stale flag management
- Governance and permissions
- Flag dependencies and conflicts
- Performance considerations
- Testing flag-gated code
- Rollback discipline
- Observability on flags
- Common failures (rapid-fire)
- The framework: 14 considerations for sustainable feature flagging
- If required data is unavailable
- Reference files
- Closing: when to remove a flag
Files
README.mddoc357 bytesSKILL.mdcore25,796 bytesSKILL.mdcore25,796 bytesSKILL.mdcore25,796 bytesreferences/flag-lifecycle-checklist.mddoc5,006 bytesreferences/flag-naming-conventions.mddoc5,094 bytesreferences/flag-rollout-strategies.mddoc7,061 bytesreferences/flag-types-reference.mddoc6,712 bytesreferences/governance-and-permissions.mddoc6,954 bytesreferences/stale-flag-cleanup-playbook.mddoc6,154 bytesreferences/targeting-rule-patterns.mddoc6,706 bytes
Read SKILL.md
# Feature Flagging
A senior engineer's playbook for using feature flags well, not just frequently.
Feature flags are infrastructure. Treated as such, they enable kill switches, gradual rollouts, A/B experiments, permission gates, and operational toggles without redeploys. Treated casually, they become the largest accumulating technical debt in your codebase: thousands of dead flags, conflicting evaluation logic, brittle targeting, and a permission surface no one fully understands.
This skill is the discipline that prevents the second outcome. It assumes you have a feature flag platform (LaunchDarkly, Flagsmith, Split.io, VWO FME, GrowthBook, Statsig, PostHog, Optimizely; the platform does not matter for the principles). It assumes your engineering team can implement targeting rules and SDK integration. The hard part is the operational discipline, and that is what is here.
When to use this skill: any time you are about to introduce a flag, modify a flag, audit existing flags, or design a flag-related governance policy.
---
## What this skill is for
feature-launch-playbook
When your agent uses it
The operational playbook for launching a feature well. Positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring with pre-defined rollback triggers, post-launch measurement against spec hypotheses, and the discipline that distinguishes shipping from releasing from actually launching. Triggers on launch plan, feature launch, launch checklist, ship vs release, rollout strategy, gradual rollout, sales enablement, support readiness, launch announcement, post-launch measurement, launch failure, declared victory too early. Also triggers when planning a launch (any size, any segment), auditing an existing launch process, fixing the we shipped it but the metric did not move problem, or building a launch checklist for the team.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
5,441 tokensWhen the skill is activated
Reference documents
18,254 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Ship vs release vs launch
- Launch tiers
- Pre-launch: positioning
- Pre-launch: internal alignment
- Pre-launch: customer comms plan
- Pre-launch: sales enablement (B2B)
- Pre-launch: support readiness
- Launch day: rollout strategy
- Launch day: monitoring
- Launch day: comms execution
- Post-launch: measurement against spec hypotheses
- Post-launch: iteration and follow-ups
- Common failure modes
- The framework: 12 considerations for a real launch
- If required data is unavailable
- Reference files
- Closing: most failed launches are unlaunched
Files
README.mddoc364 bytesSKILL.mdcore26,290 bytesSKILL.mdcore26,290 bytesreferences/common-launch-failures.mddoc11,194 bytesreferences/customer-comms-playbook.mddoc8,102 bytesreferences/internal-alignment-checklist.mddoc7,355 bytesreferences/launch-tier-decision.mddoc6,987 bytesreferences/monitoring-readiness-checklist.mddoc8,429 bytesreferences/positioning-canvas.mddoc8,542 bytesreferences/post-launch-measurement-framework.mddoc9,449 bytesreferences/rollout-strategy-patterns.mddoc8,971 bytesreferences/sales-enablement-template.mddoc8,314 bytesreferences/support-readiness-checklist.mddoc7,719 bytes
Read SKILL.md
# Feature Launch Playbook
A veteran PM-leader's playbook for launching features well, not just shipping them.
Most teams conflate shipping, releasing, and launching. Shipping means engineering work is complete. Releasing means users can access it, even if it is behind a flag at 1 percent. Launching is the discipline of positioning, internal alignment, customer comms, sales enablement, support readiness, rollout strategy, monitoring, and post-launch measurement that turns "feature exists" into "feature lands."
A feature that ships without launching costs you the same engineering investment but captures a fraction of the value. Sales does not know how to sell it. Support does not know how to help with it. Customers do not notice it. The metric you said you would move does not move because nobody knows the feature is there.
This skill is the operational playbook. It assumes you have already written the spec (`pm-spec-writing`), prioritized it onto the roadmap (`roadmap-planning`), instrumented it (`product-analytics-setup`), and possibly tested it (`experiment-design`). The launch is the next discipline: how to actually get the feature in front of the right users, with the right context, in a way that lets you measure whether it worked.
When to use this skill: planning a launch (any size, any segment), auditing an existing launch process, fixing the "we shipped it but the metric did not move" problem, or building a launch checklist for the team.
---
form-strategy
When your agent uses it
Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are low or spam is overwhelming.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
2,521 tokensWhen the skill is activated
Reference documents
2,271 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc354 bytesSKILL.mdcore11,441 bytesSKILL.mdcore11,441 bytesreferences/form-anatomy-checklist.mddoc9,144 bytes
Read SKILL.md
# Form Strategy
Forms are where intent becomes action. Design them well or lose conversions, frustrate users, and drown in spam. Stack-agnostic.
---
## When to use
- Designing or redesigning a form
- Conversion is dropping on a key form
- Spam volume is overwhelming the inbox or database
- Auditing forms across a site
- Planning validation logic
- Choosing form tooling (form service, custom build, no-code)frontend-component-build
When your agent uses it
Build production-ready frontend components with accessible markup, sensible props, defined states, and tested behavior. Use this skill whenever the user wants to build a component from scratch, refactor an existing one, design a component API, or implement a UI element with proper states and accessibility. Triggers on build a component, create a button, create a modal, create a form input, component API, props design, component states, refactor component, accessible component. Also triggers when implementing UI from a design that needs to be reusable.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
1,921 tokensWhen the skill is activated
Reference documents
5,904 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 dimensions
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc365 bytesSKILL.mdcore8,657 bytesreferences/accessibility-patterns.mddoc8,072 bytesreferences/component-api-patterns.mddoc8,038 bytesreferences/component-spec-template.mddoc7,070 bytes
Read SKILL.md
# Frontend Component Build
Build production-ready components. Stack-agnostic principles. Most patterns translate to React, Vue, Svelte, or vanilla web components.
This skill is about implementing a component well. For broader system design see `design-system`. For day-to-day visual decisions see `design-standards`.
---
## When to use
- Building a new component from scratch
- Refactoring an existing component
- Designing a component API (props, slots, events)
- Adding accessibility to an existing componentfunnel-flow-architecture
When your agent uses it
Architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. Honest about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience-and-stage) patterns. Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, multi-tool funnel orchestration. Also triggers when the team's growth tools are working individually but not together, when audience segments share one nurture path, or when a funnel is being architected from scratch.
What it loads into context
Frontmatter
198 tokensAlways available to the agent
SKILL.md
4,363 tokensWhen the skill is activated
Reference documents
16,479 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- Silo-funnels vs kitchen-sink-funnels vs matched-funnels
- Audience and stage segmentation
- Entry-point architecture
- Tool-to-funnel mapping
- Nurture sequence architecture
- Cross-tool data flow
- Funnel measurement
- Funnel iteration discipline
- Architecture anti-patterns
- The framework: 12 considerations for funnel flow architecture
- If required data is unavailable
- Reference files
- Closing: funnels are architecture, not collections
- Closing: funnels earn investment when they compose
Files
README.mddoc365 bytesSKILL.mdcore22,328 bytesSKILL.mdcore22,328 bytesreferences/architecture-anti-patterns.mddoc8,941 bytesreferences/audience-and-stage-segmentation.mddoc9,391 bytesreferences/common-funnel-architecture-failures.mddoc8,080 bytesreferences/cross-tool-data-flow-patterns.mddoc10,099 bytesreferences/entry-point-architecture-patterns.mddoc8,906 bytesreferences/funnel-iteration-discipline.mddoc8,491 bytesreferences/funnel-measurement-patterns.mddoc9,505 bytesreferences/nurture-sequence-architecture.mddoc10,947 bytesreferences/tool-to-funnel-mapping.mddoc9,924 bytes
Read SKILL.md
# Funnel Flow Architecture
A senior growth practitioner's playbook for architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. The discipline of building a funnel architecture, not just collecting tools.
Most growth programs accumulate tools without architecture. A chatbot, a calculator, a quiz, a lead magnet, a newsletter signup, a demo CTA. Each tool works individually; none of them work together. Visitors hit one tool, leave, and never enter the broader nurture sequence. The funnel is a collection of orphans.
The growth programs that compound do something different. They architect the funnel deliberately. Different entry points lead to different nurture sequences. Different stages get different CTAs. Different tools serve different segments. Each tool is part of a larger architecture, not a standalone artifact.
This skill is the architecture skill that orchestrates the other 5 growth-tooling skills (lead-magnet-design, calculator-design, quiz-and-assessment-design, multi-step-form-design, chatbot-flow-design). Where those skills zoom into specific tool design, this skill zooms out to the cross-tool architecture that determines whether the tools compound.
The voice is the senior growth practitioner who has watched funnels architecture compound and watched siloed funnel collections produce engagement metrics with no business impact. Practical, opinionated about the difference between collecting tools and architecting funnels, willing to call out when a team's growth program needs architecture rather than another tool.
When to use this skill: architecting a funnel from scratch, auditing a growth program where tools work individually but conversion is flat, designing the cross-tool data flow that captures audience signal across touchpoints, or deciding which segments warrant which funnel paths.
incident-response
When your agent uses it
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,183 tokensWhen the skill is activated
Reference documents
2,075 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 phases
- Roles during an incident
- Decision-making during an incident
- Status page communication patterns
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore9,957 bytesSKILL.mdcore9,957 bytesreferences/incident-playbook.mddoc9,180 bytes
Read SKILL.md
# Incident Response
Manage active production incidents from detection to resolution. Stack-agnostic. Tool-agnostic.
This skill is for active incidents and incident process. For after-the-fact analysis, use `after-action-report`. For planned launches, use `launch-runbook`.
---
## When to use
- An active incident is happening
- Building incident response procedures
- Defining severity levels
- Setting up on-call rotationsinformation-architecture
When your agent uses it
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system level. Triggers on sitemap, site structure, navigation, IA, information architecture, URL structure, content types, taxonomy, categorization, breadcrumbs, hub pages, faceted navigation, site search, labeling. Also triggers when content is being created without a structural plan, or when an existing site's structure is being audited or restructured.
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
2,251 tokensWhen the skill is activated
Reference documents
3,966 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc365 bytesSKILL.mdcore10,456 bytesSKILL.mdcore10,456 bytesreferences/ia-document-template.mddoc7,519 bytesreferences/url-pattern-library.mddoc8,047 bytes
Read SKILL.md
# Information Architecture
Design the structure that holds the content. Stack-agnostic. Applies to marketing sites, product surfaces, knowledge bases, e-commerce, and editorial content.
A well-designed IA makes the rest of the project easier. A poorly-designed IA forces every downstream decision to fight the structure.
---
## When to use
- Designing a new site or major section from scratch
- Restructuring an existing site
- Adding a new content type or category
- Designing site navigation or menu systemsintegration-orchestrator
When your agent uses it
Generate a phased delivery orchestration plan for creative-direction-driven work: which skills run when, what locks at which gate, how handoffs occur, and how the cadence implements in the team's tools (Jira, Linear, Notion, Figma, GitHub) with AI agents via MCP and CLI. A temporal map of phases, lock points, handoff specs, gate definitions, and QA verification gates. Distinct from `creative-brief` (static project brief) and `creative-direction` (aesthetic direction). Triggers on integration orchestrator, delivery cadence, project orchestration, when does the brief lock, how to phase creative direction, design-development handoff, QA gate, agent-driven QA, and when a creative-direction project is starting, mid-flight with broken cadence, or integrating AI agents into PM workflow. Does NOT fire for project scoping (use `creative-brief`), aesthetic direction (use `creative-direction`), or general project management without a creative-direction throughline.
What it loads into context
Frontmatter
240 tokensAlways available to the agent
SKILL.md
4,371 tokensWhen the skill is activated
Reference documents
18,500 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is
- When to use
- When NOT to use
- Required inputs
- The framework: 7 considerations for orchestration
- Common project-type cadences
- Failure patterns
- Output format
- Reference files
Files
README.mddoc365 bytesSKILL.mdcore21,008 bytesSKILL.mdcore21,008 bytesreferences/automation-and-qa-tooling.mddoc12,839 bytesreferences/cadence-patterns.mddoc11,589 bytesreferences/example-orchestration.mddoc15,949 bytesreferences/gate-definitions.mddoc9,868 bytesreferences/handoff-protocols.mddoc12,110 bytesreferences/platform-implementation.mddoc17,271 bytesreferences/team-size-modulation.mddoc7,938 bytes
Read SKILL.md
# Integration Orchestrator
A brief tells a team what to make. Creative direction tells them what it should feel like. Neither tells them when each decision locks, who reviews what, or what stops the next phase from starting before the prior one is done. That is the gap this skill fills.
The output is a phased orchestration plan the PM can paste into a calendar Monday morning and start running Tuesday. Phases, gates, lock points, handoffs, QA verification rules, and a platform-specific implementation guide for whatever stack the team actually uses (Jira, Linear, Notion, Figma, GitHub, agile sprints).
---
## What this skill is
A creative-direction project has three layers. The brief layer defines scope, audience, deliverables, constraints, success criteria. The direction layer defines tone, aesthetic, relationship, and sensory ambition. Both produce written artifacts. Neither answers the temporal question: when does the brief lock, when does identity lock, when does copy lock, who reviews each, what gets blocked while a gate is open, what happens when a downstream task discovers the brief is wrong, and what makes "Done" mean tested rather than self-reported.
This skill produces that temporal layer. Most teams have briefs and creative direction but no orchestration plan. The result, by week 3, is everyone working in parallel with no shared sense of which decisions are still open and which are locked. Brief drift. Re-work. Identity tokens shifted after copy was already drafted against the old ones. Engineering shipping before design had a chance to review. "Done" tickets that were never actually verified.
interactive-product-tour
When your agent uses it
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of need), and contextual-when-needed (surfaces help at the moment friction occurs) patterns. Triggers on product tour, in-product tooltip, contextual help, walkthrough, feature tour, hint system, in-app guidance, tour platform. Also triggers when feature adoption is low, when users miss key product capabilities, or when an in-product help system is being scoped for the first time.
What it loads into context
Frontmatter
210 tokensAlways available to the agent
SKILL.md
3,677 tokensWhen the skill is activated
Reference documents
13,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The tour decision: when tours earn vs when documentation suffices
- Tooltip-spam vs one-and-done vs contextual-when-needed
- Trigger logic: event-based vs time-based vs state-based
- Tour architecture: single tour vs branched vs library of micro-tours
- Contextual placement: where help appears, how it dismisses
- Completion tracking and re-trigger logic
- Power-user vs new-user differentiation
- Common failure modes
- The framework: 12 considerations for product tour design
- Reference files
- Closing: tours earn the user's attention by being absent until needed
Files
README.mddoc365 bytesSKILL.mdcore17,715 bytesreferences/common-tour-failures.mddoc5,873 bytesreferences/completion-tracking-and-re-trigger.mddoc7,291 bytesreferences/contextual-placement-patterns.mddoc6,927 bytesreferences/dismissal-and-non-intrusion-patterns.mddoc7,153 bytesreferences/power-user-vs-new-user-patterns.mddoc7,350 bytesreferences/tour-anti-patterns.mddoc7,293 bytesreferences/tour-architecture-patterns.mddoc6,595 bytesreferences/tour-decision-criteria.mddoc6,966 bytesreferences/trigger-logic-patterns.mddoc7,198 bytes
Read SKILL.md
# Interactive Product Tour
A senior product marketing director's playbook for designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. The discipline of building help systems that surface at moments of need and disappear when not needed.
Most product tours fail in one of two ways. They paint every button, link, and feature with "click for tour" hints until the visual noise is so great that users develop blindness to the dots. Or they show a single first-login tour the user skips or skims, after which the same help never re-surfaces when the user actually hits a moment of friction. Help that is invisible at the moment of need is help that does not exist.
The tours that work do something different. They trigger when the user is at a moment of friction, not all the time. They surface contextual hints when the user enters a section they have not explored, clicks into a feature requiring setup, or returns after a long absence. The system knows what the user knows and surfaces help at the right moment.
The voice is the senior product marketing director who has watched feature adoption double when tours were redesigned and watched it collapse when more tooltips were piled onto every surface. Practical, opinionated about the trigger logic that distinguishes useful help from visual noise, willing to call out when no in-product tour at all is the right answer.
When to use this skill: scoping an in-product help system for the first time, auditing a tour system that produces engagement metrics with no adoption lift, designing the trigger logic that decides when help surfaces, or deciding which features warrant tours vs documentation.
---
internationalization
When your agent uses it
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled internationalization rollout. Triggers on internationalization, i18n, localization, l10n, hreflang, multi-language, translation workflow, RTL, locale, ccTLD, subfolder vs subdomain, language switcher. Also triggers when international audiences underperform or translations are stale.
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
2,672 tokensWhen the skill is activated
Reference documents
2,123 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc361 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesSKILL.mdcore12,366 bytesreferences/locale-checklist.mddoc8,829 bytes
Read SKILL.md
# Internationalization
Add languages and regions in a way that works for users, search engines, and the team maintaining the content. Stack-agnostic.
---
## When to use
- Adding the first non-English (or non-default) language
- Adding additional locales to an existing internationalized site
- Choosing URL structure for languages
- Implementing hreflang tags
- Designing translation workflow
- Handling currency, date, time, and number formatsjourney-mapping
When your agent uses it
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the user experience, or visualize touchpoints and pain points. Triggers on customer journey, journey map, service blueprint, user journey, experience map, touchpoint analysis, friction map, journey audit, end-to-end experience, customer experience map. Also triggers when the team has departmental views of users but no shared map of what the experience actually feels like.
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
2,143 tokensWhen the skill is activated
Reference documents
1,816 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 deliverables
- Common phases by product type
- How to gather the inputs
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc356 bytesSKILL.mdcore10,007 bytesSKILL.mdcore10,007 bytesreferences/journey-map-template.mddoc6,875 bytes
Read SKILL.md
# Journey Mapping
Build journey maps and service blueprints that surface friction, align teams, and identify opportunities. Stack-agnostic. Tool-agnostic.
This skill is for mapping the experience. For testing specific touchpoints, use `usability-testing`. For broader generative research, use `ux-research`. For analyzing conversion, use `cro-optimization`.
---
## When to use
- Departments have different mental models of the customer experience
- Customer experience feels disjointed across touchpoints
- Specific friction or drop-off points need diagnosis
- Strategic planning needs a shared view of the userjtbd-framing
When your agent uses it
The Jobs-to-be-Done framework as applied product methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity (discovery, prioritization, positioning) and where it becomes performative ritual (job-statement workshops that do not drive decisions, persona-theater disguised as JTBD). Triggers on jobs-to-be-done, JTBD, job statements, struggling moments, hire criteria, fire criteria, switch triggers, functional emotional social jobs, outcome-driven innovation. Also triggers when a team is over-relying on feature-request lists or persona archetypes that do not drive product decisions, when a positioning conversation needs the framing JTBD provides, or when discovery is producing outputs that do not connect to product strategy.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
4,378 tokensWhen the skill is activated
Reference documents
16,480 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Feature-request-list vs persona-theater vs job-framing
- The job statement structure
- Identifying struggling moments
- Hire and fire criteria
- Functional, emotional, and social dimensions of jobs
- Where JTBD adds clarity vs where it becomes ritual
- Applying JTBD to discovery, prioritization, positioning
- Common failure modes
- The framework: 12 considerations for JTBD framing
- If required data is unavailable
- Reference files
- Closing: jobs over features
Files
README.mddoc353 bytesSKILL.mdcore21,757 bytesSKILL.mdcore21,757 bytesreferences/applying-jtbd-to-discovery.mddoc10,969 bytesreferences/applying-jtbd-to-positioning.mddoc10,319 bytesreferences/applying-jtbd-to-prioritization.mddoc11,069 bytesreferences/common-jtbd-failures.mddoc11,018 bytesreferences/functional-emotional-social-dimensions.mddoc10,358 bytesreferences/hire-and-fire-criteria.mddoc10,674 bytesreferences/identifying-struggling-moments.mddoc9,877 bytesreferences/job-statement-structure-patterns.mddoc9,309 bytes
Read SKILL.md
# Jobs-to-be-Done Framing
A senior product leader's playbook for the Jobs-to-be-Done framework as applied methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity and where it becomes performative ritual.
JTBD has become one of the more cited and less practiced frameworks in product. Teams cite it in strategy docs, run job-statement workshops, produce wall-sized artifacts, and continue building from feature requests and persona archetypes the next quarter. The methodology gets the credit; the practice gets skipped.
This skill is JTBD as applied product methodology. The framework's actual contribution: surfacing what users are trying to ACCOMPLISH (the job) rather than treating users as preference-aggregators (feature requests) or demographic archetypes (persona theater). When the framing is grounded in struggling moments and hire/fire criteria, it produces decisions; when it stops at the job-statement worksheet, it produces ritual.
This skill is honest about both modes. JTBD genuinely earns its keep in discovery, prioritization, and positioning when applied with rigor. It becomes ceremony when teams treat job statements as deliverables rather than as analytical tools.
The voice is the senior product leader who has used JTBD well and watched plenty of teams use it badly. Concrete, opinionated about what the framework actually contributes, willing to call out where it gets oversold.
When to use this skill: applying JTBD to a discovery cycle, replacing persona-driven prioritization with job-driven prioritization, reframing positioning around what users hire the product to do, or auditing whether existing JTBD work in the org is driving decisions.
landing-page-copy
When your agent uses it
Write landing page copy with attention to the hero, value proposition, social proof, objection handling, and conversion-focused CTAs. Use this skill whenever the user wants to write a landing page, sales page, hero section, or any conversion-focused web copy. Triggers on landing page, sales page, hero copy, value proposition, headline, subheadline, hero section, CTA copy, conversion copy, opt-in page, squeeze page. Also triggers when the user has a marketing campaign or product launch needing dedicated conversion copy. Use `cro-optimization` instead when the page already exists and the ask is to lift its conversion rate through testing rather than to write the copy.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
2,506 tokensWhen the skill is activated
Reference documents
4,094 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 7 sections
- The CTA itself
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore10,807 bytesSKILL.mdcore10,807 bytesreferences/hero-formulas.mddoc7,286 bytesreferences/objection-library.mddoc10,581 bytes
Read SKILL.md
# Landing Page Copy
Write copy for pages with a single conversion goal: signup, purchase, demo request, download, lead capture. Stack-agnostic.
This skill is narrower than `content-and-copy`. Landing pages exist to drive a specific action, not to inform broadly.
---
## When to use
- Writing a hero section for a homepage or product page
- Writing a sales page or long-form sales letter
- Drafting opt-in or lead-capture page copy
- Campaign-specific landing pageslaunch-runbook
When your agent uses it
Plan and execute a launch runbook covering pre-launch verification, go-live procedures, DNS cutover, post-launch monitoring, and rollback procedures. Use this skill whenever the user is preparing to launch a website or product, planning a DNS cutover, building a go-live checklist, or executing a launch day. Triggers on launch runbook, go-live, launch day, DNS cutover, deploy to production, site launch, product launch, cutover plan, launch checklist, deployment procedure. Also triggers when a launch is approaching and the team needs structured coordination, even if 'runbook' is not explicitly stated.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
1,769 tokensWhen the skill is activated
Reference documents
2,219 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Roles and responsibilities
- Rollback criteria
- Communication plan
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc355 bytesSKILL.mdcore7,870 bytesreferences/runbook-template.mddoc8,785 bytes
Read SKILL.md
# Launch Runbook
Plan and execute the launch of a website, product, or major release. The runbook is the document everyone uses on launch day. Stack-agnostic.
This skill is for the launch event. For pre-launch QA, use `qa-testing`. For post-launch incident handling, use `incident-response`.
---
## When to use
- Launching a new website or major redesign
- Migrating from one platform to another
- Releasing a major product or feature
- Coordinating cross-team launcheslead-magnet-design
When your agent uses it
Designing lead magnets that earn the email. The discipline of building gated content (ebooks, templates, checklists, swipe files, mini-courses, free tools) that delivers genuine standalone value while qualifying the lead and warming them for what comes next. Honest about thin-bait (overpromises, underdelivers), kitchen-sink-resource (everything, helps with nothing), and earned-value-magnet (delivers standalone value while qualifying the lead). Triggers on lead magnet, gated content, opt-in offer, ebook, checklist, template, swipe file, mini-course, free tool, content upgrade, freebie, opt-in, list-building offer. Also triggers when an audience is being asked for an email and the offer attached to that ask needs design discipline, when previous lead magnets converted but did not produce qualified leads, or when a lead magnet is being scoped for the first time.
What it loads into context
Frontmatter
254 tokensAlways available to the agent
SKILL.md
5,157 tokensWhen the skill is activated
Reference documents
19,302 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The lead magnet decision: when to build one, when not to
- Thin-bait vs kitchen-sink-resource vs earned-value-magnet
- Format selection
- The "would they pay for this" test
- Audience-fit qualification
- Title and presentation discipline
- Delivery and follow-up sequence design
- Format-specific quality gates
- Common failure modes
- The framework: 12 considerations for lead magnet design
- If required data is unavailable
- Reference files
- Closing: magnets earn the email when they earn the reader's afternoon
Files
README.mddoc359 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesSKILL.mdcore25,058 bytesreferences/audience-fit-qualification.mddoc10,332 bytesreferences/common-lead-magnet-failures.mddoc10,585 bytesreferences/delivery-and-follow-up-sequences.mddoc10,478 bytesreferences/format-selection-patterns.mddoc10,248 bytesreferences/format-specific-quality-gates.mddoc11,226 bytesreferences/lead-magnet-anti-patterns.mddoc10,160 bytesreferences/lead-magnet-decision-criteria.mddoc9,683 bytesreferences/title-and-presentation-discipline.mddoc10,262 bytesreferences/would-they-pay-for-this-test.mddoc9,875 bytes
Read SKILL.md
# Lead Magnet Design
A senior growth practitioner's playbook for designing lead magnets that earn the email. Templates, checklists, swipe files, mini-courses, free tools, ebooks. The discipline of building gated content that delivers genuine standalone value while qualifying the lead and warming them for the next conversation.
Most lead magnets are bait. A vague headline, a thin PDF, an email gate, a follow-up sequence the reader resents. Conversion-rate metrics look fine because the form converted; the email list grows; and the unsubscribe rate climbs because the magnet was a transaction the reader regrets the moment they download.
The lead magnets that work as compounding assets do something different. They deliver value the reader would have paid for if they had to. They qualify the lead by audience-fit, so the list that grows is the right list. They set up the next conversation honestly, so the follow-up sequence is a continuation rather than an apology.
This skill is the parent-frame methodology for the growth tooling track. Calculators (`calculator-design`) and quizzes (`quiz-and-assessment-design`) are specific lead-magnet types covered as their own skills. This skill provides the methodology for deciding WHAT to build before deciding WHAT TYPE.
The voice is the senior growth practitioner who has watched lead magnets earn long-term subscribers and watched them burn list trust within a single send. Practical, opinionated about format selection, willing to tell the reader when a lead magnet is the wrong investment for the goal.
When to use this skill: scoping a lead magnet for the first time, auditing a lead magnet that converts but does not qualify, deciding which format fits a specific audience and offer, or designing the post-download sequence that turns the magnet into a relationship.
logo-design
When your agent uses it
Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from `brand-identity`, which produces the complete system (logo plus color, type, voice, applications). Goes deep on the logo specifically: typographic register, symbol approach, application-context discipline (16px favicon, embroidery, signage, motion), and production specs (SVG-ready, single-color, reverse). Triggers on logo design, design a logo, wordmark, monogram, lockup, mark variants, logo iterations, redesign or refine the logo, logo refresh, letterform-as-symbol, and exploring mark variants for an established brand. Does NOT fire for full brand identity (use `brand-identity`), positioning or strategy (use `brand-discovery`), project-wide creative direction (use `creative-direction`), or one-off illustration.
What it loads into context
Frontmatter
244 tokensAlways available to the agent
SKILL.md
4,918 tokensWhen the skill is activated
Reference documents
25,104 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 considerations for logo design
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc352 bytesSKILL.mdcore23,396 bytesreferences/application-contexts.mddoc17,153 bytesreferences/architectures-explained.mddoc14,068 bytesreferences/category-conventions.mddoc24,902 bytesreferences/client-package.mddoc10,036 bytesreferences/example-variant-spec.mddoc9,457 bytesreferences/symbol-approaches.mddoc20,630 bytesreferences/typographic-registers.mddoc20,910 bytes
Read SKILL.md
# Logo Design
A logo is a system of marks, not a single drawing. This skill produces multiple production-grade variants exploring different architectural approaches, each with rationale, application specs, and a clear position on what it signals and rejects.
The output is decision material, not a finished logo. The brand owner selects from the variants and the skill produces production refinement on the chosen direction.
---
## When to use
- The brand has a name and tonal direction; the deliverable is logo work specifically
- Generating 6 to 12 variants for client review and selection
- Refining a wordmark to production: kerning, optical adjustments, weight selection
- Exploring symbol options to pair with an existing wordmarklong-form-content-frameworks
When your agent uses it
Patterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guides, manifestos, ebooks, long-form tutorials. The structural disciplines that distinguish publication-quality long-form from bloggy-long padding or academic bloat. Different from pillar-content-architecture (which covers hub structure); this skill covers individual deep-dive pieces. Triggers on long-form content, case study writing, whitepaper, research report, definitive guide, ebook, manifesto, long-form tutorial, deep-dive article, anchor piece, foundational article, structural archetypes. Also triggers when a piece is over 3,000 words and the team is unsure how to structure it, when a long-form draft feels padded or saggy, or when a flagship asset needs the depth to actually earn the length.
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
6,281 tokensWhen the skill is activated
Reference documents
19,820 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Bloggy-long vs academic-bloat vs publication-quality
- Long-form formats and when each fits
- Structural archetypes
- Section weight calibration
- Lede patterns for long-form
- Sustaining attention across 5,000+ words
- Citations and source authority
- Visualization and breakouts
- Closing patterns
- Distribution implications for long-form
- Common failure modes
- The framework: 12 considerations for long-form content
- If required data is unavailable
- Reference files
- Closing: long-form earns its length or it does not
Files
README.mddoc369 bytesSKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesSKILL.mdcore30,116 bytesreferences/attention-sustaining-techniques.mddoc9,928 bytesreferences/breakouts-and-visualization.mddoc10,656 bytesreferences/citation-and-source-authority.mddoc10,608 bytesreferences/closing-patterns.mddoc12,274 bytesreferences/common-long-form-failures.mddoc11,920 bytesreferences/format-decision-framework.mddoc10,895 bytesreferences/lede-patterns-for-long-form.mddoc10,091 bytesreferences/section-weight-calibration.mddoc9,590 bytesreferences/structural-archetype-patterns.mddoc10,668 bytes
Read SKILL.md
# Long-Form Content Frameworks
A senior editorial leader's playbook for individual long-form content pieces. The structural disciplines that distinguish publication-quality work from bloggy-long padding or academic bloat.
Long-form is where most content programs lose their nerve or lose their way. Teams either stretch a 1,500-word post to 5,000 with filler (the bloggy-long failure mode), or they over-document the topic with no editorial spine (the academic-bloat failure mode). The pieces that earn their length are the ones where each section justifies its weight, the lede sets a thesis the body actually delivers, and the closing leaves the reader with something specific.
This skill covers the individual long-form piece: the case study, the whitepaper, the research report, the manifesto, the ebook chapter or full ebook, the definitive guide, the long-form tutorial. Different from `pillar-content-architecture` (which covers HUB architecture: how a pillar plus cluster system fits together), this skill covers the long-form PIECE itself, regardless of whether it sits at the center of a hub or stands alone.
The voice is the senior editorial leader who has shipped dozens of flagship long-form assets and watched plenty of others fail. Honest about which formats earn their length, which structural archetypes fit which problems, and where long-form most often goes wrong.
When to use this skill: planning a flagship long-form piece, structuring a draft that feels saggy, reviewing a long-form piece that is technically correct but emotionally flat, or auditing a content library to find the long-form pieces that should have been blog posts.
---
media-asset-management
When your agent uses it
Plan and run a media pipeline for images, video, and downloadable assets. Use this skill when designing image storage and delivery, choosing formats (WebP, AVIF), setting up responsive images, picking a video host, organizing a brand asset library, or auditing a slow image pipeline. Triggers on image pipeline, asset library, DAM, image optimization, WebP, AVIF, responsive images, video hosting, image CDN, asset workflow, media management. Also triggers when images are slow, broken, or scattered across systems.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
2,722 tokensWhen the skill is activated
Reference documents
2,892 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 stages
- Format reference
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc363 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesSKILL.mdcore12,160 bytesreferences/responsive-image-patterns.mddoc10,442 bytes
Read SKILL.md
# Media Asset Management
Design how images, video, and downloadable files get stored, processed, organized, and served. Stack-agnostic. The principles apply whether you're running a custom pipeline or using a hosted service.
---
## When to use
- Designing or redesigning the image and media pipeline
- Choosing a media CDN or image service
- Setting up responsive image delivery
- Planning a digital asset management (DAM) system
- Auditing media performance issues
- Picking video hosting and embedding strategymonitoring-and-alerting
When your agent uses it
Design and run a monitoring system for a website or web app. Use this skill when setting up uptime checks, defining SLOs, configuring error tracking, choosing what to alert on, designing on-call rotations, or fixing alert fatigue. Triggers on monitoring, alerts, uptime, SLO, SLA, error rate, on-call, pager, alert fatigue, observability, dashboards, what should we monitor. Also triggers when an incident reveals a gap in monitoring.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,426 tokensWhen the skill is activated
Reference documents
2,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 layers
- SLOs and error budgets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc364 bytesSKILL.mdcore10,455 bytesSKILL.mdcore10,455 bytesreferences/slo-design-guide.mddoc9,231 bytes
Read SKILL.md
# Monitoring and Alerting
Decide what to watch, what to alert on, and how to make sure the right person finds out when things break.
---
## When to use
- Setting up monitoring on a new site or service
- Defining SLOs (service level objectives) and error budgets
- Choosing which alerts page someone vs which go to a quiet channel
- Designing or fixing on-call rotation
- Diagnosing alert fatigue
- Filling monitoring gaps revealed by an incidentmulti-step-form-design
When your agent uses it
Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent. Honest about kitchen-sink-single-page (overwhelms before the user starts), progress-theater (steps without genuine staging), and genuinely-staged (each step earns its own page) patterns. Triggers on multi-step form, multi-page form, form wizard, signup wizard, lead form, application form, intake form, configurator, onboarding form. Also triggers when a long form is converting poorly, when an audience is dropping off mid-form, or when a multi-step form is being scoped for the first time.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
4,502 tokensWhen the skill is activated
Reference documents
18,556 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The multi-step decision: when to break into steps vs keep single-page
- Kitchen-sink-single-page vs progress-theater vs genuinely-staged
- Step architecture: what belongs on each step
- Progress indicator design
- Conditional logic
- Save-and-resume mechanics
- Validation strategy
- Drop-off measurement and remediation
- Form anti-patterns
- Common failure modes
- The framework: 12 considerations for multi-step form design
- If required data is unavailable
- Reference files
- Closing: multi-step forms earn completion when each step earns its place
Files
README.mddoc363 bytesSKILL.mdcore21,950 bytesSKILL.mdcore21,950 bytesreferences/common-multi-step-form-failures.mddoc9,115 bytesreferences/conditional-logic-patterns.mddoc9,842 bytesreferences/drop-off-measurement-and-remediation.mddoc10,513 bytesreferences/form-anti-patterns.mddoc9,904 bytesreferences/multi-step-decision-criteria.mddoc9,397 bytesreferences/progress-indicator-patterns.mddoc9,529 bytesreferences/save-and-resume-mechanics.mddoc10,296 bytesreferences/step-architecture-patterns.mddoc10,195 bytesreferences/validation-strategy-patterns.mddoc10,607 bytes
Read SKILL.md
# Multi-Step Form Design
A senior growth practitioner's playbook for designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent.
Most multi-step forms are either kitchen-sink-single-pages dressed up as steps or arbitrary chunking that adds friction without adding clarity. The form looks more sophisticated; the completion rate does not move; the audience is no better served than before.
The multi-step forms that work do something different. Each step represents a coherent unit of cognitive work the user can complete with confidence. Progress indicators reinforce momentum. Conditional logic responds to earlier answers and removes irrelevant fields. The form feels like a guided process, not an obstacle course.
The voice is the senior growth practitioner who has watched multi-step forms convert at twice the single-page rate and watched them collapse to half. Practical, opinionated about when steps add value and when they add friction, willing to call out arbitrary chunking that does not earn its complexity.
When to use this skill: scoping a multi-step form for the first time, auditing a long single-page form that converts poorly, deciding when to break a form into steps and when to keep it on one page, or designing the conditional logic that makes the form feel adaptive.
---
okr-design
When your agent uses it
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition with quarterly accountability). Triggers on OKR design, OKR setting, key result design, OKR scoring, mid-quarter recalibration, OKR cascading, outcomes vs outputs, quarterly planning, goal setting. Also triggers when a team's OKRs are always hit and producing no learning, when OKRs are demoralizing because they were set as fantasy, or when the team uses OKR vocabulary but the practice has decayed.
What it loads into context
Frontmatter
231 tokensAlways available to the agent
SKILL.md
4,861 tokensWhen the skill is activated
Reference documents
18,633 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Sandbagged vs aspirational-fantasy vs stretch
- Objective design
- Key result design
- Cascading OKRs across the org
- Scoring discipline
- Mid-quarter recalibration
- The OKR review cadence
- OKRs vs roadmap items vs metrics
- Common failure modes
- The framework: 12 considerations for OKR design
- If required data is unavailable
- Reference files
- Closing: OKRs are accountability infrastructure
Files
README.mddoc351 bytesSKILL.mdcore22,458 bytesSKILL.mdcore22,458 bytesreferences/cascading-okrs-decisions.mddoc9,261 bytesreferences/common-okr-failures.mddoc9,801 bytesreferences/key-result-design-patterns.mddoc10,108 bytesreferences/mid-quarter-recalibration.mddoc9,998 bytesreferences/objective-design-patterns.mddoc9,503 bytesreferences/okr-anti-patterns.mddoc10,791 bytesreferences/okrs-vs-roadmap-vs-metrics.mddoc9,051 bytesreferences/review-cadence-templates.mddoc9,910 bytesreferences/scoring-discipline.mddoc9,650 bytes
Read SKILL.md
# OKR Design
A senior product leader's playbook for OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the practical disciplines that distinguish OKRs from quarterly to-do lists or impossible-fantasy goal-setting.
OKRs are accountability infrastructure. When designed well, they produce a quarterly rhythm of ambitious goal-setting, mid-quarter learning, end-of-quarter scoring, and adjustment for the next quarter. When designed badly, they become a tax on the team that produces no signal: sandbagged OKRs that always hit 100% (no ambition, no learning), aspirational fantasy OKRs that nobody can hit (demoralizing, ignored after week 2), or vague OKRs that the team scores generously regardless of outcome.
This skill is OKR design as practical methodology. The teams that benefit from OKRs are the ones that hold the discipline: outcomes over outputs, key results that actually measure the outcome, scoring honestly even when uncomfortable, recalibrating mid-quarter when warranted, and using the OKR review cadence to drive learning rather than performance theater.
The voice is the senior product leader who has run OKRs in healthy organizations and watched the practice decay in others. Concrete, opinionated about what actually works, willing to call out the failure modes that conference talks gloss over.
When to use this skill: designing OKRs for the next quarter, auditing why current OKRs are not driving decisions, recalibrating an OKR practice that has decayed, or onboarding a team to OKRs that has never used them.
---
onboarding-wizard-design
When your agent uses it
Designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. Honest about tutorial-overload (dump everything upfront), skip-friendly-empty (skipped onboarding leads to abandoned product), and earned-progressive-disclosure (right things at the right moments) patterns. Triggers on onboarding wizard, product onboarding, first-run experience, signup flow, activation flow, FRX, time-to-value, ah-ha moment design. Also triggers when activation rates are low, when users skip onboarding and never return, when onboarding flows are being scoped for the first time, or when audience research shows users not finding key features.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
4,250 tokensWhen the skill is activated
Reference documents
14,038 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The wizard decision: when wizards earn vs when contextual help suffices
- Tutorial-overload vs skip-friendly-empty vs earned-progressive-disclosure
- Step architecture: what belongs in each step, sequence logic
- The ah-ha moment design
- Progressive disclosure patterns
- Skip and resume mechanics
- Drop-off measurement and remediation
- Wizard variations by user type
- Common failure modes
- The framework: 12 considerations for onboarding wizard design
- Reference files
- Closing: wizards earn the user's first session
Files
README.mddoc365 bytesSKILL.mdcore20,722 bytesreferences/ah-ha-moment-engineering.mddoc8,665 bytesreferences/common-onboarding-failures.mddoc6,305 bytesreferences/drop-off-measurement-templates.mddoc7,421 bytesreferences/progressive-disclosure-patterns.mddoc7,744 bytesreferences/skip-and-resume-mechanics.mddoc8,137 bytesreferences/step-architecture-patterns.mddoc8,267 bytesreferences/user-type-variation-patterns.mddoc6,413 bytesreferences/wizard-anti-patterns.mddoc7,636 bytesreferences/wizard-decision-criteria.mddoc7,484 bytes
Read SKILL.md
# Onboarding Wizard Design
A senior product marketing director's playbook for designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. The discipline of building an onboarding sequence the user actually completes.
Most product onboarding wizards fail in one of two ways. They cram every feature into a 12-step intro the user has not earned the patience for. Or they offer a "skip onboarding" button so prominent that users skip into an empty product with no context, and then churn the next day because they never found the value. The activation rate is the metric that matters, and most wizards are optimizing for the wrong thing.
The wizards that work do something different. Each step earns the user one step closer to value. The wizard surfaces the right thing at the right moment, not everything upfront. Skip exists but is balanced against staying engaged. The user reaches the ah-ha moment with a sense that the product respected their time.
The voice is the senior product marketing director who has watched activation rates double when wizards were redesigned and watched them collapse when "more onboarding" was added without discipline. Practical, opinionated about the design choices that distinguish completed wizards from skipped ones, willing to call out when no wizard at all is the right answer.
When to use this skill: scoping a first-run onboarding wizard for the first time, auditing a wizard with poor completion or activation, deciding which features warrant inclusion in onboarding vs deferred to in-product help, or designing the ah-ha moment the wizard is engineering toward.
---
oss-contribution-research
When your agent uses it
Research and prepare an outside contribution to an open-source repo, then stop at a queue item for a human to approve: policy check, intake, duplicate check, reproduction, patch, the repo's own checks, an independent critic rerun, and a disclosed, hashed draft of the exact text to post. Use this skill whenever the user wants to contribute to someone else's repo, fix an upstream bug, pick up a good-first-issue, draft an AI-assisted pull request for an outside project, follow up on their own outside PR, or run a gated contribution pipeline. Triggers on open source contribution, contribute to this repo, upstream fix, outside PR, external PR, good first issue, fix this issue in their repo, contribution research, AI-assisted PR, disclose AI in PR, reply to review on my PR. Also triggers when the user names an issue in a repo they do not maintain and asks for a fix, even if they do not say contribute.
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
4,438 tokensWhen the skill is activated
Reference documents
6,298 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: gates in order, stop at the first fail
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc366 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesSKILL.mdcore19,263 bytesreferences/example-intake-item.mddoc3,366 bytesreferences/policy-classification.mddoc5,088 bytesreferences/pr-description-template.mddoc5,476 bytesreferences/queue-item-template.mddoc6,802 bytesreferences/repro-record-template.mddoc4,985 bytes
Read SKILL.md
# OSS Contribution Research
Prepare one outside contribution to an open-source repo, gate by gate, and stop at a queue item a human approves. The agent running this skill never posts.
---
## When to use
- Picking up an existing issue or confirmed bug in a repo the user does not maintain
- Checking whether a repo accepts AI-assisted pull requests before any work starts
- Asking a maintainer for a go-ahead before writing a patch (an intake comment)
- Turning a fix into a small, disclosed pull request draft that a human approves
- Following up on the user's own outside pull request: a review reply, the 14-day ping, or the 28-day close
- Running a contribution pipeline with an approval queue and a per-repo registrypaid-media-strategy
When your agent uses it
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media strategy, ad budget allocation, channel selection, paid media plan, audit my Google Ads, audit my Meta Ads, scale paid media, kill underperforming campaign, paid media hypothesis, ad spend strategy, attribution reality, performance marketing strategy. Also triggers when a team is asking how to scale paid media, or whether to add a new channel, or how to reallocate spend across channels.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
4,664 tokensWhen the skill is activated
Reference documents
10,699 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Hypothesis discipline for paid spend
- Channel selection: when to use which platform
- Budget allocation: brand vs performance, baseline vs test
- Audience targeting: prospecting vs retargeting vs exclusion
- Bid strategy: when each fits
- Campaign types
- What NOT to spend on
- Creative testing: within campaign vs across campaign
- Frequency capping
- Attribution mismatch: platform-reported vs actual
- Common failures
- The framework: 11 considerations for sustainable paid media
- If required data is unavailable
- Reference files
- Closing: when in doubt, kill the campaign
Files
README.mddoc360 bytesSKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesSKILL.mdcore22,384 bytesreferences/ads-platform-comparison.mddoc7,238 bytesreferences/audience-segmentation-patterns.mddoc6,779 bytesreferences/bid-strategy-reference.mddoc6,441 bytesreferences/budget-allocation-templates.mddoc5,725 bytesreferences/campaign-type-reference.mddoc8,243 bytesreferences/channel-decision-matrix.mddoc5,956 bytesreferences/common-failures.mddoc8,642 bytes
Read SKILL.md
# Paid Media Strategy
A senior performance marketer's playbook for running paid media that produces real outcomes.
The default state of paid media is wasted spend. Most accounts have campaigns running because they always have, audiences targeting because the rep suggested it, bid strategies on auto because manual is hard, creative not refreshed because there is no system. The cost compounds. A 20% efficiency gain on a $500K-per-year account is $100K back to the business. A 50% gain on a $5M-per-year account is $2.5M.
This skill is the discipline that produces those gains. It assumes you have a paid media platform (Google Ads, Meta, LinkedIn, TikTok, or aggregators like Synter) connected. It assumes you have working analytics and conversion tracking. The hard part is the strategic discipline behind the spend, and that is what is here.
When to use this skill: any time you are designing a paid media plan, evaluating whether to scale or kill a campaign, allocating budget across channels, or auditing an existing account.
---
## What this skill is for
performance-optimization
When your agent uses it
Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
2,449 tokensWhen the skill is activated
Reference documents
5,263 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: Core Web Vitals
- Beyond Core Web Vitals
- Workflow
- Tools
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc365 bytesSKILL.mdcore10,763 bytesSKILL.mdcore10,763 bytesSKILL.mdcore10,763 bytesreferences/audit-template.mddoc5,602 bytesreferences/optimization-checklist.mddoc5,634 bytesreferences/optimization-playbook.mddoc9,303 bytes
Read SKILL.md
# Performance Optimization
Diagnose web performance issues and produce a remediation plan. Stack-agnostic. Anchored to Core Web Vitals and standard browser performance patterns.
This skill goes deeper than the performance checks in `qa-testing` and `seo-technical`. Use this when performance itself is the goal.
---
## When to use
- Fixing Core Web Vitals (LCP, INP, CLS)
- Diagnosing slow page loads
- Reducing JavaScript bundle size
- Optimizing images, fonts, and other assetspillar-content-architecture
When your agent uses it
How to design a content hub that earns topical authority. Pillar topic selection, cluster planning, internal linking architecture, URL structure, pillar and cluster page anatomy, topical authority signals for SEO and AEO/GEO, and the maintenance discipline that distinguishes intentional hubs from accidental orphans. Triggers on pillar content, content hub, topic cluster, topical authority, content architecture, hub and spoke, pillar page, cluster page, content silo, internal linking strategy. Also triggers when a content set is not ranking despite individual piece quality, when a pillar was launched without a cluster, or when content has accumulated without an architecture.
What it loads into context
Frontmatter
177 tokensAlways available to the agent
SKILL.md
4,719 tokensWhen the skill is activated
Reference documents
15,475 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- Pillar vs cluster vs orphan content
- Topic selection for pillar pages
- Cluster planning
- Internal linking architecture
- URL structure and information architecture
- Pillar page anatomy
- Cluster piece anatomy
- Topical authority signals
- Maintenance and refresh patterns
- Common failure modes
- The framework: 12 considerations for hub architecture
- If required data is unavailable
- Reference files
- Closing: architecture is the moat
Files
README.mddoc368 bytesSKILL.mdcore22,093 bytesSKILL.mdcore22,093 bytesreferences/cluster-piece-anatomy.mddoc6,439 bytesreferences/cluster-planning-patterns.mddoc6,294 bytesreferences/common-pillar-failures.mddoc9,390 bytesreferences/content-refresh-patterns.mddoc7,972 bytesreferences/internal-linking-architecture.mddoc7,222 bytesreferences/pillar-cluster-decision.mddoc5,860 bytesreferences/pillar-page-anatomy.mddoc7,443 bytesreferences/topic-selection-criteria.mddoc6,377 bytesreferences/topical-authority-signals.mddoc7,006 bytesreferences/url-structure-patterns.mddoc6,327 bytes
Read SKILL.md
# Pillar Content Architecture
A senior content architect's playbook for designing content hubs that earn topical authority.
Most content programs accumulate accidentally. Pieces ship one at a time, internal linking happens (or does not) in editing, similar topics get covered by multiple pieces with no coordination, and six months later the team has a content set that looks like a sitemap but feels like a yard sale. Search engines see disconnected pages; AI engines see scattered citations; readers cannot tell which piece is the entry point and which is the reference.
This skill is the discipline of intentional hub architecture. It assumes you have decided which topic areas to invest in (see `content-strategy`) and have keyword data (see `seo-keyword`). It does not write any individual piece (see `content-brief-authoring` for per-piece work and `content-and-copy` for execution). What it does is design the structure: which topic gets a pillar, which subtopics get cluster pieces, how the pieces link to each other, where they live in the URL hierarchy, and what topical authority signals the architecture is engineered to produce.
When to use this skill: launching a new content hub, restructuring an existing content set into a hub, deciding whether a piece should be a pillar or a cluster, or auditing why a content area is not ranking despite individual piece quality.
---
## What this skill is for
pm-spec-writing
When your agent uses it
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
2,068 tokensWhen the skill is activated
Reference documents
4,715 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 4 phases
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc1,724 bytesSKILL.mdcore8,907 bytesSKILL.mdcore8,907 bytesreferences/dev-brief-template.mddoc6,155 bytesreferences/feature-spec-template.mddoc4,691 bytesreferences/prioritization-frameworks.mddoc6,889 bytes
Read SKILL.md
# PM Spec Writing
Take an idea (often vague) and turn it into a specification a developer or AI agent can actually build from. Stack-agnostic. Works for new features, bug fixes, content changes, or infrastructure work.
---
## When to use
- Translating an idea into a buildable feature spec
- Writing a PRD or product requirement document
- Filing a bug report that someone else can act on
- Scoping a project before kickoff
- Prioritizing a backlog of feature requests
- Writing acceptance criteria for an existing featureproduct-analytics-setup
When your agent uses it
How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
4,983 tokensWhen the skill is activated
Reference documents
15,624 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- The instrumentation hierarchy
- Event taxonomy design
- Property design: event-level vs user-level
- Naming conventions
- Schema versioning
- Funnel design
- Cohort definitions
- Retention measurement
- North Star and supporting metrics
- The trustable dashboard principle
- Instrumentation debt
- Common failure modes
- The framework: 12 considerations for trustable product analytics
- If required data is unavailable
- Reference files
- Closing: when in doubt, instrument less
Files
README.mddoc364 bytesSKILL.mdcore23,754 bytesSKILL.mdcore23,754 bytesSKILL.mdcore23,754 bytesreferences/cohort-definition-patterns.mddoc7,519 bytesreferences/common-failures.mddoc9,554 bytesreferences/event-taxonomy-template.mddoc7,741 bytesreferences/funnel-design-templates.mddoc7,741 bytesreferences/instrumentation-audit-checklist.mddoc7,398 bytesreferences/naming-convention-reference.mddoc5,956 bytesreferences/north-star-metric-selection.mddoc8,027 bytesreferences/property-design-patterns.mddoc6,781 bytesreferences/schema-versioning-patterns.mddoc7,061 bytes
Read SKILL.md
# Product Analytics Setup
A senior PM and analyst's playbook for instrumenting product analytics correctly the first time.
Most product analytics setups are some combination of inherited mistakes, dashboard sprawl, and events nobody trusts. The team launches a new feature; instrumentation gets bolted on under deadline pressure; naming drifts; properties are inconsistent; six months later nobody can answer simple questions because the answer depends on which event you trust.
This skill is the discipline that prevents that. It assumes you have answered the strategic questions about what to measure (see `analytics-strategy`). It assumes you have a tool connected (Mixpanel, Heap, PostHog, Amplitude, or warehouse-native via BigQuery, Snowflake, or dbt). The hard part is the systematic execution: naming conventions, property design, schema versioning, funnel construction, cohort definitions, retention measurement.
When to use this skill: setting up product analytics from scratch, auditing an existing instrumentation, fixing a "we have data but cannot trust it" problem, or designing instrumentation for a new feature.
---
## What this skill is for
product-configurator-design
When your agent uses it
Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus meaningful constraints plus escape hatches) patterns. Triggers on configurator design, build-your-own, custom configuration, plan builder, product customizer, configuration tool. Also triggers when users abandon mid-configuration, when configurator conversion is poor, or when a configurator is being scoped for the first time.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
3,262 tokensWhen the skill is activated
Reference documents
8,199 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The configurator decision: when configurators earn investment vs when bundles suffice
- Infinite-options vs canned-bundles-only vs guided-configuration
- Default-configuration design
- Constraint logic
- Real-time pricing and impact display
- Validation and error patterns
- Save-and-share mechanics
- Configurator-to-cart handoff
- Common failure modes
- The framework: 12 considerations for configurator design
- Reference files
- Closing: configurators earn investment when they earn the configuration that ships
Files
README.mddoc368 bytesSKILL.mdcore16,741 bytesreferences/common-configurator-failures.mddoc5,145 bytesreferences/configurator-anti-patterns.mddoc5,057 bytesreferences/configurator-decision-criteria.mddoc4,204 bytesreferences/configurator-to-cart-handoff.mddoc4,526 bytesreferences/constraint-logic-patterns.mddoc4,485 bytesreferences/default-configuration-design.mddoc2,978 bytesreferences/real-time-pricing-patterns.mddoc4,007 bytesreferences/save-and-share-mechanics.mddoc5,134 bytesreferences/validation-and-error-patterns.mddoc4,810 bytes
Read SKILL.md
# Product Configurator Design
A senior product marketing director's playbook for designing build-your-own product configurators. Tesla-style vehicle configurators, custom-pricing builders, plan-builders, product customizers. Constraint logic, real-time pricing, validation, save-and-share mechanics. The discipline of building a configurator that produces configurations users actually commit to.
Most configurators fail in one of two ways. They expose every parameter at full granularity (47 toggles, 12 sliders) and produce decision paralysis; users abandon halfway through. Or they pretend to be configurators but are actually three pre-built bundles labeled "Custom"; the configurator framing was marketing while the product is bundles.
The configurators that work do something different. Smart defaults that produce a sensible starting configuration; meaningful constraints that prevent invalid combinations and surface why; escape hatches into deeper customization for users who want it; real-time pricing that responds to choices. Users feel guided rather than overwhelmed.
The voice is the senior product marketing director who has watched configurators double conversion when redesigned with smart defaults and watched them collapse when "more options" were added without constraint logic. Practical, opinionated about the constraints that protect users from themselves, willing to call out when canned bundles are the right answer.
When to use this skill: scoping a build-your-own configurator for the first time, auditing a configurator with high abandonment, designing the constraint logic that prevents invalid combinations, or deciding which parameters earn exposure vs which should default.
---
programmatic-seo
When your agent uses it
How to design and run a programmatic SEO program that produces durable traffic instead of penalty-bait. Data source identification, template design, schema patterns, quality control at scale, internal linking architecture, crawl budget management, AEO/GEO for programmatic pages, refresh discipline, and the make-or-break question of whether pSEO is the right answer for your program at all. Triggers on programmatic SEO, pSEO, scaled content, page generation, template SEO, location pages, comparison pages, directory site, listing site, scaled landing pages, programmatic content. Also triggers when a content set is not ranking, has been hit by an algorithm update, or when a team is considering pSEO as a growth lever.
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
5,170 tokensWhen the skill is activated
Reference documents
15,811 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill is for
- When pSEO is the right answer
- Data source identification
- Template design
- Schema design
- Quality control at scale
- Internal linking across the set
- Crawl budget management
- AEO and GEO for programmatic pages
- Refresh and maintenance at scale
- Common failure modes
- The framework: 12 considerations for programmatic SEO
- If required data is unavailable
- Reference files
- Closing: quality at scale or not at all
Files
README.mddoc357 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesSKILL.mdcore25,081 bytesreferences/aeo-geo-for-programmatic-pages.mddoc7,984 bytesreferences/common-pseo-failures.mddoc10,408 bytesreferences/crawl-budget-management.mddoc7,087 bytesreferences/data-source-identification-patterns.mddoc6,693 bytesreferences/internal-linking-at-scale.mddoc7,396 bytesreferences/quality-control-at-scale.mddoc7,880 bytesreferences/refresh-at-scale.mddoc7,454 bytesreferences/schema-design-patterns.mddoc7,817 bytesreferences/template-design-patterns.mddoc6,634 bytesreferences/when-pseo-works-decision.mddoc6,952 bytes
Read SKILL.md
# Programmatic SEO
A senior SEO strategist's playbook for designing and running programmatic SEO programs that produce durable traffic instead of penalty-bait.
Programmatic SEO has a complicated reputation. Sites like Zillow, Airbnb, TripAdvisor, Indeed, and Yelp have built billion-dollar traffic engines on pSEO. Other sites have built pSEO programs that got hit by Google's helpful-content updates and lost 80% of their traffic in a week. The difference is rarely the technique; it is the underlying data quality and the quality control discipline at scale.
This skill is the playbook for getting that distinction right. It assumes you have decided what keyword space to target (see `seo-keyword`) and how the broader content program is shaped (see `content-strategy`). It does not write individual editorial pieces (see `content-and-copy` for that) and does not architect editorial topic hubs (see `pillar-content-architecture` for that). What it does is teach the discipline of generating high-volume pages programmatically from structured data sources without producing thin content, duplicate content, or scale-without-substance pages that get penalized.
When to use this skill: deciding whether pSEO is a fit for the program at all (the most important question), designing a new pSEO system, auditing an existing pSEO set that is not ranking or has been hit by an algorithm update, or building quality-control discipline for a pSEO program that grew faster than its quality processes.
---
## What this skill is for
qa-testing
When your agent uses it
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
3,248 tokensWhen the skill is activated
Reference documents
1,268 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 3 tiers
- Specific QA snippets
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc351 bytesSKILL.mdcore12,894 bytesSKILL.mdcore12,894 bytesreferences/qa-report-template.mddoc4,363 bytes
Read SKILL.md
# QA Testing
Verify that a page, feature, or site is working before declaring it shipped. Stack-agnostic. Console-snippet driven for speed.
This skill is faster than `accessibility-audit` (which goes deeper on WCAG) and `performance-optimization` (which goes deeper on Core Web Vitals). Use this skill for general QA. Use the specialists for deep audits.
---
## When to use
- After every deploy (smoke test)
- After launching a new page or feature (standard audit)
- Before a major release (full release matrix)
- Investigating a "something looks off" reportquiz-and-assessment-design
When your agent uses it
Designing quizzes, personality assessments, and recommendation tools that segment users into actionable categories rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping, lead capture integration. Honest about clickbait-quiz (engagement only), vanity-result (entertaining, not useful), and actionable-segmentation (genuine categorization that drives next-step recommendations) patterns. Triggers on quiz, assessment, personality test, recommendation tool, scorecard, diagnostic, fit evaluator, what-type-of-X-are-you, persona quiz. Also triggers when an audience needs a categorization-driven lead magnet, when a vanity quiz is producing engagement but no qualified leads, or when an assessment is being scoped for the first time.
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
4,340 tokensWhen the skill is activated
Reference documents
18,994 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The quiz/assessment decision: when this format earns investment
- Clickbait-quiz vs vanity-result vs actionable-segmentation
- Question architecture
- Scoring algorithms
- Result categorization
- Result-to-recommendation mapping
- Lead capture integration
- Quiz anti-patterns
- Common failure modes
- The framework: 12 considerations for quiz and assessment design
- Reference files
- Closing: quizzes earn engagement when they earn the next step
Files
README.mddoc367 bytesSKILL.mdcore21,637 bytesSKILL.mdcore21,637 bytesreferences/clickbait-vs-actionable-distinctions.mddoc10,891 bytesreferences/common-quiz-failures.mddoc9,721 bytesreferences/lead-capture-integration-patterns.mddoc10,098 bytesreferences/question-architecture-patterns.mddoc10,502 bytesreferences/quiz-anti-patterns.mddoc10,555 bytesreferences/quiz-investment-criteria.mddoc9,217 bytesreferences/result-categorization-patterns.mddoc10,462 bytesreferences/result-to-recommendation-mapping.mddoc11,699 bytesreferences/scoring-algorithm-patterns.mddoc11,391 bytes
Read SKILL.md
# Quiz and Assessment Design
A senior growth practitioner's playbook for designing quizzes and assessments that produce actionable segmentation rather than generating clicks for clicks' sake. Question architecture, scoring algorithms, result categorization, recommendation mapping. The discipline of building a quiz the audience actually uses to make a decision.
Most quizzes on the web are clickbait. "What kind of pizza are you?" energy applied to brand-building, with results that flatter the taker but drive no specific next step. The quiz captures emails because the format implies fun; the leads are unqualified because the result told them nothing they could act on.
The quizzes that work as compounding assets do something different. They categorize the taker into a defined segment with a specific recommendation matched to that segment. The taker comes away knowing what to do next, not just what they are. The brand becomes the source of the recommendation the audience acted on.
This skill is one of the specific lead-magnet types covered as its own skill. The parent-frame methodology lives in `lead-magnet-design`; the quiz-specific methodology (scoring algorithms, result categorization, recommendation matching) lives here.
The voice is the senior growth practitioner who has watched quizzes earn long-term subscribers and watched them produce engagement metrics with no downstream impact. Practical, opinionated about the difference between fun-quiz and decision-quiz, willing to call out when a quiz is the wrong format for the goal.
When to use this skill: scoping a quiz or assessment for the first time, auditing a quiz that produces engagement but no qualified leads, designing the result categories that drive specific recommendations, or deciding which inputs warrant the lead-capture step.
roadmap-planning
When your agent uses it
Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next, sequencing, prioritization, OKR planning, capacity planning, what's on the roadmap, plan the year, what to ship next quarter. Also triggers when stakeholders are pulling in different directions and the team needs a defensible plan.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
2,462 tokensWhen the skill is activated
Reference documents
1,861 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- Reference files
Files
README.mddoc357 bytesSKILL.mdcore10,981 bytesreferences/prioritization-frameworks.mddoc8,044 bytes
Read SKILL.md
# Roadmap Planning
Take a pile of ideas, requests, and ongoing work. Produce a defensible plan for what to ship, when, and why. The output is a roadmap document plus the prioritization work that made it credible.
---
## When to use
- Planning the next quarter or the next year
- Sequencing work where some items depend on others
- Balancing new builds, improvements, and maintenance
- Saying no (or "not yet") to specific requests with a defensible reason
- Aligning a team around a single shared plan
- Communicating the plan to stakeholders outside the teamscheduler-and-booking-design
When your agent uses it
Designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic Calendly link. Availability logic, qualification gating, prep automation, follow-up sequencing. Honest about any-time-friction (no qualification, just a booking link), interrogation-gate (so much qualification it scares users off), and qualified-fast-path (just enough qualification to set up the call well) patterns. Triggers on scheduler design, meeting booking, demo scheduling, sales call scheduling, calendar tool, booking page, qualification flow. Also triggers when sales team complains about cold demos, when booking conversion is poor, or when scheduler is being scoped for the first time.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
3,637 tokensWhen the skill is activated
Reference documents
12,662 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- The booking-flow decision: scheduler vs forms vs sales-pipeline tools
- Any-time-friction vs interrogation-gate vs qualified-fast-path
- Qualification field design
- Availability logic
- Routing patterns
- Prep automation
- Confirmation and reminder sequences
- Reschedule and no-show handling
- Common failure modes
- The framework: 12 considerations for scheduler and booking design
- Reference files
- Closing: schedulers earn the booking when they earn the better call
Files
README.mddoc369 bytesSKILL.mdcore17,744 bytesSKILL.mdcore17,744 bytesreferences/availability-logic-patterns.mddoc7,422 bytesreferences/common-scheduler-failures.mddoc5,777 bytesreferences/prep-automation-patterns.mddoc7,162 bytesreferences/qualification-field-design.mddoc7,144 bytesreferences/reminder-sequence-patterns.mddoc6,530 bytesreferences/reschedule-and-no-show-handling.mddoc6,899 bytesreferences/routing-patterns.mddoc6,007 bytesreferences/scheduler-anti-patterns.mddoc5,811 bytesreferences/scheduler-decision-criteria.mddoc7,105 bytes
Read SKILL.md
# Scheduler and Booking Design
A senior growth practitioner's playbook for designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic booking link. Availability logic, qualification gating, prep automation, follow-up sequencing. The discipline of building a scheduler that earns the booking by earning a better call.
Most schedulers fail in one of two ways. Generic booking links produce cold demos where reps know nothing about the person they are about to talk to. Conversion stays at the rate of unqualified raw demos. Or qualification forms with 12 fields scare users off before they can book; drop-off at the form approaches 90 percent; only the leads who happen to survive the form actually convert.
The schedulers that work do something different. Just enough qualification to set up the call well (3-5 strategic fields), context-aware availability (high-fit leads see senior reps; low-fit leads route differently), prep automation that briefs the rep before the call. The booking is honest about who the audience is; the call is set up to succeed.
The voice is the senior growth practitioner who has watched schedulers double demo conversion when redesigned and watched them collapse when more qualification was added. Practical, opinionated about which fields earn their place, willing to call out when the booking flow is the wrong tool.
When to use this skill: scoping a scheduler for the first time, auditing a booking flow with poor conversion or poor downstream call quality, designing the qualification gate that produces context without producing friction, or deciding routing logic that matches leads to the right reps.
---
security-baseline
When your agent uses it
Establish a security baseline for a website or web app. Use this skill when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, doing a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scan, security audit, harden, OWASP, security baseline. Also triggers when a security review is required for compliance or before going live.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,645 tokensWhen the skill is activated
Reference documents
2,094 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 layers
- Content Security Policy
- Workflow
- Common compliance touchpoints
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc358 bytesSKILL.mdcore11,973 bytesSKILL.mdcore11,973 bytesSKILL.mdcore11,973 bytesreferences/headers-checklist.mddoc8,049 bytes
Read SKILL.md
# Security Baseline
Establish the security floor for any production website or web app. Stack-agnostic. Covers the things that should be in place before public launch and verified periodically after.
---
## When to use
- Pre-launch security review
- Setting up a new site or environment
- Periodic security audit (quarterly recommended)
- Onboarding a new vendor or third-party integration
- Responding to a security finding or report
- Hardening after an incidentseo-aeo-geo
When your agent uses it
Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI assistants. Use this skill whenever the user wants to optimize for AI search, get cited by language models, appear in AI overviews, build llms.txt, structure content for AI extraction, or future-proof their SEO for the shift from blue links to AI answers. Triggers on AEO, GEO, AI search, AI SEO, AI overview, generative search, LLM optimization, llms.txt, AI citation, ChatGPT search, Perplexity, Gemini, Claude search, AI assistant optimization, answer engine. Also triggers when the user expresses concern about AI eating their organic traffic or wants to understand how to remain visible as search shifts.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
1,991 tokensWhen the skill is activated
Reference documents
4,281 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 layers
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc352 bytesSKILL.mdcore9,146 bytesSKILL.mdcore9,146 bytesSKILL.mdcore9,146 bytesreferences/extraction-friendly-patterns.mddoc10,550 bytesreferences/llms-txt-guide.mddoc7,985 bytes
Read SKILL.md
# AEO and GEO
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO). Make content discoverable, extractable, and citable by AI search experiences.
This skill encodes principles. AI search products evolve fast. The principles age slower than the products.
---
## When to use
- Optimizing content for AI overviews and generative answer engines
- Building or updating llms.txt
- Structuring content so AI assistants can extract and cite it correctly
- Future-proofing a site as search shifts from blue links to AI answersseo-audit-orchestration
When your agent uses it
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
1,919 tokensWhen the skill is activated
Reference documents
1,615 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 6 phases of an end-to-end audit
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc364 bytesSKILL.mdcore8,441 bytesSKILL.mdcore8,441 bytesreferences/audit-rollup-template.mddoc5,704 bytes
Read SKILL.md
# SEO Audit Orchestration
Run a complete SEO audit by sequencing the sibling audit skills in a defined order. Stack-agnostic. Assumes the Ahrefs MCP is connected. Produces a single rollup report that synthesizes findings across backlinks, keywords, content, traffic, technical health, and rankings.
---
## When to use
- Running a full SEO audit (quarterly, biannual, annual)
- Pre-acquisition SEO due diligence
- Post-migration verification (after content move, replatform, or domain change)
- Onboarding a new client or new property
- Building a baseline before a major SEO investment
- Diagnosing chronic underperformanceseo-backlink-audit
When your agent uses it
Audit a backlink profile using Ahrefs MCP data: profile health, anchor text distribution, toxic link identification, lost link reclamation, and gap analysis against competitors. Use this skill when reviewing backlink health, scoping a disavow project, recovering from a manual action, planning link building, or doing M&A due diligence on a property's link equity. Triggers on backlink audit, link profile, toxic links, disavow, anchor text analysis, lost links, link reclamation, referring domains, link gap. Also triggers when traffic decline correlates with link loss or when an unnatural link warning appears in Search Console.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
1,718 tokensWhen the skill is activated
Reference documents
1,436 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 dimensions of a backlink profile
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc359 bytesSKILL.mdcore7,804 bytesSKILL.mdcore7,804 bytesSKILL.mdcore7,804 bytesreferences/toxic-link-criteria.mddoc5,888 bytes
Read SKILL.md
# SEO Backlink Audit
Audit a backlink profile using data pulled from the Ahrefs MCP. Stack-agnostic. Produces a profile health assessment, a toxic link list (if needed), a reclamation list, and a gap analysis against competitors.
---
## When to use
- Periodic backlink health check (quarterly or biannual)
- Recovering from a Google manual action or unnatural link warning
- Scoping a disavow file
- Pre-acquisition due diligence on link equity
- Planning a link building campaign (need a baseline)
- Investigating ranking drops correlated with link lossseo-competitor
When your agent uses it
Run a competitive SEO analysis comparing the user's site to chosen competitors across SERP overlap, content depth, backlink profiles, technical posture, and brand presence. Use this skill whenever the user wants to analyze competitors, find content gaps, identify backlink opportunities, understand why competitors outrank them, or benchmark against the rest of their category. Triggers on competitor analysis, competitive analysis, SERP analysis, content gap, backlink gap, why is X ranking, who is winning the SERP, beat my competitor, benchmark, market positioning. Also triggers when planning a content strategy and the question 'what are competitors doing' is implicit.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
1,527 tokensWhen the skill is activated
Reference documents
3,127 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Required inputs
- The framework: 5 angles
- Workflow
- Failure patterns
- Output format
- If required data is unavailable
- Reference files
Files
README.mddoc355 bytesSKILL.mdcore7,164 bytesSKILL.mdcore7,164 bytesreferences/competitive-audit-template.mddoc3,764 bytesreferences/content-gap-method.mddoc8,556 bytes
Read SKILL.md
# SEO Competitor Analysis
Compare a site to its competitors and find the gaps worth closing. Stack-agnostic. Tool-friendly but tool-optional.
---
## When to use
- Identifying which competitors to study
- Finding content gaps (topics they cover, you do not)
- Finding backlink gaps (sites linking to them, not you)
- Understanding why a specific competitor outranks the user
- Benchmarking authority, technical posture, and content depth
Skills included
- accessibility-audit
- ads-creative-development
- ads-performance-analytics
- after-action-report
- ai-content-collaboration
- analytics-strategy
- art-direction
- backup-and-disaster-recovery
- beta-program-management
- brand-archetype-system
- brand-discovery
- brand-ideation
- brand-identity
- brand-style-guide
- brand-voice
- calculator-design
- chatbot-flow-design
- code-review-web
- comparison-tool-design
- competitor-experience-audit
- content-and-copy
- content-brief-authoring
- content-distribution
- content-migration
- content-refresh-system
- content-repurposing
- content-strategy
- cost-optimization
- creative-brief
- creative-brief-selector
- creative-direction
- cro-optimization
- data-warehouse-experimentation
- dependency-management
- design-standards
- design-system
- discovery-research-synthesis
- dispatch-authoring
- documentation-strategy
- domain-strategy
- editorial-qa
- email-deliverability
- email-sequences
- evidence-based-reviews
- experiment-design
- experimentation-analytics
- experimentation-platform-orchestrator
- feature-flagging
- feature-launch-playbook
- form-strategy
- frontend-component-build
- funnel-flow-architecture
- incident-response
- information-architecture
- integration-orchestrator
- interactive-product-tour
- internationalization
- journey-mapping
- jtbd-framing
- landing-page-copy
- launch-runbook
- lead-magnet-design
- logo-design
- long-form-content-frameworks
- media-asset-management
- monitoring-and-alerting
- multi-step-form-design
- okr-design
- onboarding-wizard-design
- oss-contribution-research
- paid-media-strategy
- performance-optimization
- pillar-content-architecture
- pm-spec-writing
- product-analytics-setup
- product-configurator-design
- programmatic-seo
- qa-testing
- quiz-and-assessment-design
- roadmap-planning
- scheduler-and-booking-design
- security-baseline
- seo-aeo-geo
- seo-audit-orchestration
- seo-backlink-audit
- seo-competitor
- seo-content-audit
- seo-content-gap-audit
- seo-keyword
- seo-keyword-gap-audit
- seo-offpage
- seo-onpage
- seo-rank-tracking
- seo-site-health-audit
- seo-technical
- seo-traffic-diagnosis
- skill-creation-walkthrough
- sprint-operations
- stakeholder-communication
- team-onboarding-playbook
- ticket-authoring
- upgrade-flow-design
- usability-testing
- user-feedback-aggregation
- ux-research
- vendor-evaluation
- vertical-site-conventions
- accessibility-audit
- ads-creative-development
- ads-performance-analytics
- after-action-report
- ai-content-collaboration
- analytics-strategy
- art-direction
- backup-and-disaster-recovery
- beta-program-management
- brand-archetype-system
- brand-discovery
- brand-ideation
- brand-identity
- brand-style-guide
- brand-voice
- calculator-design
- chatbot-flow-design
- code-review-web
- comparison-tool-design
- competitor-experience-audit
- content-and-copy
- content-brief-authoring
- content-distribution
- content-migration
- content-refresh-system
- content-repurposing
- content-strategy
- cost-optimization
- creative-brief
- creative-brief-selector
- creative-direction
- cro-optimization
- data-warehouse-experimentation
- dependency-management
- design-standards
- design-system
- discovery-research-synthesis
- dispatch-authoring
- documentation-strategy
- domain-strategy
- editorial-qa
- email-deliverability
- email-sequences
- evidence-based-reviews
- experiment-design
- experimentation-analytics
- experimentation-platform-orchestrator
- feature-flagging
- feature-launch-playbook
- form-strategy
- frontend-component-build
- funnel-flow-architecture
- incident-response
- information-architecture
- integration-orchestrator
- interactive-product-tour
- internationalization
- journey-mapping
- jtbd-framing
- landing-page-copy
- launch-runbook
- lead-magnet-design
- logo-design
- long-form-content-frameworks
- media-asset-management
- monitoring-and-alerting
- multi-step-form-design
- okr-design
- onboarding-wizard-design
- oss-contribution-research
- paid-media-strategy
- performance-optimization
- pillar-content-architecture
- pm-spec-writing
- product-analytics-setup
- product-configurator-design
- programmatic-seo
- qa-testing
- quiz-and-assessment-design
- roadmap-planning
- scheduler-and-booking-design
- security-baseline
- seo-aeo-geo
- seo-audit-orchestration
- seo-backlink-audit
- seo-competitor
- seo-content-audit
- seo-content-gap-audit
- seo-keyword
- seo-keyword-gap-audit
- seo-offpage
- seo-onpage
- seo-rank-tracking
- seo-site-health-audit
- seo-technical
- seo-traffic-diagnosis
- skill-creation-walkthrough
- sprint-operations
- stakeholder-communication
- team-onboarding-playbook
- ticket-authoring
- upgrade-flow-design
- usability-testing
- user-feedback-aggregation
- ux-research
- vendor-evaluation
- vertical-site-conventions
- accessibility-audit
- ads-creative-development
- ads-performance-analytics
- after-action-report
- ai-content-collaboration
- analytics-strategy
- art-direction
- backup-and-disaster-recovery
- beta-program-management
- brand-archetype-system
- brand-discovery
- brand-ideation
- brand-identity
- brand-style-guide
- brand-voice
- calculator-design
- chatbot-flow-design
- code-review-web
- comparison-tool-design
- competitor-experience-audit
- content-and-copy
- content-brief-authoring
- content-distribution
- content-migration
- content-refresh-system
- content-repurposing
- content-strategy
- cost-optimization
- creative-brief
- creative-brief-selector
- creative-direction
- cro-optimization
- data-warehouse-experimentation
- dependency-management
- design-standards
- design-system
- discovery-research-synthesis
- dispatch-authoring
- documentation-strategy
- domain-strategy
- editorial-qa
- email-deliverability
- email-sequences
- evidence-based-reviews
- experiment-design
- experimentation-analytics
- experimentation-platform-orchestrator
- feature-flagging
- feature-launch-playbook
- form-strategy
- frontend-component-build
- funnel-flow-architecture
- incident-response
- information-architecture
- integration-orchestrator
- interactive-product-tour
- internationalization
- journey-mapping
- jtbd-framing
- landing-page-copy
- launch-runbook
- lead-magnet-design
- logo-design
- long-form-content-frameworks
- media-asset-management
- monitoring-and-alerting
- multi-step-form-design
- okr-design
- onboarding-wizard-design
- oss-contribution-research
- paid-media-strategy
- performance-optimization
- pillar-content-architecture
- pm-spec-writing
- product-analytics-setup
- product-configurator-design
- programmatic-seo
- qa-testing
- quiz-and-assessment-design
- roadmap-planning
- scheduler-and-booking-design
- security-baseline
- seo-aeo-geo
- seo-audit-orchestration
- seo-backlink-audit
- seo-competitor
Showing 300 of 321 skills. See GitHub for the complete repository.
Repository facts
- License
- MIT
- Created
- Apr 28, 2026
- Last pushed
- Oct 27, 2026
- Forks
- 137
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #867 · best #670 · down 139 in 30 days
- #861 on Oct 31
- #863 on Nov 1
- #862 on Nov 2
- #868 on Nov 3
- #866 on Nov 4
- #867 since Nov 5
81 earlier periods
- #787 on Aug 2
- #837 on Aug 6
- #791 on Aug 8
- #802 on Aug 9
- #833 on Aug 10
- #834 on Aug 11
- #830 on Aug 12
- #837 on Aug 13
- #821 on Aug 14
- #795 on Aug 15
- #814 on Aug 16
- #819 on Aug 17
- #839 on Aug 18
- #830 on Aug 19
- #818 on Aug 20
- #824 on Aug 21
- #775 on Aug 22
- #743 on Aug 23
- #740 on Aug 24
- #733 on Aug 25
- #710 on Aug 26
- #714 on Aug 27
- #735 on Aug 28
- #679 on Aug 29
- #678 on Aug 30
- #711 on Aug 31
- #718 on Sep 1
- #704 on Sep 2
- #712 on Sep 3
- #688 on Sep 4
- #673 on Sep 5
- #694 on Sep 6
- #705 on Sep 7
- #714 on Sep 9
- #717 on Sep 10
- #697 on Sep 11
- #698 on Sep 12
- #694 on Sep 13
- #716 on Sep 14
- #717 on Sep 16
- #718 on Sep 17
- #703 on Sep 18
- #676 on Sep 19
- #693 on Sep 20
- #708 on Sep 21
- #726 on Sep 22
- #713 on Sep 23
- #690 on Sep 24
- #672 on Sep 25
- #670 on Sep 26
- #703 on Sep 27
- #708 on Sep 28
- #745 on Sep 29
- #721 on Sep 30
- #680 on Oct 1
- #691 on Oct 2
- #671 on Oct 3
- #705 on Oct 4
- #711 on Oct 5
- #722 on Oct 6
- #728 on Oct 7
- #770 on Oct 8
- #737 on Oct 9
- #722 on Oct 10
- #720 on Oct 11
- #736 on Oct 12
- #737 on Oct 13
- #747 on Oct 14
- #742 on Oct 15
- #745 on Oct 16
- #724 on Oct 17
- #715 on Oct 18
- #754 on Oct 19
- #756 on Oct 20
- #760 on Oct 21
- #742 from Oct 22 to Oct 23
- #707 on Oct 24
- #842 on Oct 25
- #854 on Oct 28
- #860 on Oct 29
- #858 on Oct 30
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 658 notes
dist/codex/.agents/skills/accessibility-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/accessibility-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/ads-performance-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/ads-performance-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/ads-performance-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/after-action-report/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/after-action-report/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/ai-content-collaboration/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/ai-content-collaboration/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/backup-and-disaster-recovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/beta-program-management/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-ideation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-identity/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-identity/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-style-guide/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-style-guide/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/brand-style-guide/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/calculator-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddist/codex/.agents/skills/calculator-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 15 references to secretsin 9 files: code-review-web/references/nextjs-patterns.md:149 code-review-web/references/nextjs-patterns.md:149 code-review-web/references/nextjs-patterns.md:149 and 6 more
- No requests to vote in Hot
Show all 759 signals by file
.claude-plugin/plugin.json
- Network accessline 4
"version": "1.2.0", "author": { "name": "RampStack" }, "homepage": "https://rampstack.co", - Network accessline 5
"author": { "name": "RampStack" }, "homepage": "https://rampstack.co", "repository": "https://github.com/rampstackco/claude-skills", - Network accessline 6
"homepage": "https://rampstack.co", - Network accessline 7
"repository": "https://github.com/rampstackco/claude-skills",
dist/codex/.agents/skills/accessibility-audit/references/aria-patterns.md
- Network accessline 457
- W3C ARIA Authoring Practices Guide (APG): https://www.w3.org/WAI/ARIA/apg/. Patterns and examples. - Network accessline 458
- WAI-ARIA 1.2 specification: https://www.w3.org/TR/wai-aria-1.2/. Canonical reference. - Network accessline 459
- The W3C ARIA Roles, States, and Properties listing: https://www.w3.org/TR/wai-aria-1.2/#role_definitions. Searchable.
dist/codex/.agents/skills/accessibility-audit/references/wcag-quick-reference.md
- Network accessline 5
For the canonical specification, refer to W3C: https://www.w3.org/TR/WCAG21/
dist/codex/.agents/skills/code-review-web/references/nextjs-patterns.md
- Network accessline 94
const config = { env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Network accessline 95
env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", }, - Network accessline 96
SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Network accessline 245
[Credential-related source omitted] - Access to secretsline 245
[Credential-related source omitted] - Network accessline 259
WP_API_URL=https://cms.yourdomain.com/wp-json # correct - Network accessline 260
WP_API_URL=https://yourdomain.com/wp-json # loops back to Next.js
dist/codex/.agents/skills/code-review-web/references/wordpress-headless-patterns.md
- Network accessline 29
WP_API_URL=https://cms.yourdomain.com/wp-json - Network accessline 35
WP_API_URL=https://yourdomain.com/wp-json # this will break after DNS cutover - Network accessline 51
define("WP_HOME", "https://cms.yourdomain.com"); - Network accessline 52
define("WP_SITEURL", "https://cms.yourdomain.com"); - Network accessline 68
<img src="https://cms.yourdomain.com/wp-content/uploads/photo.jpg" alt="..." /> - Network accessline 79
// Convert CMS media URL to a pattern the frontend image optimizer accepts function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); - Network accessline 80
function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); } - Network accessline 81
return url.replace("https://cms.yourdomain.com", ""); - Network accessline 89
If editors paste full URLs into the content (`<img src="https://cms.yourdomain.com/...">`), changing the CMS subdomain later breaks every reference. Use relative paths or template-rendered URLs instead. - Network accessline 95
WordPress posts have a `link` field in the API response that returns the WordPress-rendered URL (e.g., `https://cms.yourdomain.com/post-slug/`). This is wrong for the public-facing site. - Network accessline 122
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 138
wp_remote_post('https://yourdomain.com/api/revalidate', [ - Network accessline 155
const posts = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 176
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 210
const res = await fetch(`${WP_API_URL}/wp/v2/posts?per_page=100`); - Network accessline 240
const res = await fetch(`${WP_API_URL}/wp/v2/posts?_embed=true`);
dist/codex/.agents/skills/competitor-experience-audit/references/experience-dimensions-checklist.md
- Network accessline 19
Rendered required: **partial.** The primary task can usually be identified from a static fetch (it is in the markup), but its visual dominance and protection from competitors requires the rendered view.
dist/codex/.agents/skills/content-migration/references/migration-runbook.md
dist/codex/.agents/skills/creative-brief-selector/references/05-section-shapes-vocabulary.md
- Network accessline 17
- **When it fits**: brands where the photograph and the type carry roughly equal weight and the eye is meant to ricochet between them. Premium DTC product hero is the canonical fit; a single product on the image side and a price-and-CTA on - Network accessline 18
- **References**: [allbirds.com](https://allbirds.com), [tecovas.com](https://tecovas.com). - Network accessline 25
- **When it fits**: inventory marketplaces, regional specialists, sites where the photograph signals what the marketplace is for and the band carries the controls. Also fits magazine-style editorial registers where one strong image opens an - Network accessline 26
- **References**: [bringatrailer.com](https://bringatrailer.com), [icon4x4.com](https://icon4x4.com). - Network accessline 33
- **When it fits**: hospitality experiences where the place is the product (balloon ride, restaurant, hotel), mission-driven nonprofits where the documentary photograph is the evidence, premium B2B where the product is photographed at scale - Network accessline 34
- **References**: [bombasses.com](https://bombasses.com) (hospitality), [charitywater.org](https://charitywater.org) (institution-mission). - Network accessline 41
- **When it fits**: editorial publications, ideas-led brands, B2B SaaS where the proposition is conceptual, premium consultancies, law and finance where understated credibility is the play. - **References**: [nytimes.com](https://nytimes.co - Network accessline 42
- **References**: [nytimes.com](https://nytimes.com), [stripe.com](https://stripe.com) (mild type-led, with type leading and a subtle product render below). - Network accessline 49
- **When it fits**: portfolio brands, atmospheric or contemplative registers, single-product brands where the page is essentially a long-scroll story and the hero is just the opening line. - **References**: [linear.app](https://linear.app), - Network accessline 50
- **References**: [linear.app](https://linear.app), [framer.com](https://framer.com) (both run centered single-column heroes at times). - Network accessline 57
- **When it fits**: magazine cover style, photography portfolios, single-product hero where the product carries everything and the type is a caption-scale credit line. - **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.c - Network accessline 58
- **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.com](https://aesop.com) (varies; some pages use asymmetric layouts). - Network accessline 65
- **When it fits**: directory and marketplace shapes where the breadth of the catalog is the value, ecommerce catalog shapes where shoppability above the fold is the conversion lever. - **References**: [airbnb.com](https://airbnb.com) (sear - Network accessline 66
- **References**: [airbnb.com](https://airbnb.com) (search results hero is the grid), [unsplash.com](https://unsplash.com). - Network accessline 73
- **When it fits**: B2B engineering procurement, hardware comparison sites, financial product comparison, anywhere the buyer is data-anchored before they care about photography. - **References**: [parametricportfolio.com](https://www.parame - Network accessline 74
- **References**: [parametricportfolio.com](https://www.parametricportfolio.com), [substack.com/pricing](https://substack.com/pricing) (pricing-table-as-hero variants). - Network accessline 93
- **When it fits**: ecommerce catalog with deep category trees, multi-tenant marketplaces with seller-side and buyer-side links, B2B sites with documentation libraries. - **References**: [amazon.com](https://amazon.com), [shopify.com](https - Network accessline 94
- **References**: [amazon.com](https://amazon.com), [shopify.com](https://shopify.com), most large retailers. - Network accessline 101
- **When it fits**: ideas-led brands, single-page narratives, publications where the nav lives in the top chrome and the bottom is just the credit line. - **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), port - Network accessline 102
- **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), portfolio sites. - Network accessline 109
- **When it fits**: publications, magazine sites, editorial collectives, organizations where the people are the brand. - **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 110
- **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 117
- **When it fits**: content sites, newsletter-first publications, brands where the newsletter is the customer-relationship channel. - **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 118
- **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 125
- **When it fits**: conversion-led sites where the bottom of the page is the second-most-attended surface (after the hero), marketing sites, B2B with a sign-up funnel. - **References**: [vercel.com](https://vercel.com), [linear.app](https:/ - Network accessline 126
- **References**: [vercel.com](https://vercel.com), [linear.app](https://linear.app).
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.md
- Network accessline 9
- [bungie.net](https://bungie.net) - The canonical AAA-action studio chrome register: cinematic full-bleed key-art hero, dark-mode-first ground, restrained type chrome that lets the game art carry. Inherit the cinematic hero treatment, the - Network accessline 10
- [insomniac.games](https://insomniac.games) - Insomniac Games. The studio chrome at composed-cinematic; the titles portfolio surfaced with care. Inherit the titles-portfolio anatomy and the craft-proud-without-arrogance voice. - Network accessline 11
- [naughtydog.com](https://naughtydog.com) - Naughty Dog. The restrained-cinematic studio register; type-led studio band with the team presented at masthead density. Inherit the studio-band convention and the restrained-cinematic chrome. - Network accessline 12
- [remedygames.com](https://remedygames.com) - Remedy Entertainment. The composed-cinematic register at the studio level, with a smaller portfolio presented with editorial discipline. Inherit the title-detail-page-as-small-monograph anatomy - Network accessline 16
- [steampowered.com](https://steampowered.com) - Steam. Platform chrome that hosts third-party content. Wrong vertical (platform, not studio); the platform chrome reads totally different from a studio's content-creator brand. - Network accessline 17
- [itch.io](https://itch.io) - Itch.io. Indie game platform; minimal chrome; wrong register and wrong vertical.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.md
- Network accessline 11
- [marathonthegame.com](https://marathonthegame.com) - The saturated single-IP marketing register at its most committed: a published title's own brand, dark-mode-first, with the title's palette and art carrying the saturation rather than th - Network accessline 12
- [deathstranding.com](https://deathstranding.com) - Single-IP world-immersion marketing: the site immerses the visitor in one world (the setting, the lore) in the game's own voice rather than the studio's. Inherit the world-as-protagonist - Network accessline 13
- [cyberpunk.net](https://cyberpunk.net) - Saturated single-IP launch register: type at title-card scale, palette depth carrying the world's own tones. Inherit the type-at-scale and palette-depth treatment; do NOT pull the neon-magenta iden - Network accessline 14
- [bandainamcoent.com/games/elden-ring](https://www.bandainamcoent.com/games/elden-ring) - Single-IP lore-immersion marketing: a world page that treats the world as the protagonist with deep lore in the title's voice. Inherit the lore-immer - Network accessline 18
- Studio and publisher portfolio sites ([bungie.net](https://bungie.net), [naughtydog.com](https://naughtydog.com), and the paired `bold-confident-editorial-restrained-aaa-game-studio` register) - The studio chrome composes and recedes to l - Network accessline 19
- Platform-chrome sites ([steampowered.com](https://steampowered.com), [store.epicgames.com](https://store.epicgames.com), [itch.io](https://itch.io)) - Platforms host third-party content and lean restrained to let the content carry. A sing
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.md
- Network accessline 9
- [drinktrade.com](https://drinktrade.com) - Subscriber-first commerce explicit: cadence picker on the home, match-quiz to find your roast, pause and swap surfaced as features rather than buried in account settings. Editorial-restrained typ - Network accessline 10
- [counterculturecoffee.com](https://counterculturecoffee.com) - Specialty roaster with subscription surfaced; documentary photography of farms and farmers carries the page; editorial type. The canonical reference for "farm-direct specialty - Network accessline 11
- [onyxcoffeelab.com](https://onyxcoffeelab.com) - Editorial-restrained register at its most refined: type-led, considered photography, premium-but-approachable. Useful as the type-system reference (small-caps, restrained tracking, editoria - Network accessline 12
- [atlascoffeeclub.com](https://atlascoffeeclub.com) - Subscriber-first explicitly with a world-coffee-journey narrative. The closest match to the "one origin a month, named farm, named process" positioning. Useful for how to surface the ro - Network accessline 16
- [starbucks.com](https://starbucks.com) - Mass-market grocery register; frappuccino lifestyle photography; promotional cadence dominates the homepage. The register a specialty roaster must not pull from. - Network accessline 17
- [folgerscoffee.com](https://folgerscoffee.com) - Commodity grocery brand; red-can heritage but no specialty register. The bottom of the grocery shelf, conceptually.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/editorial-restrained-literary-quarterly.md
- Network accessline 9
- [aeon.co](https://aeon.co) - Multidisciplinary ideas register. Considered design, restrained palette (warm-grey ground with deep type and a single accent), essays at substantial length, multiple disciplines per surface. Inherit the ideas- - Network accessline 10
- [thepointmag.com](https://thepointmag.com) - Themed multi-author essay structure at length. The closest peer on the audience axis (broadly literary readers across disciplines). Inherit the multi-author themed-issue treatment and the essay - Network accessline 11
- [cabinetmagazine.org](https://cabinetmagazine.org) - The closest structural anchor in the field: each issue is organized around a single thematic question rendered with editorial restraint. Inherit the single-theme-per-issue structure and - Network accessline 12
- [canopycanopycanopy.com](https://canopycanopycanopy.com) - Triple Canopy. Themed digital-first sequenced issues with editorial restraint. Inherit the digital-first design discipline and the sequenced-issue numbering. - Network accessline 16
- [thedriftmag.com](https://thedriftmag.com) - Politically situated, generationally branded, identity-forward. A considered quarterly must avoid the political-statement register on conversion architecture, palette, and voice. - Network accessline 17
- [nplusonemag.com](https://nplusonemag.com) - Institutional NY cultural authority register. A considered quarterly should not borrow the geographic or generational positioning. - Network accessline 18
- [laphamsquarterly.org](https://laphamsquarterly.org) - Historical-source-driven format (passages from historical writing assembled around a theme). A different format entirely; canonical to that publication and not transferable. - Network accessline 19
- [thebeliever.net](https://www.thebeliever.net) - McSweeney's-adjacent geometric illustration identity. A type-led quarterly should not borrow the illustration-led visual treatment. - Network accessline 20
- [atavist.com](https://atavist.com) - Single-essay-per-issue reportage register. A multi-essay themed quarterly is a different shape. - Network accessline 21
- [themarginalian.org](https://themarginalian.org) - Single-author blog register. A multi-author themed quarterly is a different shape.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/heritage-local-service-barbershop.md
- Network accessline 9
- [therosemontbarbers.com](https://therosemontbarbers.com) - Cuts gallery, interior atmosphere, social-proof badge, real team page in the heritage register. - Network accessline 10
- [speakeasybarberlounge.com](https://speakeasybarberlounge.com) - Atmosphere-led, period-specific cues (lounge fittings, warm interior), interior photography carries the page. - Network accessline 11
- [franksdenver.com](https://franksdenver.com) - Heritage register at a higher-end price point; restrained palette, considered editorial layout. - Network accessline 12
- [alfanisbarbershop.com](https://alfanisbarbershop.com) - Small-operator heritage, atmosphere-forward, real-team page.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/hospitality-experience-balloon-ride.md
- Network accessline 9
- [nvaloft.com](https://nvaloft.com) - Regional operator, atmosphere-forward, dawn-palette imagery. - Network accessline 10
- [aerogelicballooning.com](https://aerogelicballooning.com) - Atmosphere-led, ride arc surfaced, photography drives the page. - Network accessline 11
- [rainbowryders.com](https://rainbowryders.com) - Multi-region operator, photography-led, named packages with prices. - Network accessline 12
- [sundanceballoons.com](https://sundanceballoons.com) - Multi-region operator, considered-warm register, ride-arc framing.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/luxe-considered-curated-stays-directory.md
- Network accessline 11
- [plumguide.com](https://plumguide.com) - The curated-design short-term-stay register: a small vetted collection rather than the long tail, each stay presented with editorial care. Inherit the curated-collection posture and the property-as - Network accessline 12
- [boutique-homes.com](https://boutique-homes.com) - The design-led curated-stays register: architecturally distinctive properties grouped by design feeling. Inherit the design-forward collection grouping and the generous property gallery; - Network accessline 13
- [onefinestay.com](https://onefinestay.com) - The upper-curated hospitality register: a small set of standout homes with a hotel-grade presentation. Inherit the restrained-confident chrome and the aspirational photo direction; do NOT pull
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.md
- Network accessline 9
- [themodernhouse.com](https://themodernhouse.com) - The canonical reference for the design-led residential brokerage register at editorial-restrained tier. Each listing reads as a small monograph; the architect is named in the listing card - Network accessline 10
- [phillips.com](https://phillips.com/design) - Phillips's design auction catalog register. The monograph treatment per lot (designer, year, materials, provenance) transfers cleanly to a residential listing. Inherit the per-lot monograph an - Network accessline 11
- [dezeen.com](https://dezeen.com) - The architectural press register. Listing-style architecture coverage with architect credits, year, materials, photography. Inherit the architecture-press literacy and the credit-line convention. - Network accessline 12
- [architecturaldigest.com](https://architecturaldigest.com) - The design-publication register with residential homes covered as design objects. Inherit the photography sensibility and the design-publication restraint. - Network accessline 16
- [zillow.com](https://zillow.com) - Mass-market portal; algorithmic listing presentation, estimated-value overlays, financing-first conversion. The register a luxe-considered brokerage must avoid on conversion architecture, palette, and vo - Network accessline 17
- [realtor.com](https://realtor.com) - Same mass-market portal register; broker-listing-syndication shape, generic photography presentation. - Network accessline 18
- [redfin.com](https://redfin.com) - Mass-market portal with light brokerage layer; price-anxiety scoring, financing partnerships surfaced as primary CTAs.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/minimal-essentialist-documentary-honest-trades-directory.md
- Network accessline 11
- [angi.com](https://angi.com) - The modern consolidated home-services directory register: category-and-location search, provider listings, the lead-handoff conversion. Inherit the search-first discovery spine and the category structure; do - Network accessline 12
- [thumbtack.com](https://thumbtack.com) - The matched-services register: structured by trade and location, provider profiles with comparable fields. Inherit the comparable-provider-profile anatomy; do NOT pull the blue palette or the get-m - Network accessline 13
- [houzz.com](https://houzz.com) - The visual-services-directory register: real work photography carrying the provider listings. Inherit the documentary work-in-context photography direction (a trade in progress, a finished job), not glamou
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/premium-dtc-maker-western-boots.md
- Network accessline 9
- [tecovas.com](https://tecovas.com) - The elevated-DTC reference: product-forward hero, named prices visible, restrained merchandising. No discount banners above the fold. - Network accessline 10
- [lucchese.com](https://lucchese.com) - Heritage register; serif-led, craft narrative as a supporting band rather than the lead. - Network accessline 11
- [oldgringoboots.com](https://oldgringoboots.com) - Smaller-maker, leather-forward photography, restrained editorial set instead of catalog density. - Network accessline 12
- [ranchroadboots.com](https://ranchroadboots.com) - Small-operator boutique competing in the same position; useful for cross-checking how a peer maker handles wayfinding on a small collection. - Network accessline 16
- [durangoboots.com](https://durangoboots.com) - Catalog-dense big-box texture; discount cadence, SKU-strip-above-the-fold, sale-badge pile. Not the register a premium small maker should pull from. - Network accessline 17
- [justinboots.com](https://justinboots.com) - Same big-box texture in a different brand; promotional banners and grid density dominate. - Network accessline 18
- [bootbarn.com](https://bootbarn.com) - Multi-brand retailer rather than a maker; merchandising-led rather than craft-led.
dist/codex/.agents/skills/creative-brief-selector/references/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.md
- Network accessline 9
- [bringatrailer.com](https://bringatrailer.com) - The canonical listing-detail transparency reference: full ownership history, mileage timeline, photograph density (forty to one hundred photographs per lot is typical), a comments thread th - Network accessline 10
- [icon4x4.com](https://icon4x4.com) - Editorial documentary register applied to working vehicles. Inherit the photography direction (vehicles photographed in landscape and at work, not glamour shots on a studio seamless), the considered ed - Network accessline 11
- [filson.com](https://filson.com) - Mountain West heritage workwear register. Inherit the palette tendency (granite, evergreen, oxblood, aspen gold; cool ground with restrained accents), the documentary photography that supports the type r - Network accessline 12
- [patagonia.com](https://patagonia.com) - The adjacent outdoor-utility register, useful as the second positive on voice (plain-direct, no marketing inflation, the audience treated as competent). - Network accessline 16
- [cargurus.com](https://cargurus.com) - Mass-market national passenger-car register; price-anxiety scoring as the hero, financing-first conversion architecture. The register a specialist regional marketplace must avoid on conversion archit - Network accessline 17
- [cars.com](https://cars.com) - Same mass-market national register; promotional banner cadence, broad-inventory generalist posture. - Network accessline 18
- [carvana.com](https://carvana.com) - DTC mass-market with vending-machine theatrics, financing-first. The register to avoid on theatrics and on conversion-flow priority. - Network accessline 19
- [autotempest.com](https://autotempest.com) - Meta-aggregator with no editorial voice; utility-only search-across-the-others. A specialist marketplace must not read as utility-only. - Network accessline 20
- [edmunds.com](https://edmunds.com) - Research-led advisory; content-heavy editorial sitting adjacent to a marketplace. A specialist marketplace must not read as a magazine pretending to be a marketplace.
dist/codex/.agents/skills/domain-strategy/SKILL.md
- Network accessline 146
- Configure 301 redirect for the non-canonical - Force HTTPS for both - Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical. - Network accessline 148
- Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical.
dist/codex/.agents/skills/frontend-component-build/references/accessibility-patterns.md
- Network accessline 53
<a href="https://external.com" target="_blank" rel="noopener noreferrer">
dist/codex/.agents/skills/funnel-flow-architecture/references/cross-tool-data-flow-patterns.md
- Access to secretsline 166
[Credential-related source omitted]
dist/codex/.agents/skills/integration-orchestrator/references/platform-implementation.md
- Network accessline 21
- **Availability.** Official remote MCP server, launched 2025. - **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](ht - Network accessline 22
- **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](https://github.com/atlassian/atlassian-mcp-server). - Network accessline 51
- **Availability.** Official, well-supported. - **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 52
- **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 77
- **Availability.** Official. - **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 78
- **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 103
- **Availability.** Figma Dev Mode MCP exists but is dev-mode-focused (component inspection, code generation, design token export). - **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 104
- **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 129
- **Availability.** Official. - **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server). - Network accessline 130
- **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server).
dist/codex/.agents/skills/internationalization/SKILL.md
- Network accessline 89
<link rel="alternate" hreflang="en-US" href="https://example.com/en-us/page"> - Network accessline 90
<link rel="alternate" hreflang="en-GB" href="https://example.com/en-gb/page"> - Network accessline 91
<link rel="alternate" hreflang="de-DE" href="https://example.com/de-de/page"> - Network accessline 92
<link rel="alternate" hreflang="x-default" href="https://example.com/en-us/page">
dist/codex/.agents/skills/oss-contribution-research/references/example-intake-item.md
- Network accessline 18
- item_id: feedparse-412-intake-empty-pubdate - repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - Network accessline 19
- repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - action: intake - Network accessline 20
- url: https://github.com/example-org/feedparse/issues/412 - Network accessline 23
## Policy allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and rev - Network accessline 24
allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and reviewed by t
dist/codex/.agents/skills/oss-contribution-research/references/policy-classification.md
- Network accessline 56
allows: CONTRIBUTING.md:63 "AI-assisted contributions are welcome" (https://...). Disclosure for issue_comment: [registry text].
dist/codex/.agents/skills/oss-contribution-research/references/queue-item-template.md
- Network accessline 11
- item_id: [unique slug, a-z 0-9 and -, 8 to 80 characters, e.g. feedparse-412-intake] - repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - Network accessline 12
- repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - action: [intake | pr | reply | close] - Network accessline 13
- url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item]
dist/codex/.agents/skills/oss-contribution-research/references/repro-record-template.md
- Network accessline 16
target: owner/repo#n, in a code span when the record is pasted into a queue item surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 17
surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 43
target: `example-org/chartkit#88` surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 44
surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 45
steps: 1. Open http://localhost:8080/?file=http://localhost:8080/fixtures/chart-3.0.json
dist/codex/.agents/skills/performance-optimization/references/optimization-playbook.md
- Network accessline 28
- Ensure web fonts don't block rendering (`font-display: swap`) - Inline critical CSS for the heading section - Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 30
- Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 112
Use WebPageTest or `curl -w "@curl-format.txt" -s -o /dev/null https://example.com` to measure just TTFB.
dist/codex/.agents/skills/pillar-content-architecture/references/cluster-piece-anatomy.md
- Network accessline 101
{ "@context": "https://schema.org", - Network accessline 102
"@context": "https://schema.org", - Network accessline 103
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 104
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 105
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 106
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
dist/codex/.agents/skills/pillar-content-architecture/references/pillar-page-anatomy.md
dist/codex/.agents/skills/pillar-content-architecture/references/url-structure-patterns.md
- Network accessline 68
{ "@context": "https://schema.org", - Network accessline 69
"@context": "https://schema.org", - Network accessline 70
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 71
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 72
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 73
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
dist/codex/.agents/skills/product-analytics-setup/references/schema-versioning-patterns.md
dist/codex/.agents/skills/qa-testing/SKILL.md
- Network accessline 154
fetch(window.location.origin, { method: 'HEAD' })
dist/codex/.agents/skills/security-baseline/SKILL.md
- Network accessline 141
Content-Security-Policy: script-src 'self' https://trusted.com; ...
dist/codex/.agents/skills/security-baseline/references/headers-checklist.md
- Network accessline 108
Content-Security-Policy: default-src 'self'; script-src 'self' https://trusted-cdn.com; - Network accessline 109
default-src 'self'; script-src 'self' https://trusted-cdn.com; style-src 'self' 'unsafe-inline'; - Network accessline 110
script-src 'self' https://trusted-cdn.com; - Network accessline 149
Permissions-Policy: camera=(self), geolocation=(self "https://maps.example.com") - Network accessline 209
Reporting-Endpoints: csp-endpoint="https://example.com/csp", default="https://example.com/reports" - Network accessline 288
curl -I https://example.com
dist/codex/.agents/skills/seo-aeo-geo/references/extraction-friendly-patterns.md
- Access to secretsline 175
[Credential-related source omitted]
dist/codex/.agents/skills/seo-aeo-geo/references/llms-txt-guide.md
- Network accessline 67
- [The Complete Guide to X](https://example.com/complete-guide-x): A 5,000-word reference covering fundamentals through advanced topics. - Network accessline 68
- [How to Choose Y](https://example.com/how-to-choose-y): Decision framework with comparison tables and worked examples. - Network accessline 69
- [The Beginner's Guide to Z](https://example.com/beginner-z): A 30-minute primer for someone new to the topic. - Network accessline 73
- [A vs B](https://example.com/a-vs-b): Head-to-head feature, pricing, and use case comparison. - Network accessline 74
- [Top 10 [Category]](https://example.com/top-10): Ranked list with selection criteria. - Network accessline 78
- [Calculator](https://example.com/calculator): Free interactive tool for [purpose]. - Network accessline 79
- [Templates](https://example.com/templates): Downloadable templates with examples. - Network accessline 83
- [About us](https://example.com/about) - Network accessline 84
- [Methodology](https://example.com/methodology) - Network accessline 85
- [Editorial standards](https://example.com/editorial-standards) - Network accessline 101
- [How it works](https://example.com/product): Overview of core functionality and architecture. - Network accessline 102
- [Pricing](https://example.com/pricing): Transparent pricing tiers and what each includes. - Network accessline 103
- [Integrations](https://example.com/integrations): Third-party tools we connect with. - Network accessline 107
- [Getting started](https://docs.example.com/getting-started): 15-minute setup guide. - Network accessline 108
- [API reference](https://docs.example.com/api): Complete API documentation. - Network accessline 109
- [Best practices](https://docs.example.com/best-practices): How successful customers use the product. - Network accessline 113
- [Customer stories](https://example.com/customers): How specific customers achieved specific outcomes. - Network accessline 114
- [Blog](https://example.com/blog): Engineering posts, product updates, and industry analysis. - Network accessline 115
- [Changelog](https://example.com/changelog): Recent product changes. - Network accessline 119
- [Security](https://example.com/security): SOC 2, encryption, compliance. - Network accessline 120
- [Privacy policy](https://example.com/privacy) - Network accessline 121
- [Terms of service](https://example.com/terms) - Network accessline 201
- [Full content dump](https://example.com/llms-full.txt): The complete content of all linked pages. - Network accessline 221
- [ ] File is at `https://yourdomain.com/llms.txt` (root)
dist/codex/.agents/skills/seo-backlink-audit/references/toxic-link-criteria.md
- Network accessline 108
https://otherwiselegitimate-example.com/sponsored-post-page
dist/codex/.agents/skills/seo-technical/references/audit-template.md
- Network accessline 41
- [ ] Critical sections of the site are not accidentally disallowed - [ ] Specific user agents are not blocked (`Googlebot`, `Bingbot`) - [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 43
- [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 227
- [ ] Both `https://www` and `https://` (and `http://` versions) verified as separate properties
dist/pi/.agents/skills/accessibility-audit/references/aria-patterns.md
- Network accessline 457
- W3C ARIA Authoring Practices Guide (APG): https://www.w3.org/WAI/ARIA/apg/. Patterns and examples. - Network accessline 458
- WAI-ARIA 1.2 specification: https://www.w3.org/TR/wai-aria-1.2/. Canonical reference. - Network accessline 459
- The W3C ARIA Roles, States, and Properties listing: https://www.w3.org/TR/wai-aria-1.2/#role_definitions. Searchable.
dist/pi/.agents/skills/accessibility-audit/references/wcag-quick-reference.md
- Network accessline 5
For the canonical specification, refer to W3C: https://www.w3.org/TR/WCAG21/
dist/pi/.agents/skills/code-review-web/references/nextjs-patterns.md
- Network accessline 94
const config = { env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Network accessline 95
env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", }, - Network accessline 96
SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Network accessline 245
[Credential-related source omitted] - Access to secretsline 245
[Credential-related source omitted] - Network accessline 259
WP_API_URL=https://cms.yourdomain.com/wp-json # correct - Network accessline 260
WP_API_URL=https://yourdomain.com/wp-json # loops back to Next.js
dist/pi/.agents/skills/code-review-web/references/wordpress-headless-patterns.md
- Network accessline 29
WP_API_URL=https://cms.yourdomain.com/wp-json - Network accessline 35
WP_API_URL=https://yourdomain.com/wp-json # this will break after DNS cutover - Network accessline 51
define("WP_HOME", "https://cms.yourdomain.com"); - Network accessline 52
define("WP_SITEURL", "https://cms.yourdomain.com"); - Network accessline 68
<img src="https://cms.yourdomain.com/wp-content/uploads/photo.jpg" alt="..." /> - Network accessline 79
// Convert CMS media URL to a pattern the frontend image optimizer accepts function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); - Network accessline 80
function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); } - Network accessline 81
return url.replace("https://cms.yourdomain.com", ""); - Network accessline 89
If editors paste full URLs into the content (`<img src="https://cms.yourdomain.com/...">`), changing the CMS subdomain later breaks every reference. Use relative paths or template-rendered URLs instead. - Network accessline 95
WordPress posts have a `link` field in the API response that returns the WordPress-rendered URL (e.g., `https://cms.yourdomain.com/post-slug/`). This is wrong for the public-facing site. - Network accessline 122
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 138
wp_remote_post('https://yourdomain.com/api/revalidate', [ - Network accessline 155
const posts = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 176
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 210
const res = await fetch(`${WP_API_URL}/wp/v2/posts?per_page=100`); - Network accessline 240
const res = await fetch(`${WP_API_URL}/wp/v2/posts?_embed=true`);
dist/pi/.agents/skills/competitor-experience-audit/references/experience-dimensions-checklist.md
- Network accessline 19
Rendered required: **partial.** The primary task can usually be identified from a static fetch (it is in the markup), but its visual dominance and protection from competitors requires the rendered view.
dist/pi/.agents/skills/content-migration/references/migration-runbook.md
dist/pi/.agents/skills/creative-brief-selector/references/05-section-shapes-vocabulary.md
- Network accessline 17
- **When it fits**: brands where the photograph and the type carry roughly equal weight and the eye is meant to ricochet between them. Premium DTC product hero is the canonical fit; a single product on the image side and a price-and-CTA on - Network accessline 18
- **References**: [allbirds.com](https://allbirds.com), [tecovas.com](https://tecovas.com). - Network accessline 25
- **When it fits**: inventory marketplaces, regional specialists, sites where the photograph signals what the marketplace is for and the band carries the controls. Also fits magazine-style editorial registers where one strong image opens an - Network accessline 26
- **References**: [bringatrailer.com](https://bringatrailer.com), [icon4x4.com](https://icon4x4.com). - Network accessline 33
- **When it fits**: hospitality experiences where the place is the product (balloon ride, restaurant, hotel), mission-driven nonprofits where the documentary photograph is the evidence, premium B2B where the product is photographed at scale - Network accessline 34
- **References**: [bombasses.com](https://bombasses.com) (hospitality), [charitywater.org](https://charitywater.org) (institution-mission). - Network accessline 41
- **When it fits**: editorial publications, ideas-led brands, B2B SaaS where the proposition is conceptual, premium consultancies, law and finance where understated credibility is the play. - **References**: [nytimes.com](https://nytimes.co - Network accessline 42
- **References**: [nytimes.com](https://nytimes.com), [stripe.com](https://stripe.com) (mild type-led, with type leading and a subtle product render below). - Network accessline 49
- **When it fits**: portfolio brands, atmospheric or contemplative registers, single-product brands where the page is essentially a long-scroll story and the hero is just the opening line. - **References**: [linear.app](https://linear.app), - Network accessline 50
- **References**: [linear.app](https://linear.app), [framer.com](https://framer.com) (both run centered single-column heroes at times). - Network accessline 57
- **When it fits**: magazine cover style, photography portfolios, single-product hero where the product carries everything and the type is a caption-scale credit line. - **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.c - Network accessline 58
- **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.com](https://aesop.com) (varies; some pages use asymmetric layouts). - Network accessline 65
- **When it fits**: directory and marketplace shapes where the breadth of the catalog is the value, ecommerce catalog shapes where shoppability above the fold is the conversion lever. - **References**: [airbnb.com](https://airbnb.com) (sear - Network accessline 66
- **References**: [airbnb.com](https://airbnb.com) (search results hero is the grid), [unsplash.com](https://unsplash.com). - Network accessline 73
- **When it fits**: B2B engineering procurement, hardware comparison sites, financial product comparison, anywhere the buyer is data-anchored before they care about photography. - **References**: [parametricportfolio.com](https://www.parame - Network accessline 74
- **References**: [parametricportfolio.com](https://www.parametricportfolio.com), [substack.com/pricing](https://substack.com/pricing) (pricing-table-as-hero variants). - Network accessline 93
- **When it fits**: ecommerce catalog with deep category trees, multi-tenant marketplaces with seller-side and buyer-side links, B2B sites with documentation libraries. - **References**: [amazon.com](https://amazon.com), [shopify.com](https - Network accessline 94
- **References**: [amazon.com](https://amazon.com), [shopify.com](https://shopify.com), most large retailers. - Network accessline 101
- **When it fits**: ideas-led brands, single-page narratives, publications where the nav lives in the top chrome and the bottom is just the credit line. - **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), port - Network accessline 102
- **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), portfolio sites. - Network accessline 109
- **When it fits**: publications, magazine sites, editorial collectives, organizations where the people are the brand. - **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 110
- **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 117
- **When it fits**: content sites, newsletter-first publications, brands where the newsletter is the customer-relationship channel. - **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 118
- **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 125
- **When it fits**: conversion-led sites where the bottom of the page is the second-most-attended surface (after the hero), marketing sites, B2B with a sign-up funnel. - **References**: [vercel.com](https://vercel.com), [linear.app](https:/ - Network accessline 126
- **References**: [vercel.com](https://vercel.com), [linear.app](https://linear.app).
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.md
- Network accessline 9
- [bungie.net](https://bungie.net) - The canonical AAA-action studio chrome register: cinematic full-bleed key-art hero, dark-mode-first ground, restrained type chrome that lets the game art carry. Inherit the cinematic hero treatment, the - Network accessline 10
- [insomniac.games](https://insomniac.games) - Insomniac Games. The studio chrome at composed-cinematic; the titles portfolio surfaced with care. Inherit the titles-portfolio anatomy and the craft-proud-without-arrogance voice. - Network accessline 11
- [naughtydog.com](https://naughtydog.com) - Naughty Dog. The restrained-cinematic studio register; type-led studio band with the team presented at masthead density. Inherit the studio-band convention and the restrained-cinematic chrome. - Network accessline 12
- [remedygames.com](https://remedygames.com) - Remedy Entertainment. The composed-cinematic register at the studio level, with a smaller portfolio presented with editorial discipline. Inherit the title-detail-page-as-small-monograph anatomy - Network accessline 16
- [steampowered.com](https://steampowered.com) - Steam. Platform chrome that hosts third-party content. Wrong vertical (platform, not studio); the platform chrome reads totally different from a studio's content-creator brand. - Network accessline 17
- [itch.io](https://itch.io) - Itch.io. Indie game platform; minimal chrome; wrong register and wrong vertical.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.md
- Network accessline 11
- [marathonthegame.com](https://marathonthegame.com) - The saturated single-IP marketing register at its most committed: a published title's own brand, dark-mode-first, with the title's palette and art carrying the saturation rather than th - Network accessline 12
- [deathstranding.com](https://deathstranding.com) - Single-IP world-immersion marketing: the site immerses the visitor in one world (the setting, the lore) in the game's own voice rather than the studio's. Inherit the world-as-protagonist - Network accessline 13
- [cyberpunk.net](https://cyberpunk.net) - Saturated single-IP launch register: type at title-card scale, palette depth carrying the world's own tones. Inherit the type-at-scale and palette-depth treatment; do NOT pull the neon-magenta iden - Network accessline 14
- [bandainamcoent.com/games/elden-ring](https://www.bandainamcoent.com/games/elden-ring) - Single-IP lore-immersion marketing: a world page that treats the world as the protagonist with deep lore in the title's voice. Inherit the lore-immer - Network accessline 18
- Studio and publisher portfolio sites ([bungie.net](https://bungie.net), [naughtydog.com](https://naughtydog.com), and the paired `bold-confident-editorial-restrained-aaa-game-studio` register) - The studio chrome composes and recedes to l - Network accessline 19
- Platform-chrome sites ([steampowered.com](https://steampowered.com), [store.epicgames.com](https://store.epicgames.com), [itch.io](https://itch.io)) - Platforms host third-party content and lean restrained to let the content carry. A sing
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.md
- Network accessline 9
- [drinktrade.com](https://drinktrade.com) - Subscriber-first commerce explicit: cadence picker on the home, match-quiz to find your roast, pause and swap surfaced as features rather than buried in account settings. Editorial-restrained typ - Network accessline 10
- [counterculturecoffee.com](https://counterculturecoffee.com) - Specialty roaster with subscription surfaced; documentary photography of farms and farmers carries the page; editorial type. The canonical reference for "farm-direct specialty - Network accessline 11
- [onyxcoffeelab.com](https://onyxcoffeelab.com) - Editorial-restrained register at its most refined: type-led, considered photography, premium-but-approachable. Useful as the type-system reference (small-caps, restrained tracking, editoria - Network accessline 12
- [atlascoffeeclub.com](https://atlascoffeeclub.com) - Subscriber-first explicitly with a world-coffee-journey narrative. The closest match to the "one origin a month, named farm, named process" positioning. Useful for how to surface the ro - Network accessline 16
- [starbucks.com](https://starbucks.com) - Mass-market grocery register; frappuccino lifestyle photography; promotional cadence dominates the homepage. The register a specialty roaster must not pull from. - Network accessline 17
- [folgerscoffee.com](https://folgerscoffee.com) - Commodity grocery brand; red-can heritage but no specialty register. The bottom of the grocery shelf, conceptually.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/editorial-restrained-literary-quarterly.md
- Network accessline 9
- [aeon.co](https://aeon.co) - Multidisciplinary ideas register. Considered design, restrained palette (warm-grey ground with deep type and a single accent), essays at substantial length, multiple disciplines per surface. Inherit the ideas- - Network accessline 10
- [thepointmag.com](https://thepointmag.com) - Themed multi-author essay structure at length. The closest peer on the audience axis (broadly literary readers across disciplines). Inherit the multi-author themed-issue treatment and the essay - Network accessline 11
- [cabinetmagazine.org](https://cabinetmagazine.org) - The closest structural anchor in the field: each issue is organized around a single thematic question rendered with editorial restraint. Inherit the single-theme-per-issue structure and - Network accessline 12
- [canopycanopycanopy.com](https://canopycanopycanopy.com) - Triple Canopy. Themed digital-first sequenced issues with editorial restraint. Inherit the digital-first design discipline and the sequenced-issue numbering. - Network accessline 16
- [thedriftmag.com](https://thedriftmag.com) - Politically situated, generationally branded, identity-forward. A considered quarterly must avoid the political-statement register on conversion architecture, palette, and voice. - Network accessline 17
- [nplusonemag.com](https://nplusonemag.com) - Institutional NY cultural authority register. A considered quarterly should not borrow the geographic or generational positioning. - Network accessline 18
- [laphamsquarterly.org](https://laphamsquarterly.org) - Historical-source-driven format (passages from historical writing assembled around a theme). A different format entirely; canonical to that publication and not transferable. - Network accessline 19
- [thebeliever.net](https://www.thebeliever.net) - McSweeney's-adjacent geometric illustration identity. A type-led quarterly should not borrow the illustration-led visual treatment. - Network accessline 20
- [atavist.com](https://atavist.com) - Single-essay-per-issue reportage register. A multi-essay themed quarterly is a different shape. - Network accessline 21
- [themarginalian.org](https://themarginalian.org) - Single-author blog register. A multi-author themed quarterly is a different shape.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/heritage-local-service-barbershop.md
- Network accessline 9
- [therosemontbarbers.com](https://therosemontbarbers.com) - Cuts gallery, interior atmosphere, social-proof badge, real team page in the heritage register. - Network accessline 10
- [speakeasybarberlounge.com](https://speakeasybarberlounge.com) - Atmosphere-led, period-specific cues (lounge fittings, warm interior), interior photography carries the page. - Network accessline 11
- [franksdenver.com](https://franksdenver.com) - Heritage register at a higher-end price point; restrained palette, considered editorial layout. - Network accessline 12
- [alfanisbarbershop.com](https://alfanisbarbershop.com) - Small-operator heritage, atmosphere-forward, real-team page.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/hospitality-experience-balloon-ride.md
- Network accessline 9
- [nvaloft.com](https://nvaloft.com) - Regional operator, atmosphere-forward, dawn-palette imagery. - Network accessline 10
- [aerogelicballooning.com](https://aerogelicballooning.com) - Atmosphere-led, ride arc surfaced, photography drives the page. - Network accessline 11
- [rainbowryders.com](https://rainbowryders.com) - Multi-region operator, photography-led, named packages with prices. - Network accessline 12
- [sundanceballoons.com](https://sundanceballoons.com) - Multi-region operator, considered-warm register, ride-arc framing.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/luxe-considered-curated-stays-directory.md
- Network accessline 11
- [plumguide.com](https://plumguide.com) - The curated-design short-term-stay register: a small vetted collection rather than the long tail, each stay presented with editorial care. Inherit the curated-collection posture and the property-as - Network accessline 12
- [boutique-homes.com](https://boutique-homes.com) - The design-led curated-stays register: architecturally distinctive properties grouped by design feeling. Inherit the design-forward collection grouping and the generous property gallery; - Network accessline 13
- [onefinestay.com](https://onefinestay.com) - The upper-curated hospitality register: a small set of standout homes with a hotel-grade presentation. Inherit the restrained-confident chrome and the aspirational photo direction; do NOT pull
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.md
- Network accessline 9
- [themodernhouse.com](https://themodernhouse.com) - The canonical reference for the design-led residential brokerage register at editorial-restrained tier. Each listing reads as a small monograph; the architect is named in the listing card - Network accessline 10
- [phillips.com](https://phillips.com/design) - Phillips's design auction catalog register. The monograph treatment per lot (designer, year, materials, provenance) transfers cleanly to a residential listing. Inherit the per-lot monograph an - Network accessline 11
- [dezeen.com](https://dezeen.com) - The architectural press register. Listing-style architecture coverage with architect credits, year, materials, photography. Inherit the architecture-press literacy and the credit-line convention. - Network accessline 12
- [architecturaldigest.com](https://architecturaldigest.com) - The design-publication register with residential homes covered as design objects. Inherit the photography sensibility and the design-publication restraint. - Network accessline 16
- [zillow.com](https://zillow.com) - Mass-market portal; algorithmic listing presentation, estimated-value overlays, financing-first conversion. The register a luxe-considered brokerage must avoid on conversion architecture, palette, and vo - Network accessline 17
- [realtor.com](https://realtor.com) - Same mass-market portal register; broker-listing-syndication shape, generic photography presentation. - Network accessline 18
- [redfin.com](https://redfin.com) - Mass-market portal with light brokerage layer; price-anxiety scoring, financing partnerships surfaced as primary CTAs.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/minimal-essentialist-documentary-honest-trades-directory.md
- Network accessline 11
- [angi.com](https://angi.com) - The modern consolidated home-services directory register: category-and-location search, provider listings, the lead-handoff conversion. Inherit the search-first discovery spine and the category structure; do - Network accessline 12
- [thumbtack.com](https://thumbtack.com) - The matched-services register: structured by trade and location, provider profiles with comparable fields. Inherit the comparable-provider-profile anatomy; do NOT pull the blue palette or the get-m - Network accessline 13
- [houzz.com](https://houzz.com) - The visual-services-directory register: real work photography carrying the provider listings. Inherit the documentary work-in-context photography direction (a trade in progress, a finished job), not glamou
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/premium-dtc-maker-western-boots.md
- Network accessline 9
- [tecovas.com](https://tecovas.com) - The elevated-DTC reference: product-forward hero, named prices visible, restrained merchandising. No discount banners above the fold. - Network accessline 10
- [lucchese.com](https://lucchese.com) - Heritage register; serif-led, craft narrative as a supporting band rather than the lead. - Network accessline 11
- [oldgringoboots.com](https://oldgringoboots.com) - Smaller-maker, leather-forward photography, restrained editorial set instead of catalog density. - Network accessline 12
- [ranchroadboots.com](https://ranchroadboots.com) - Small-operator boutique competing in the same position; useful for cross-checking how a peer maker handles wayfinding on a small collection. - Network accessline 16
- [durangoboots.com](https://durangoboots.com) - Catalog-dense big-box texture; discount cadence, SKU-strip-above-the-fold, sale-badge pile. Not the register a premium small maker should pull from. - Network accessline 17
- [justinboots.com](https://justinboots.com) - Same big-box texture in a different brand; promotional banners and grid density dominate. - Network accessline 18
- [bootbarn.com](https://bootbarn.com) - Multi-brand retailer rather than a maker; merchandising-led rather than craft-led.
dist/pi/.agents/skills/creative-brief-selector/references/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.md
- Network accessline 9
- [bringatrailer.com](https://bringatrailer.com) - The canonical listing-detail transparency reference: full ownership history, mileage timeline, photograph density (forty to one hundred photographs per lot is typical), a comments thread th - Network accessline 10
- [icon4x4.com](https://icon4x4.com) - Editorial documentary register applied to working vehicles. Inherit the photography direction (vehicles photographed in landscape and at work, not glamour shots on a studio seamless), the considered ed - Network accessline 11
- [filson.com](https://filson.com) - Mountain West heritage workwear register. Inherit the palette tendency (granite, evergreen, oxblood, aspen gold; cool ground with restrained accents), the documentary photography that supports the type r - Network accessline 12
- [patagonia.com](https://patagonia.com) - The adjacent outdoor-utility register, useful as the second positive on voice (plain-direct, no marketing inflation, the audience treated as competent). - Network accessline 16
- [cargurus.com](https://cargurus.com) - Mass-market national passenger-car register; price-anxiety scoring as the hero, financing-first conversion architecture. The register a specialist regional marketplace must avoid on conversion archit - Network accessline 17
- [cars.com](https://cars.com) - Same mass-market national register; promotional banner cadence, broad-inventory generalist posture. - Network accessline 18
- [carvana.com](https://carvana.com) - DTC mass-market with vending-machine theatrics, financing-first. The register to avoid on theatrics and on conversion-flow priority. - Network accessline 19
- [autotempest.com](https://autotempest.com) - Meta-aggregator with no editorial voice; utility-only search-across-the-others. A specialist marketplace must not read as utility-only. - Network accessline 20
- [edmunds.com](https://edmunds.com) - Research-led advisory; content-heavy editorial sitting adjacent to a marketplace. A specialist marketplace must not read as a magazine pretending to be a marketplace.
dist/pi/.agents/skills/domain-strategy/SKILL.md
- Network accessline 149
- Configure 301 redirect for the non-canonical - Force HTTPS for both - Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical. - Network accessline 151
- Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical.
dist/pi/.agents/skills/frontend-component-build/references/accessibility-patterns.md
- Network accessline 53
<a href="https://external.com" target="_blank" rel="noopener noreferrer">
dist/pi/.agents/skills/funnel-flow-architecture/references/cross-tool-data-flow-patterns.md
- Access to secretsline 166
[Credential-related source omitted]
dist/pi/.agents/skills/integration-orchestrator/references/platform-implementation.md
- Network accessline 21
- **Availability.** Official remote MCP server, launched 2025. - **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](ht - Network accessline 22
- **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](https://github.com/atlassian/atlassian-mcp-server). - Network accessline 51
- **Availability.** Official, well-supported. - **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 52
- **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 77
- **Availability.** Official. - **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 78
- **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 103
- **Availability.** Figma Dev Mode MCP exists but is dev-mode-focused (component inspection, code generation, design token export). - **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 104
- **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 129
- **Availability.** Official. - **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server). - Network accessline 130
- **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server).
dist/pi/.agents/skills/internationalization/SKILL.md
- Network accessline 92
<link rel="alternate" hreflang="en-US" href="https://example.com/en-us/page"> - Network accessline 93
<link rel="alternate" hreflang="en-GB" href="https://example.com/en-gb/page"> - Network accessline 94
<link rel="alternate" hreflang="de-DE" href="https://example.com/de-de/page"> - Network accessline 95
<link rel="alternate" hreflang="x-default" href="https://example.com/en-us/page">
dist/pi/.agents/skills/oss-contribution-research/references/example-intake-item.md
- Network accessline 18
- item_id: feedparse-412-intake-empty-pubdate - repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - Network accessline 19
- repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - action: intake - Network accessline 20
- url: https://github.com/example-org/feedparse/issues/412 - Network accessline 23
## Policy allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and rev - Network accessline 24
allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and reviewed by t
dist/pi/.agents/skills/oss-contribution-research/references/policy-classification.md
- Network accessline 56
allows: CONTRIBUTING.md:63 "AI-assisted contributions are welcome" (https://...). Disclosure for issue_comment: [registry text].
dist/pi/.agents/skills/oss-contribution-research/references/queue-item-template.md
- Network accessline 11
- item_id: [unique slug, a-z 0-9 and -, 8 to 80 characters, e.g. feedparse-412-intake] - repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - Network accessline 12
- repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - action: [intake | pr | reply | close] - Network accessline 13
- url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item]
dist/pi/.agents/skills/oss-contribution-research/references/repro-record-template.md
- Network accessline 16
target: owner/repo#n, in a code span when the record is pasted into a queue item surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 17
surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 43
target: `example-org/chartkit#88` surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 44
surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 45
steps: 1. Open http://localhost:8080/?file=http://localhost:8080/fixtures/chart-3.0.json
dist/pi/.agents/skills/performance-optimization/references/optimization-playbook.md
- Network accessline 28
- Ensure web fonts don't block rendering (`font-display: swap`) - Inline critical CSS for the heading section - Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 30
- Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 112
Use WebPageTest or `curl -w "@curl-format.txt" -s -o /dev/null https://example.com` to measure just TTFB.
dist/pi/.agents/skills/pillar-content-architecture/references/cluster-piece-anatomy.md
- Network accessline 101
{ "@context": "https://schema.org", - Network accessline 102
"@context": "https://schema.org", - Network accessline 103
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 104
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 105
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 106
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
dist/pi/.agents/skills/pillar-content-architecture/references/pillar-page-anatomy.md
dist/pi/.agents/skills/pillar-content-architecture/references/url-structure-patterns.md
- Network accessline 68
{ "@context": "https://schema.org", - Network accessline 69
"@context": "https://schema.org", - Network accessline 70
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 71
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 72
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 73
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
dist/pi/.agents/skills/product-analytics-setup/references/schema-versioning-patterns.md
dist/pi/.agents/skills/qa-testing/SKILL.md
- Network accessline 157
fetch(window.location.origin, { method: 'HEAD' })
dist/pi/.agents/skills/security-baseline/SKILL.md
- Network accessline 144
Content-Security-Policy: script-src 'self' https://trusted.com; ...
dist/pi/.agents/skills/security-baseline/references/headers-checklist.md
- Network accessline 108
Content-Security-Policy: default-src 'self'; script-src 'self' https://trusted-cdn.com; - Network accessline 109
default-src 'self'; script-src 'self' https://trusted-cdn.com; style-src 'self' 'unsafe-inline'; - Network accessline 110
script-src 'self' https://trusted-cdn.com; - Network accessline 149
Permissions-Policy: camera=(self), geolocation=(self "https://maps.example.com") - Network accessline 209
Reporting-Endpoints: csp-endpoint="https://example.com/csp", default="https://example.com/reports" - Network accessline 288
curl -I https://example.com
dist/pi/.agents/skills/seo-aeo-geo/references/extraction-friendly-patterns.md
- Access to secretsline 175
[Credential-related source omitted]
dist/pi/.agents/skills/seo-aeo-geo/references/llms-txt-guide.md
- Network accessline 67
- [The Complete Guide to X](https://example.com/complete-guide-x): A 5,000-word reference covering fundamentals through advanced topics. - Network accessline 68
- [How to Choose Y](https://example.com/how-to-choose-y): Decision framework with comparison tables and worked examples. - Network accessline 69
- [The Beginner's Guide to Z](https://example.com/beginner-z): A 30-minute primer for someone new to the topic. - Network accessline 73
- [A vs B](https://example.com/a-vs-b): Head-to-head feature, pricing, and use case comparison. - Network accessline 74
- [Top 10 [Category]](https://example.com/top-10): Ranked list with selection criteria. - Network accessline 78
- [Calculator](https://example.com/calculator): Free interactive tool for [purpose]. - Network accessline 79
- [Templates](https://example.com/templates): Downloadable templates with examples. - Network accessline 83
- [About us](https://example.com/about) - Network accessline 84
- [Methodology](https://example.com/methodology) - Network accessline 85
- [Editorial standards](https://example.com/editorial-standards) - Network accessline 101
- [How it works](https://example.com/product): Overview of core functionality and architecture. - Network accessline 102
- [Pricing](https://example.com/pricing): Transparent pricing tiers and what each includes. - Network accessline 103
- [Integrations](https://example.com/integrations): Third-party tools we connect with. - Network accessline 107
- [Getting started](https://docs.example.com/getting-started): 15-minute setup guide. - Network accessline 108
- [API reference](https://docs.example.com/api): Complete API documentation. - Network accessline 109
- [Best practices](https://docs.example.com/best-practices): How successful customers use the product. - Network accessline 113
- [Customer stories](https://example.com/customers): How specific customers achieved specific outcomes. - Network accessline 114
- [Blog](https://example.com/blog): Engineering posts, product updates, and industry analysis. - Network accessline 115
- [Changelog](https://example.com/changelog): Recent product changes. - Network accessline 119
- [Security](https://example.com/security): SOC 2, encryption, compliance. - Network accessline 120
- [Privacy policy](https://example.com/privacy) - Network accessline 121
- [Terms of service](https://example.com/terms) - Network accessline 201
- [Full content dump](https://example.com/llms-full.txt): The complete content of all linked pages. - Network accessline 221
- [ ] File is at `https://yourdomain.com/llms.txt` (root)
dist/pi/.agents/skills/seo-backlink-audit/references/toxic-link-criteria.md
- Network accessline 108
https://otherwiselegitimate-example.com/sponsored-post-page
dist/pi/.agents/skills/seo-technical/references/audit-template.md
- Network accessline 41
- [ ] Critical sections of the site are not accidentally disallowed - [ ] Specific user agents are not blocked (`Googlebot`, `Bingbot`) - [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 43
- [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 227
- [ ] Both `https://www` and `https://` (and `http://` versions) verified as separate properties
skills/accessibility-audit/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-accessibility-audit): the same accessibility audit tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** Tier 1, the first tasks built for this job. - **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-09-26. - **Full results:** [openaddict.com/skills/rampstackco-accessibility-audit](https://openaddict.com/skills/r - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-accessibility-audit](https://openaddict.com/skills/rampstackco-accessibility-audit)
skills/accessibility-audit/references/aria-patterns.md
- Network accessline 457
- W3C ARIA Authoring Practices Guide (APG): https://www.w3.org/WAI/ARIA/apg/. Patterns and examples. - Network accessline 458
- WAI-ARIA 1.2 specification: https://www.w3.org/TR/wai-aria-1.2/. Canonical reference. - Network accessline 459
- The W3C ARIA Roles, States, and Properties listing: https://www.w3.org/TR/wai-aria-1.2/#role_definitions. Searchable.
skills/accessibility-audit/references/wcag-quick-reference.md
- Network accessline 5
For the canonical specification, refer to W3C: https://www.w3.org/TR/WCAG21/
skills/ads-creative-development/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/ads-performance-analytics/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/after-action-report/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/ai-content-collaboration/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/analytics-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/art-direction/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/backup-and-disaster-recovery/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/beta-program-management/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-archetype-system/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-discovery/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-ideation/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-identity/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-style-guide/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/brand-voice/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-brand-voice): the same voice tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** The site publishes no tier for this job. - **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-08-30. - **Full results:** [openaddict.com/skills/rampstackco-brand-voice](https://openaddict.com/skills/rampstackco- - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-brand-voice](https://openaddict.com/skills/rampstackco-brand-voice)
skills/calculator-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/chatbot-flow-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/code-review-web/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-code-review-web): the same code review tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** Tier 1, the first tasks built for this job. Helped on Tier 3, GPT-5 mini via API: +26.7 percentage points (+3.2 to +50.1). - **Date:** pinned at commit `a67dd34`; newest run 2026-09-26. - **Full results:** [openaddict.com/skills - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-code-review-web](https://openaddict.com/skills/rampstackco-code-review-web)
skills/code-review-web/references/nextjs-patterns.md
- Network accessline 94
const config = { env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Network accessline 95
env: { SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", }, - Network accessline 96
SITE_URL: process.env.SITE_URL ?? "https://yourdomain.com", - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Network accessline 245
[Credential-related source omitted] - Access to secretsline 245
[Credential-related source omitted] - Network accessline 259
WP_API_URL=https://cms.yourdomain.com/wp-json # correct - Network accessline 260
WP_API_URL=https://yourdomain.com/wp-json # loops back to Next.js
skills/code-review-web/references/wordpress-headless-patterns.md
- Network accessline 29
WP_API_URL=https://cms.yourdomain.com/wp-json - Network accessline 35
WP_API_URL=https://yourdomain.com/wp-json # this will break after DNS cutover - Network accessline 51
define("WP_HOME", "https://cms.yourdomain.com"); - Network accessline 52
define("WP_SITEURL", "https://cms.yourdomain.com"); - Network accessline 68
<img src="https://cms.yourdomain.com/wp-content/uploads/photo.jpg" alt="..." /> - Network accessline 79
// Convert CMS media URL to a pattern the frontend image optimizer accepts function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); - Network accessline 80
function rewriteMediaUrl(url: string): string { return url.replace("https://cms.yourdomain.com", ""); } - Network accessline 81
return url.replace("https://cms.yourdomain.com", ""); - Network accessline 89
If editors paste full URLs into the content (`<img src="https://cms.yourdomain.com/...">`), changing the CMS subdomain later breaks every reference. Use relative paths or template-rendered URLs instead. - Network accessline 95
WordPress posts have a `link` field in the API response that returns the WordPress-rendered URL (e.g., `https://cms.yourdomain.com/post-slug/`). This is wrong for the public-facing site. - Network accessline 122
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 138
wp_remote_post('https://yourdomain.com/api/revalidate', [ - Network accessline 155
const posts = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 176
const res = await fetch(`${WP_API_URL}/wp/v2/posts`, { - Network accessline 210
const res = await fetch(`${WP_API_URL}/wp/v2/posts?per_page=100`); - Network accessline 240
const res = await fetch(`${WP_API_URL}/wp/v2/posts?_embed=true`);
skills/comparison-tool-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/competitor-experience-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/competitor-experience-audit/references/experience-dimensions-checklist.md
- Network accessline 19
Rendered required: **partial.** The primary task can usually be identified from a static fetch (it is in the markup), but its visual dominance and protection from competitors requires the rendered view.
skills/content-and-copy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-brief-authoring/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-distribution/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-migration/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-migration/references/migration-runbook.md
skills/content-refresh-system/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-repurposing/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/content-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/cost-optimization/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/creative-brief-selector/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/creative-brief-selector/references/05-section-shapes-vocabulary.md
- Network accessline 17
- **When it fits**: brands where the photograph and the type carry roughly equal weight and the eye is meant to ricochet between them. Premium DTC product hero is the canonical fit; a single product on the image side and a price-and-CTA on - Network accessline 18
- **References**: [allbirds.com](https://allbirds.com), [tecovas.com](https://tecovas.com). - Network accessline 25
- **When it fits**: inventory marketplaces, regional specialists, sites where the photograph signals what the marketplace is for and the band carries the controls. Also fits magazine-style editorial registers where one strong image opens an - Network accessline 26
- **References**: [bringatrailer.com](https://bringatrailer.com), [icon4x4.com](https://icon4x4.com). - Network accessline 33
- **When it fits**: hospitality experiences where the place is the product (balloon ride, restaurant, hotel), mission-driven nonprofits where the documentary photograph is the evidence, premium B2B where the product is photographed at scale - Network accessline 34
- **References**: [bombasses.com](https://bombasses.com) (hospitality), [charitywater.org](https://charitywater.org) (institution-mission). - Network accessline 41
- **When it fits**: editorial publications, ideas-led brands, B2B SaaS where the proposition is conceptual, premium consultancies, law and finance where understated credibility is the play. - **References**: [nytimes.com](https://nytimes.co - Network accessline 42
- **References**: [nytimes.com](https://nytimes.com), [stripe.com](https://stripe.com) (mild type-led, with type leading and a subtle product render below). - Network accessline 49
- **When it fits**: portfolio brands, atmospheric or contemplative registers, single-product brands where the page is essentially a long-scroll story and the hero is just the opening line. - **References**: [linear.app](https://linear.app), - Network accessline 50
- **References**: [linear.app](https://linear.app), [framer.com](https://framer.com) (both run centered single-column heroes at times). - Network accessline 57
- **When it fits**: magazine cover style, photography portfolios, single-product hero where the product carries everything and the type is a caption-scale credit line. - **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.c - Network accessline 58
- **References**: [magnumphotos.com](https://magnumphotos.com), [aesop.com](https://aesop.com) (varies; some pages use asymmetric layouts). - Network accessline 65
- **When it fits**: directory and marketplace shapes where the breadth of the catalog is the value, ecommerce catalog shapes where shoppability above the fold is the conversion lever. - **References**: [airbnb.com](https://airbnb.com) (sear - Network accessline 66
- **References**: [airbnb.com](https://airbnb.com) (search results hero is the grid), [unsplash.com](https://unsplash.com). - Network accessline 73
- **When it fits**: B2B engineering procurement, hardware comparison sites, financial product comparison, anywhere the buyer is data-anchored before they care about photography. - **References**: [parametricportfolio.com](https://www.parame - Network accessline 74
- **References**: [parametricportfolio.com](https://www.parametricportfolio.com), [substack.com/pricing](https://substack.com/pricing) (pricing-table-as-hero variants). - Network accessline 93
- **When it fits**: ecommerce catalog with deep category trees, multi-tenant marketplaces with seller-side and buyer-side links, B2B sites with documentation libraries. - **References**: [amazon.com](https://amazon.com), [shopify.com](https - Network accessline 94
- **References**: [amazon.com](https://amazon.com), [shopify.com](https://shopify.com), most large retailers. - Network accessline 101
- **When it fits**: ideas-led brands, single-page narratives, publications where the nav lives in the top chrome and the bottom is just the credit line. - **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), port - Network accessline 102
- **References**: [pitchfork.com](https://pitchfork.com) (varies; minimal footer), portfolio sites. - Network accessline 109
- **When it fits**: publications, magazine sites, editorial collectives, organizations where the people are the brand. - **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 110
- **References**: [theatlantic.com](https://theatlantic.com), [theverge.com](https://theverge.com). - Network accessline 117
- **When it fits**: content sites, newsletter-first publications, brands where the newsletter is the customer-relationship channel. - **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 118
- **References**: [substack.com](https://substack.com), most content sites operating newsletter-led growth. - Network accessline 125
- **When it fits**: conversion-led sites where the bottom of the page is the second-most-attended surface (after the hero), marketing sites, B2B with a sign-up funnel. - **References**: [vercel.com](https://vercel.com), [linear.app](https:/ - Network accessline 126
- **References**: [vercel.com](https://vercel.com), [linear.app](https://linear.app).
skills/creative-brief-selector/references/reference-bank/bold-confident-editorial-restrained-aaa-game-studio.md
- Network accessline 9
- [bungie.net](https://bungie.net) - The canonical AAA-action studio chrome register: cinematic full-bleed key-art hero, dark-mode-first ground, restrained type chrome that lets the game art carry. Inherit the cinematic hero treatment, the - Network accessline 10
- [insomniac.games](https://insomniac.games) - Insomniac Games. The studio chrome at composed-cinematic; the titles portfolio surfaced with care. Inherit the titles-portfolio anatomy and the craft-proud-without-arrogance voice. - Network accessline 11
- [naughtydog.com](https://naughtydog.com) - Naughty Dog. The restrained-cinematic studio register; type-led studio band with the team presented at masthead density. Inherit the studio-band convention and the restrained-cinematic chrome. - Network accessline 12
- [remedygames.com](https://remedygames.com) - Remedy Entertainment. The composed-cinematic register at the studio level, with a smaller portfolio presented with editorial discipline. Inherit the title-detail-page-as-small-monograph anatomy - Network accessline 16
- [steampowered.com](https://steampowered.com) - Steam. Platform chrome that hosts third-party content. Wrong vertical (platform, not studio); the platform chrome reads totally different from a studio's content-creator brand. - Network accessline 17
- [itch.io](https://itch.io) - Itch.io. Indie game platform; minimal chrome; wrong register and wrong vertical.
skills/creative-brief-selector/references/reference-bank/bold-confident-vibrant-saturated-single-ip-game-title.md
- Network accessline 11
- [marathonthegame.com](https://marathonthegame.com) - The saturated single-IP marketing register at its most committed: a published title's own brand, dark-mode-first, with the title's palette and art carrying the saturation rather than th - Network accessline 12
- [deathstranding.com](https://deathstranding.com) - Single-IP world-immersion marketing: the site immerses the visitor in one world (the setting, the lore) in the game's own voice rather than the studio's. Inherit the world-as-protagonist - Network accessline 13
- [cyberpunk.net](https://cyberpunk.net) - Saturated single-IP launch register: type at title-card scale, palette depth carrying the world's own tones. Inherit the type-at-scale and palette-depth treatment; do NOT pull the neon-magenta iden - Network accessline 14
- [bandainamcoent.com/games/elden-ring](https://www.bandainamcoent.com/games/elden-ring) - Single-IP lore-immersion marketing: a world page that treats the world as the protagonist with deep lore in the title's voice. Inherit the lore-immer - Network accessline 18
- Studio and publisher portfolio sites ([bungie.net](https://bungie.net), [naughtydog.com](https://naughtydog.com), and the paired `bold-confident-editorial-restrained-aaa-game-studio` register) - The studio chrome composes and recedes to l - Network accessline 19
- Platform-chrome sites ([steampowered.com](https://steampowered.com), [store.epicgames.com](https://store.epicgames.com), [itch.io](https://itch.io)) - Platforms host third-party content and lean restrained to let the content carry. A sing
skills/creative-brief-selector/references/reference-bank/editorial-restrained-documentary-honest-specialty-coffee-subscription.md
- Network accessline 9
- [drinktrade.com](https://drinktrade.com) - Subscriber-first commerce explicit: cadence picker on the home, match-quiz to find your roast, pause and swap surfaced as features rather than buried in account settings. Editorial-restrained typ - Network accessline 10
- [counterculturecoffee.com](https://counterculturecoffee.com) - Specialty roaster with subscription surfaced; documentary photography of farms and farmers carries the page; editorial type. The canonical reference for "farm-direct specialty - Network accessline 11
- [onyxcoffeelab.com](https://onyxcoffeelab.com) - Editorial-restrained register at its most refined: type-led, considered photography, premium-but-approachable. Useful as the type-system reference (small-caps, restrained tracking, editoria - Network accessline 12
- [atlascoffeeclub.com](https://atlascoffeeclub.com) - Subscriber-first explicitly with a world-coffee-journey narrative. The closest match to the "one origin a month, named farm, named process" positioning. Useful for how to surface the ro - Network accessline 16
- [starbucks.com](https://starbucks.com) - Mass-market grocery register; frappuccino lifestyle photography; promotional cadence dominates the homepage. The register a specialty roaster must not pull from. - Network accessline 17
- [folgerscoffee.com](https://folgerscoffee.com) - Commodity grocery brand; red-can heritage but no specialty register. The bottom of the grocery shelf, conceptually.
skills/creative-brief-selector/references/reference-bank/editorial-restrained-literary-quarterly.md
- Network accessline 9
- [aeon.co](https://aeon.co) - Multidisciplinary ideas register. Considered design, restrained palette (warm-grey ground with deep type and a single accent), essays at substantial length, multiple disciplines per surface. Inherit the ideas- - Network accessline 10
- [thepointmag.com](https://thepointmag.com) - Themed multi-author essay structure at length. The closest peer on the audience axis (broadly literary readers across disciplines). Inherit the multi-author themed-issue treatment and the essay - Network accessline 11
- [cabinetmagazine.org](https://cabinetmagazine.org) - The closest structural anchor in the field: each issue is organized around a single thematic question rendered with editorial restraint. Inherit the single-theme-per-issue structure and - Network accessline 12
- [canopycanopycanopy.com](https://canopycanopycanopy.com) - Triple Canopy. Themed digital-first sequenced issues with editorial restraint. Inherit the digital-first design discipline and the sequenced-issue numbering. - Network accessline 16
- [thedriftmag.com](https://thedriftmag.com) - Politically situated, generationally branded, identity-forward. A considered quarterly must avoid the political-statement register on conversion architecture, palette, and voice. - Network accessline 17
- [nplusonemag.com](https://nplusonemag.com) - Institutional NY cultural authority register. A considered quarterly should not borrow the geographic or generational positioning. - Network accessline 18
- [laphamsquarterly.org](https://laphamsquarterly.org) - Historical-source-driven format (passages from historical writing assembled around a theme). A different format entirely; canonical to that publication and not transferable. - Network accessline 19
- [thebeliever.net](https://www.thebeliever.net) - McSweeney's-adjacent geometric illustration identity. A type-led quarterly should not borrow the illustration-led visual treatment. - Network accessline 20
- [atavist.com](https://atavist.com) - Single-essay-per-issue reportage register. A multi-essay themed quarterly is a different shape. - Network accessline 21
- [themarginalian.org](https://themarginalian.org) - Single-author blog register. A multi-author themed quarterly is a different shape.
skills/creative-brief-selector/references/reference-bank/heritage-local-service-barbershop.md
- Network accessline 9
- [therosemontbarbers.com](https://therosemontbarbers.com) - Cuts gallery, interior atmosphere, social-proof badge, real team page in the heritage register. - Network accessline 10
- [speakeasybarberlounge.com](https://speakeasybarberlounge.com) - Atmosphere-led, period-specific cues (lounge fittings, warm interior), interior photography carries the page. - Network accessline 11
- [franksdenver.com](https://franksdenver.com) - Heritage register at a higher-end price point; restrained palette, considered editorial layout. - Network accessline 12
- [alfanisbarbershop.com](https://alfanisbarbershop.com) - Small-operator heritage, atmosphere-forward, real-team page.
skills/creative-brief-selector/references/reference-bank/hospitality-experience-balloon-ride.md
- Network accessline 9
- [nvaloft.com](https://nvaloft.com) - Regional operator, atmosphere-forward, dawn-palette imagery. - Network accessline 10
- [aerogelicballooning.com](https://aerogelicballooning.com) - Atmosphere-led, ride arc surfaced, photography drives the page. - Network accessline 11
- [rainbowryders.com](https://rainbowryders.com) - Multi-region operator, photography-led, named packages with prices. - Network accessline 12
- [sundanceballoons.com](https://sundanceballoons.com) - Multi-region operator, considered-warm register, ride-arc framing.
skills/creative-brief-selector/references/reference-bank/luxe-considered-curated-stays-directory.md
- Network accessline 11
- [plumguide.com](https://plumguide.com) - The curated-design short-term-stay register: a small vetted collection rather than the long tail, each stay presented with editorial care. Inherit the curated-collection posture and the property-as - Network accessline 12
- [boutique-homes.com](https://boutique-homes.com) - The design-led curated-stays register: architecturally distinctive properties grouped by design feeling. Inherit the design-forward collection grouping and the generous property gallery; - Network accessline 13
- [onefinestay.com](https://onefinestay.com) - The upper-curated hospitality register: a small set of standout homes with a hotel-grade presentation. Inherit the restrained-confident chrome and the aspirational photo direction; do NOT pull
skills/creative-brief-selector/references/reference-bank/luxe-considered-editorial-restrained-residential-architectural-brokerage.md
- Network accessline 9
- [themodernhouse.com](https://themodernhouse.com) - The canonical reference for the design-led residential brokerage register at editorial-restrained tier. Each listing reads as a small monograph; the architect is named in the listing card - Network accessline 10
- [phillips.com](https://phillips.com/design) - Phillips's design auction catalog register. The monograph treatment per lot (designer, year, materials, provenance) transfers cleanly to a residential listing. Inherit the per-lot monograph an - Network accessline 11
- [dezeen.com](https://dezeen.com) - The architectural press register. Listing-style architecture coverage with architect credits, year, materials, photography. Inherit the architecture-press literacy and the credit-line convention. - Network accessline 12
- [architecturaldigest.com](https://architecturaldigest.com) - The design-publication register with residential homes covered as design objects. Inherit the photography sensibility and the design-publication restraint. - Network accessline 16
- [zillow.com](https://zillow.com) - Mass-market portal; algorithmic listing presentation, estimated-value overlays, financing-first conversion. The register a luxe-considered brokerage must avoid on conversion architecture, palette, and vo - Network accessline 17
- [realtor.com](https://realtor.com) - Same mass-market portal register; broker-listing-syndication shape, generic photography presentation. - Network accessline 18
- [redfin.com](https://redfin.com) - Mass-market portal with light brokerage layer; price-anxiety scoring, financing partnerships surfaced as primary CTAs.
skills/creative-brief-selector/references/reference-bank/minimal-essentialist-documentary-honest-trades-directory.md
- Network accessline 11
- [angi.com](https://angi.com) - The modern consolidated home-services directory register: category-and-location search, provider listings, the lead-handoff conversion. Inherit the search-first discovery spine and the category structure; do - Network accessline 12
- [thumbtack.com](https://thumbtack.com) - The matched-services register: structured by trade and location, provider profiles with comparable fields. Inherit the comparable-provider-profile anatomy; do NOT pull the blue palette or the get-m - Network accessline 13
- [houzz.com](https://houzz.com) - The visual-services-directory register: real work photography carrying the provider listings. Inherit the documentary work-in-context photography direction (a trade in progress, a finished job), not glamou
skills/creative-brief-selector/references/reference-bank/premium-dtc-maker-western-boots.md
- Network accessline 9
- [tecovas.com](https://tecovas.com) - The elevated-DTC reference: product-forward hero, named prices visible, restrained merchandising. No discount banners above the fold. - Network accessline 10
- [lucchese.com](https://lucchese.com) - Heritage register; serif-led, craft narrative as a supporting band rather than the lead. - Network accessline 11
- [oldgringoboots.com](https://oldgringoboots.com) - Smaller-maker, leather-forward photography, restrained editorial set instead of catalog density. - Network accessline 12
- [ranchroadboots.com](https://ranchroadboots.com) - Small-operator boutique competing in the same position; useful for cross-checking how a peer maker handles wayfinding on a small collection. - Network accessline 16
- [durangoboots.com](https://durangoboots.com) - Catalog-dense big-box texture; discount cadence, SKU-strip-above-the-fold, sale-badge pile. Not the register a premium small maker should pull from. - Network accessline 17
- [justinboots.com](https://justinboots.com) - Same big-box texture in a different brand; promotional banners and grid density dominate. - Network accessline 18
- [bootbarn.com](https://bootbarn.com) - Multi-brand retailer rather than a maker; merchandising-led rather than craft-led.
skills/creative-brief-selector/references/reference-bank/rugged-utilitarian-documentary-honest-regional-used-vehicle-marketplace.md
- Network accessline 9
- [bringatrailer.com](https://bringatrailer.com) - The canonical listing-detail transparency reference: full ownership history, mileage timeline, photograph density (forty to one hundred photographs per lot is typical), a comments thread th - Network accessline 10
- [icon4x4.com](https://icon4x4.com) - Editorial documentary register applied to working vehicles. Inherit the photography direction (vehicles photographed in landscape and at work, not glamour shots on a studio seamless), the considered ed - Network accessline 11
- [filson.com](https://filson.com) - Mountain West heritage workwear register. Inherit the palette tendency (granite, evergreen, oxblood, aspen gold; cool ground with restrained accents), the documentary photography that supports the type r - Network accessline 12
- [patagonia.com](https://patagonia.com) - The adjacent outdoor-utility register, useful as the second positive on voice (plain-direct, no marketing inflation, the audience treated as competent). - Network accessline 16
- [cargurus.com](https://cargurus.com) - Mass-market national passenger-car register; price-anxiety scoring as the hero, financing-first conversion architecture. The register a specialist regional marketplace must avoid on conversion archit - Network accessline 17
- [cars.com](https://cars.com) - Same mass-market national register; promotional banner cadence, broad-inventory generalist posture. - Network accessline 18
- [carvana.com](https://carvana.com) - DTC mass-market with vending-machine theatrics, financing-first. The register to avoid on theatrics and on conversion-flow priority. - Network accessline 19
- [autotempest.com](https://autotempest.com) - Meta-aggregator with no editorial voice; utility-only search-across-the-others. A specialist marketplace must not read as utility-only. - Network accessline 20
- [edmunds.com](https://edmunds.com) - Research-led advisory; content-heavy editorial sitting adjacent to a marketplace. A specialist marketplace must not read as a magazine pretending to be a marketplace.
skills/creative-brief/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/creative-direction/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/cro-optimization/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/data-warehouse-experimentation/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/dependency-management/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/design-standards/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/design-system/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/discovery-research-synthesis/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/dispatch-authoring/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/documentation-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/domain-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/domain-strategy/SKILL.md
- Network accessline 149
- Configure 301 redirect for the non-canonical - Force HTTPS for both - Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical. - Network accessline 151
- Verify with curl: `curl -I http://example.com`, `curl -I http://www.example.com`, `curl -I https://www.example.com`. All should chain to a single 200 on the canonical.
skills/editorial-qa/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/email-deliverability/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/email-sequences/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/evidence-based-reviews/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/experiment-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/experimentation-analytics/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/experimentation-platform-orchestrator/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/feature-flagging/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/feature-launch-playbook/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/form-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/frontend-component-build/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/frontend-component-build/references/accessibility-patterns.md
- Network accessline 53
<a href="https://external.com" target="_blank" rel="noopener noreferrer">
skills/funnel-flow-architecture/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/funnel-flow-architecture/references/cross-tool-data-flow-patterns.md
- Access to secretsline 166
[Credential-related source omitted]
skills/incident-response/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/information-architecture/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/integration-orchestrator/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/integration-orchestrator/references/platform-implementation.md
- Network accessline 21
- **Availability.** Official remote MCP server, launched 2025. - **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](ht - Network accessline 22
- **References.** [Atlassian's Remote MCP Server announcement](https://www.atlassian.com/blog/announcements/remote-mcp-server) and [github.com/atlassian/atlassian-mcp-server](https://github.com/atlassian/atlassian-mcp-server). - Network accessline 51
- **Availability.** Official, well-supported. - **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 52
- **Reference.** [linear.app/docs/mcp](https://linear.app/docs/mcp). - Network accessline 77
- **Availability.** Official. - **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 78
- **Reference.** [developers.notion.com/guides/mcp/overview](https://developers.notion.com/guides/mcp/overview). - Network accessline 103
- **Availability.** Figma Dev Mode MCP exists but is dev-mode-focused (component inspection, code generation, design token export). - **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 104
- **Reference.** Figma's [Dev Mode documentation](https://www.figma.com/dev-mode/). - Network accessline 129
- **Availability.** Official. - **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server). - Network accessline 130
- **Reference.** [github.com/github/github-mcp-server](https://github.com/github/github-mcp-server).
skills/interactive-product-tour/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/internationalization/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/internationalization/SKILL.md
- Network accessline 92
<link rel="alternate" hreflang="en-US" href="https://example.com/en-us/page"> - Network accessline 93
<link rel="alternate" hreflang="en-GB" href="https://example.com/en-gb/page"> - Network accessline 94
<link rel="alternate" hreflang="de-DE" href="https://example.com/de-de/page"> - Network accessline 95
<link rel="alternate" hreflang="x-default" href="https://example.com/en-us/page">
skills/journey-mapping/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/jtbd-framing/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/landing-page-copy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/launch-runbook/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/lead-magnet-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/logo-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/long-form-content-frameworks/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/media-asset-management/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/monitoring-and-alerting/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/multi-step-form-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/okr-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/onboarding-wizard-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/oss-contribution-research/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/oss-contribution-research/references/example-intake-item.md
- Network accessline 18
- item_id: feedparse-412-intake-empty-pubdate - repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - Network accessline 19
- repo: example-org/feedparse - url: https://github.com/example-org/feedparse/issues/412 - action: intake - Network accessline 20
- url: https://github.com/example-org/feedparse/issues/412 - Network accessline 23
## Policy allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and rev - Network accessline 24
allows: CONTRIBUTING.md:41 "AI-assisted contributions are welcome if disclosed" (https://github.com/example-org/feedparse/blob/main/CONTRIBUTING.md). Disclosure for issue_comment: say the comment was drafted by an AI agent and reviewed by t
skills/oss-contribution-research/references/policy-classification.md
- Network accessline 56
allows: CONTRIBUTING.md:63 "AI-assisted contributions are welcome" (https://...). Disclosure for issue_comment: [registry text].
skills/oss-contribution-research/references/queue-item-template.md
- Network accessline 11
- item_id: [unique slug, a-z 0-9 and -, 8 to 80 characters, e.g. feedparse-412-intake] - repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - Network accessline 12
- repo: [owner/repo] - url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item] - action: [intake | pr | reply | close] - Network accessline 13
- url: [https://github.com/owner/repo/issues/N, or /pull/N for a reply on a PR, a ping, or a close; the one full URL in the item]
skills/oss-contribution-research/references/repro-record-template.md
- Network accessline 16
target: owner/repo#n, in a code span when the record is pasted into a queue item surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 17
surface: where the assertion ran: a local build at http://localhost:<port>, a CLI command, a test runner, a hosted page - Network accessline 43
target: `example-org/chartkit#88` surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 44
surface: local build of the viewer at http://localhost:8080, served from the repo's `viewer/dist` - Network accessline 45
steps: 1. Open http://localhost:8080/?file=http://localhost:8080/fixtures/chart-3.0.json
skills/paid-media-strategy/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/performance-optimization/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/performance-optimization/references/optimization-playbook.md
- Network accessline 28
- Ensure web fonts don't block rendering (`font-display: swap`) - Inline critical CSS for the heading section - Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 30
- Preconnect to font origin: `<link rel="preconnect" href="https://fonts.example.com">` - Network accessline 112
Use WebPageTest or `curl -w "@curl-format.txt" -s -o /dev/null https://example.com` to measure just TTFB.
skills/pillar-content-architecture/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/pillar-content-architecture/references/cluster-piece-anatomy.md
- Network accessline 101
{ "@context": "https://schema.org", - Network accessline 102
"@context": "https://schema.org", - Network accessline 103
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 104
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 105
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 106
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
skills/pillar-content-architecture/references/pillar-page-anatomy.md
skills/pillar-content-architecture/references/url-structure-patterns.md
- Network accessline 68
{ "@context": "https://schema.org", - Network accessline 69
"@context": "https://schema.org", - Network accessline 70
"@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 71
"itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, { "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" } - Network accessline 72
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com/" }, - Network accessline 73
{ "@type": "ListItem", "position": 2, "name": "Feature flag rollout", "item": "https://example.com/feature-flag-rollout/" },
skills/pm-spec-writing/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-pm-spec-writing): the same spec writing tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** Tier 1, the first tasks built for this job. - **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-09-26. - **Full results:** [openaddict.com/skills/rampstackco-pm-spec-writing](https://openaddict.com/skills/ramps - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-pm-spec-writing](https://openaddict.com/skills/rampstackco-pm-spec-writing)
skills/product-analytics-setup/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/product-analytics-setup/references/schema-versioning-patterns.md
skills/product-configurator-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/programmatic-seo/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/qa-testing/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/qa-testing/SKILL.md
- Network accessline 157
fetch(window.location.origin, { method: 'HEAD' })
skills/quiz-and-assessment-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/roadmap-planning/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/scheduler-and-booking-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/security-baseline/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/security-baseline/SKILL.md
- Network accessline 144
Content-Security-Policy: script-src 'self' https://trusted.com; ...
skills/security-baseline/references/headers-checklist.md
- Network accessline 108
Content-Security-Policy: default-src 'self'; script-src 'self' https://trusted-cdn.com; - Network accessline 109
default-src 'self'; script-src 'self' https://trusted-cdn.com; style-src 'self' 'unsafe-inline'; - Network accessline 110
script-src 'self' https://trusted-cdn.com; - Network accessline 149
Permissions-Policy: camera=(self), geolocation=(self "https://maps.example.com") - Network accessline 209
Reporting-Endpoints: csp-endpoint="https://example.com/csp", default="https://example.com/reports" - Network accessline 288
curl -I https://example.com
skills/seo-aeo-geo/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-aeo-geo/references/extraction-friendly-patterns.md
- Access to secretsline 175
[Credential-related source omitted]
skills/seo-aeo-geo/references/llms-txt-guide.md
- Network accessline 67
- [The Complete Guide to X](https://example.com/complete-guide-x): A 5,000-word reference covering fundamentals through advanced topics. - Network accessline 68
- [How to Choose Y](https://example.com/how-to-choose-y): Decision framework with comparison tables and worked examples. - Network accessline 69
- [The Beginner's Guide to Z](https://example.com/beginner-z): A 30-minute primer for someone new to the topic. - Network accessline 73
- [A vs B](https://example.com/a-vs-b): Head-to-head feature, pricing, and use case comparison. - Network accessline 74
- [Top 10 [Category]](https://example.com/top-10): Ranked list with selection criteria. - Network accessline 78
- [Calculator](https://example.com/calculator): Free interactive tool for [purpose]. - Network accessline 79
- [Templates](https://example.com/templates): Downloadable templates with examples. - Network accessline 83
- [About us](https://example.com/about) - Network accessline 84
- [Methodology](https://example.com/methodology) - Network accessline 85
- [Editorial standards](https://example.com/editorial-standards) - Network accessline 101
- [How it works](https://example.com/product): Overview of core functionality and architecture. - Network accessline 102
- [Pricing](https://example.com/pricing): Transparent pricing tiers and what each includes. - Network accessline 103
- [Integrations](https://example.com/integrations): Third-party tools we connect with. - Network accessline 107
- [Getting started](https://docs.example.com/getting-started): 15-minute setup guide. - Network accessline 108
- [API reference](https://docs.example.com/api): Complete API documentation. - Network accessline 109
- [Best practices](https://docs.example.com/best-practices): How successful customers use the product. - Network accessline 113
- [Customer stories](https://example.com/customers): How specific customers achieved specific outcomes. - Network accessline 114
- [Blog](https://example.com/blog): Engineering posts, product updates, and industry analysis. - Network accessline 115
- [Changelog](https://example.com/changelog): Recent product changes. - Network accessline 119
- [Security](https://example.com/security): SOC 2, encryption, compliance. - Network accessline 120
- [Privacy policy](https://example.com/privacy) - Network accessline 121
- [Terms of service](https://example.com/terms) - Network accessline 201
- [Full content dump](https://example.com/llms-full.txt): The complete content of all linked pages. - Network accessline 221
- [ ] File is at `https://yourdomain.com/llms.txt` (root)
skills/seo-audit-orchestration/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-backlink-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-backlink-audit/references/toxic-link-criteria.md
- Network accessline 108
https://otherwiselegitimate-example.com/sponsored-post-page
skills/seo-competitor/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-content-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-content-gap-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-keyword-gap-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-keyword/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-offpage/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-onpage/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-seo-onpage): the same on-page audit tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** Tier 1, the first tasks built for this job. - **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-09-26. - **Full results:** [openaddict.com/skills/rampstackco-seo-onpage](https://openaddict.com/skills/rampstackc - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-seo-onpage](https://openaddict.com/skills/rampstackco-seo-onpage)
skills/seo-rank-tracking/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-site-health-audit/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-technical/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/seo-technical/references/audit-template.md
- Network accessline 41
- [ ] Critical sections of the site are not accidentally disallowed - [ ] Specific user agents are not blocked (`Googlebot`, `Bingbot`) - [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 43
- [ ] Sitemap location is declared (`Sitemap: https://example.com/sitemap.xml`) - Network accessline 227
- [ ] Both `https://www` and `https://` (and `http://` versions) verified as separate properties
skills/seo-traffic-diagnosis/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/skill-creation-walkthrough/README.md
- Network accessline 7
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-skill-creation-walkthrough): the same skill authoring tasks, with this skill loaded and without it, on each model below. - Network accessline 9
- **Tier:** Tier 1, the first tasks built for this job. - **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-09-26. - **Full results:** [openaddict.com/skills/rampstackco-skill-creation-walkthrough](https://openaddict.com/s - Network accessline 11
- **Full results:** [openaddict.com/skills/rampstackco-skill-creation-walkthrough](https://openaddict.com/skills/rampstackco-skill-creation-walkthrough)
skills/sprint-operations/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/stakeholder-communication/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/team-onboarding-playbook/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/ticket-authoring/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/upgrade-flow-design/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/usability-testing/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/user-feedback-aggregation/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/ux-research/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/vendor-evaluation/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
skills/vertical-site-conventions/README.md
- Network accessline 7
Set up for testing, not yet run. What has been searched and run so far: [openaddict.com/skills/coverage](https://openaddict.com/skills/coverage).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Only the first 0 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md dist/codex/.agents/skills/accessibility-audit/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md dist/codex/.agents/skills/accessibility-audit/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md dist/codex/.agents/skills/accessibility-audit/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md dist/codex/.agents/skills/accessibility-audit/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md dist/codex/.agents/skills/accessibility-audit/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/rampstackco-claude-skills/)