#582 by GitHub stars
NeoLabHQ/context-engineering-kit
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.
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
antigravity/skills/actualize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/add-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/agent-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/analyse/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/analyse-problem/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/analyze-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/apply-anthropic-skill-best-practices/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/attach-review-to-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/brainstorm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/build-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/cause-and-effect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/commit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/context-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-hook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-ideas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-rule/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/create-workflow-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/critique/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/decay/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/design-testing-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/do-and-judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/do-competitively/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/do-in-parallel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/do-in-steps/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/fix-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/git-notes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/git-worktrees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/implement-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/judge-with-debate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/kaizen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/launch-sub-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/load-issues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/load-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/memorize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/multi-agent-patterns/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/plan-do-check-act/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/plan-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/prompt-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/propose-hypotheses/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/query/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/reflect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/reset/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/resolve-fixed-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/review-local-changes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/review-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/root-cause-tracing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/setup-arxiv-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/setup-codemap-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/setup-context7-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/setup-serena-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/subagent-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/test-coverage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/test-prompt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/test-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/thought-based-reasoning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/traiage-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/tree-of-thoughts/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/update-docs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/why/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/write-concisely/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
antigravity/skills/write-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/agent-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/context-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-hook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-rule/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/create-workflow-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/prompt-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/test-prompt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/test-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/docs/skills/update-docs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/docs/skills/write-concisely/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/actualize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/decay/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/propose-hypotheses/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/query/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/reset/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/fpf/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/analyze-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/attach-review-to-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/commit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/create-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/git-notes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/git-worktrees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/load-issues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/load-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/git/skills/resolve-fixed-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/analyse/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/analyse-problem/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/cause-and-effect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/kaizen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/plan-do-check-act/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/root-cause-tracing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/kaizen/skills/why/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/mcp/skills/build-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/mcp/skills/setup-arxiv-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/mcp/skills/setup-codemap-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/mcp/skills/setup-context7-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/mcp/skills/setup-serena-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/reflexion/skills/critique/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/reflexion/skills/memorize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/reflexion/skills/reflect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/review/skills/review-local-changes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/review/skills/review-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/review/skills/traiage-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/do-and-judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/do-competitively/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/do-in-parallel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/do-in-steps/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/judge-with-debate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/launch-sub-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/multi-agent-patterns/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/subagent-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sadd/skills/tree-of-thoughts/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sdd/skills/add-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sdd/skills/brainstorm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sdd/skills/create-ideas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sdd/skills/implement-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/sdd/skills/plan-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/tdd/skills/design-testing-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/tdd/skills/fix-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/tdd/skills/test-coverage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/tdd/skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
plugins/tdd/skills/write-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/actualize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/add-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/agent-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/analyse/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/analyse-problem/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/analyze-issue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/apply-anthropic-skill-best-practices/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/attach-review-to-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/brainstorm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/build-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/cause-and-effect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/commit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/context-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-hook/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-ideas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-rule/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/create-workflow-command/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/critique/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/decay/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/design-testing-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/do-and-judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/do-competitively/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/do-in-parallel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/do-in-steps/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/fix-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/git-notes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/git-worktrees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/implement-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/judge-with-debate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/kaizen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/launch-sub-agent/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/load-issues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/load-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/memorize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/multi-agent-patterns/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/plan-do-check-act/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/plan-task/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/prompt-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/propose-hypotheses/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/query/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/reflect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/reset/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/resolve-fixed-pr-comments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/review-local-changes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/review-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/root-cause-tracing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/setup-arxiv-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/setup-codemap-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/setup-context7-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/setup-serena-mcp/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/subagent-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/test-coverage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/test-prompt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/test-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/thought-based-reasoning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/traiage-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/tree-of-thoughts/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/update-docs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/why/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/write-concisely/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
skills/write-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
23e2428e809d → 23e2428e809d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 23e2428e809d
No earlier version was observed for comparison.
Verified commit 23e2428e809d77717f8acc9659c374a3a1fcb93e
git clone --filter=blob:none --no-checkout https://github.com/NeoLabHQ/context-engineering-kit.git .hotskills/neolabhq-context-engineering-kit && git -C .hotskills/neolabhq-context-engineering-kit checkout --detach 23e2428e809d77717f8acc9659c374a3a1fcb93e
# Copy each selected skill directory from .hotskills/neolabhq-context-engineering-kit into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/NeoLabHQ/context-engineering-kit.git .hotskills/neolabhq-context-engineering-kit && git -C .hotskills/neolabhq-context-engineering-kit checkout --detach 23e2428e809d77717f8acc9659c374a3a1fcb93e
# Copy each selected skill directory from .hotskills/neolabhq-context-engineering-kit into .cursor/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/NeoLabHQ/context-engineering-kit.git .hotskills/neolabhq-context-engineering-kit && git -C .hotskills/neolabhq-context-engineering-kit checkout --detach 23e2428e809d77717f8acc9659c374a3a1fcb93e
# Copy each selected skill directory from .hotskills/neolabhq-context-engineering-kit into .gemini/skills/<skill-name>/Heat
4.9- Star growth, last 7 daysAhead of 76% of tracked repositories
- Star growth, last 24 hoursAhead of 90% of tracked repositories
- Rank movement, last 7 daysAhead of 20% of tracked repositories
- Commits, last 30 daysAhead of 0% 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
- actualize
antigravity/skills/actualize - add-task
antigravity/skills/add-task - agent-evaluation
antigravity/skills/agent-evaluation - analyse
antigravity/skills/analyse - analyse-problem
antigravity/skills/analyse-problem - analyze-issue
antigravity/skills/analyze-issue - apply-anthropic-skill-best-practices
antigravity/skills/apply-anthropic-skill-best-practices - attach-review-to-pr
antigravity/skills/attach-review-to-pr - brainstorm
antigravity/skills/brainstorm - build-mcp
antigravity/skills/build-mcp - cause-and-effect
antigravity/skills/cause-and-effect - commit
antigravity/skills/commit - context-engineering
antigravity/skills/context-engineering - create-agent
antigravity/skills/create-agent - create-command
antigravity/skills/create-command - create-hook
antigravity/skills/create-hook - create-ideas
antigravity/skills/create-ideas - create-pr
antigravity/skills/create-pr - create-rule
antigravity/skills/create-rule - create-skill
antigravity/skills/create-skill - create-workflow-command
antigravity/skills/create-workflow-command - critique
antigravity/skills/critique - decay
antigravity/skills/decay - design-testing-strategy
antigravity/skills/design-testing-strategy - do-and-judge
antigravity/skills/do-and-judge - do-competitively
antigravity/skills/do-competitively - do-in-parallel
antigravity/skills/do-in-parallel - do-in-steps
antigravity/skills/do-in-steps - fix-tests
antigravity/skills/fix-tests - git-notes
antigravity/skills/git-notes - git-worktrees
antigravity/skills/git-worktrees - implement-task
antigravity/skills/implement-task - judge
antigravity/skills/judge - judge-with-debate
antigravity/skills/judge-with-debate - kaizen
antigravity/skills/kaizen - launch-sub-agent
antigravity/skills/launch-sub-agent - load-issues
antigravity/skills/load-issues - load-pr-comments
antigravity/skills/load-pr-comments - memorize
antigravity/skills/memorize - multi-agent-patterns
antigravity/skills/multi-agent-patterns - plan-do-check-act
antigravity/skills/plan-do-check-act - plan-task
antigravity/skills/plan-task - prompt-engineering
antigravity/skills/prompt-engineering - propose-hypotheses
antigravity/skills/propose-hypotheses - query
antigravity/skills/query - reflect
antigravity/skills/reflect - reset
antigravity/skills/reset - resolve-fixed-pr-comments
antigravity/skills/resolve-fixed-pr-comments - review-local-changes
antigravity/skills/review-local-changes - review-pr
antigravity/skills/review-pr - root-cause-tracing
antigravity/skills/root-cause-tracing - setup-arxiv-mcp
antigravity/skills/setup-arxiv-mcp - setup-codemap-cli
antigravity/skills/setup-codemap-cli - setup-context7-mcp
antigravity/skills/setup-context7-mcp - setup-serena-mcp
antigravity/skills/setup-serena-mcp - status
antigravity/skills/status - subagent-driven-development
antigravity/skills/subagent-driven-development - test-coverage
antigravity/skills/test-coverage - test-driven-development
antigravity/skills/test-driven-development - test-prompt
antigravity/skills/test-prompt - test-skill
antigravity/skills/test-skill - thought-based-reasoning
antigravity/skills/thought-based-reasoning - traiage-review
antigravity/skills/traiage-review - tree-of-thoughts
antigravity/skills/tree-of-thoughts - update-docs
antigravity/skills/update-docs - why
antigravity/skills/why - write-concisely
antigravity/skills/write-concisely - write-tests
antigravity/skills/write-tests - agent-evaluation
plugins/customaize-agent/skills/agent-evaluation - apply-anthropic-skill-best-practices
plugins/customaize-agent/skills/apply-anthropic-skill-best-practices - context-engineering
plugins/customaize-agent/skills/context-engineering - create-agent
plugins/customaize-agent/skills/create-agent - create-command
plugins/customaize-agent/skills/create-command - create-hook
plugins/customaize-agent/skills/create-hook - create-rule
plugins/customaize-agent/skills/create-rule - create-skill
plugins/customaize-agent/skills/create-skill - create-workflow-command
plugins/customaize-agent/skills/create-workflow-command - prompt-engineering
plugins/customaize-agent/skills/prompt-engineering - test-prompt
plugins/customaize-agent/skills/test-prompt - test-skill
plugins/customaize-agent/skills/test-skill - thought-based-reasoning
plugins/customaize-agent/skills/thought-based-reasoning - update-docs
plugins/docs/skills/update-docs - write-concisely
plugins/docs/skills/write-concisely - actualize
plugins/fpf/skills/actualize - decay
plugins/fpf/skills/decay - propose-hypotheses
plugins/fpf/skills/propose-hypotheses - query
plugins/fpf/skills/query - reset
plugins/fpf/skills/reset - status
plugins/fpf/skills/status - analyze-issue
plugins/git/skills/analyze-issue - attach-review-to-pr
plugins/git/skills/attach-review-to-pr - commit
plugins/git/skills/commit - create-pr
plugins/git/skills/create-pr - git-notes
plugins/git/skills/git-notes - git-worktrees
plugins/git/skills/git-worktrees - load-issues
plugins/git/skills/load-issues - load-pr-comments
plugins/git/skills/load-pr-comments - resolve-fixed-pr-comments
plugins/git/skills/resolve-fixed-pr-comments - analyse
plugins/kaizen/skills/analyse - analyse-problem
plugins/kaizen/skills/analyse-problem - cause-and-effect
plugins/kaizen/skills/cause-and-effect - kaizen
plugins/kaizen/skills/kaizen - plan-do-check-act
plugins/kaizen/skills/plan-do-check-act - root-cause-tracing
plugins/kaizen/skills/root-cause-tracing - why
plugins/kaizen/skills/why - build-mcp
plugins/mcp/skills/build-mcp - setup-arxiv-mcp
plugins/mcp/skills/setup-arxiv-mcp - setup-codemap-cli
plugins/mcp/skills/setup-codemap-cli - setup-context7-mcp
plugins/mcp/skills/setup-context7-mcp - setup-serena-mcp
plugins/mcp/skills/setup-serena-mcp - critique
plugins/reflexion/skills/critique - memorize
plugins/reflexion/skills/memorize - reflect
plugins/reflexion/skills/reflect - review-local-changes
plugins/review/skills/review-local-changes - review-pr
plugins/review/skills/review-pr - traiage-review
plugins/review/skills/traiage-review - do-and-judge
plugins/sadd/skills/do-and-judge - do-competitively
plugins/sadd/skills/do-competitively - do-in-parallel
plugins/sadd/skills/do-in-parallel - do-in-steps
plugins/sadd/skills/do-in-steps - judge
plugins/sadd/skills/judge - judge-with-debate
plugins/sadd/skills/judge-with-debate - launch-sub-agent
plugins/sadd/skills/launch-sub-agent - multi-agent-patterns
plugins/sadd/skills/multi-agent-patterns - subagent-driven-development
plugins/sadd/skills/subagent-driven-development - tree-of-thoughts
plugins/sadd/skills/tree-of-thoughts - add-task
plugins/sdd/skills/add-task - brainstorm
plugins/sdd/skills/brainstorm - create-ideas
plugins/sdd/skills/create-ideas - implement-task
plugins/sdd/skills/implement-task - plan-task
plugins/sdd/skills/plan-task - design-testing-strategy
plugins/tdd/skills/design-testing-strategy - fix-tests
plugins/tdd/skills/fix-tests - test-coverage
plugins/tdd/skills/test-coverage - test-driven-development
plugins/tdd/skills/test-driven-development - write-tests
plugins/tdd/skills/write-tests - actualize
skills/actualize - add-task
skills/add-task - agent-evaluation
skills/agent-evaluation - analyse
skills/analyse - analyse-problem
skills/analyse-problem - analyze-issue
skills/analyze-issue - apply-anthropic-skill-best-practices
skills/apply-anthropic-skill-best-practices - attach-review-to-pr
skills/attach-review-to-pr - brainstorm
skills/brainstorm - build-mcp
skills/build-mcp - cause-and-effect
skills/cause-and-effect - commit
skills/commit - context-engineering
skills/context-engineering - create-agent
skills/create-agent - create-command
skills/create-command - create-hook
skills/create-hook - create-ideas
skills/create-ideas - create-pr
skills/create-pr - create-rule
skills/create-rule - create-skill
skills/create-skill - create-workflow-command
skills/create-workflow-command - critique
skills/critique - decay
skills/decay - design-testing-strategy
skills/design-testing-strategy - do-and-judge
skills/do-and-judge - do-competitively
skills/do-competitively - do-in-parallel
skills/do-in-parallel - do-in-steps
skills/do-in-steps - fix-tests
skills/fix-tests - git-notes
skills/git-notes - git-worktrees
skills/git-worktrees - implement-task
skills/implement-task - judge
skills/judge - judge-with-debate
skills/judge-with-debate - kaizen
skills/kaizen - launch-sub-agent
skills/launch-sub-agent - load-issues
skills/load-issues - load-pr-comments
skills/load-pr-comments - memorize
skills/memorize - multi-agent-patterns
skills/multi-agent-patterns - plan-do-check-act
skills/plan-do-check-act - plan-task
skills/plan-task - prompt-engineering
skills/prompt-engineering - propose-hypotheses
skills/propose-hypotheses - query
skills/query - reflect
skills/reflect - reset
skills/reset - resolve-fixed-pr-comments
skills/resolve-fixed-pr-comments - review-local-changes
skills/review-local-changes - review-pr
skills/review-pr - root-cause-tracing
skills/root-cause-tracing - setup-arxiv-mcp
skills/setup-arxiv-mcp - setup-codemap-cli
skills/setup-codemap-cli - setup-context7-mcp
skills/setup-context7-mcp - setup-serena-mcp
skills/setup-serena-mcp - status
skills/status - subagent-driven-development
skills/subagent-driven-development - test-coverage
skills/test-coverage - test-driven-development
skills/test-driven-development - test-prompt
skills/test-prompt - test-skill
skills/test-skill - thought-based-reasoning
skills/thought-based-reasoning - traiage-review
skills/traiage-review - tree-of-thoughts
skills/tree-of-thoughts - update-docs
skills/update-docs - why
skills/why - write-concisely
skills/write-concisely - write-tests
skills/write-tests
How it works
actualize
When your agent uses it
Reconcile the project's FPF state with recent repository changes
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
944 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- File: .fpf/.baseline
- When to Run
Scripts executed separately
../../../plugins/reflexion/hooks/src/index.ts
Files
../../../.claude-plugin/marketplace.jsonasset5,881 bytesSKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytes../../../plugins/customaize-agent/.claude-plugin/plugin.jsonasset365 bytes../../../plugins/ddd/.claude-plugin/plugin.jsonasset348 bytes../../../plugins/docs/.claude-plugin/plugin.jsonasset225 bytes../../../plugins/fpf/.claude-plugin/plugin.jsonasset522 bytes../../../plugins/git/.claude-plugin/plugin.jsonasset246 bytes../../../plugins/kaizen/.claude-plugin/plugin.jsonasset391 bytes../../../plugins/mcp/.claude-plugin/plugin.jsonasset306 bytes../../../plugins/reflexion/.claude-plugin/plugin.jsonasset399 bytes../../../plugins/reflexion/hooks/hooks.jsonasset745 bytes../../../plugins/reflexion/hooks/src/index.tsruns4,740 bytes../../../plugins/review/.claude-plugin/plugin.jsonasset247 bytes../../../plugins/sadd/.claude-plugin/plugin.jsonasset324 bytes../../../plugins/sdd/.claude-plugin/plugin.jsonasset335 bytes../../../plugins/tdd/.claude-plugin/plugin.jsonasset266 bytes../../../plugins/tech-stack/.claude-plugin/plugin.jsonasset266 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubadd-task
When your agent uses it
creates draft task file in .specs/tasks/draft/ with original user intent
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,503 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- Input
- Instructions
- Constraints
- Expected Output
- Success Criteria
- Examples
Files
SKILL.mdcore6,006 bytesSKILL.mdcore6,006 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubagent-evaluation
When your agent uses it
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
12,599 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Evaluation Challenges
- Evaluation Rubric Design
- Evaluation Methodologies
- Test Set Design
- Context Engineering Evaluation
- Advanced Evaluation: LLM-as-Judge
- Evaluation Metrics Reference
- Evaluation Approaches
- Rubric Generation
- Practical Guidance
- Examples
- Guidelines
- Example: Evaluating a Claude Code Command
- Position Bias
- Length Bias
- Self-Enhancement Bias
- Verbosity Bias
- Authority Bias
- Aggregate Bias Detection
- Summary Table
- Pattern 1: Structured Evaluation Workflow
- Pattern 2: Hierarchical Evaluation Workflow
- Pattern 3: Panel of LLM Judges (PoLL)
- Pattern 4: Confidence Calibration
- Pattern 5: Structured Output Format
- Evaluation Workflows for Claude Code Development
- Anti-Patterns to Avoid
- Handling Evaluation Failures
- Validating Evaluation Prompts (Meta-Evaluation)
- Metric Categories
- Selection Decision Tree
- Metric Selection by Use Case
- Interpreting Metric Results
- Reporting Template
Files
SKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse
When your agent uses it
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
3,664 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Method Selection Logic
- Steps
- Method 1: Gemba Walk
- Method 2: Value Stream Mapping
- Method 3: Muda (Waste Analysis)
- Notes
Files
SKILL.mdcore15,105 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse-problem
When your agent uses it
Comprehensive A3 one-page problem analysis with root cause and action plan
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
3,906 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- A3 Template
- Examples
- Notes
Files
SKILL.mdcore31,282 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyze-issue
When your agent uses it
Analyze a GitHub issue and create a detailed technical specification
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
554 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Issue Summary
- Problem Statement
- Technical Approach
- Implementation Plan
- Test Plan
- Files to Modify
- Files to Create
- Existing Utilities to Leverage
- Success Criteria
- Out of Scope
Files
SKILL.mdcore2,229 bytesSKILL.mdcore2,229 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubapply-anthropic-skill-best-practices
When your agent uses it
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
10,120 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core principles
- Skill structure
- Workflows and feedback loops
- Content guidelines
- Common patterns
- Evaluation and iteration
- Anti-patterns to avoid
- Advanced: Skills with executable code
- Technical notes
- Checklist for effective Skills
Files
SKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubattach-review-to-pr
When your agent uses it
Add line-specific review comments to pull requests using GitHub CLI API
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
3,831 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preferred Approach: Using MCP GitHub Tools
- Overview
- Prerequisites
- Understanding GitHub's Review Comment System
- Adding a Single Line-Specific Comment
- Adding Multiple Line-Specific Comments Together
- Common Issues and Solutions
- Best Practices
- Workflow Examples
- Helpful Helper Scripts
- Related Documentation
- API Reference
Files
SKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbrainstorm
When your agent uses it
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
607 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Process
- After the Design
- Key Principles
Files
SKILL.mdcore2,996 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbuild-mcp
When your agent uses it
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
2,857 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- 🚀 High-Level Workflow
- 📚 Documentation Library
Files
SKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcause-and-effect
When your agent uses it
Systematic Fishbone analysis exploring problem causes across six categories
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,464 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore6,747 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcommit
When your agent uses it
Create well-formatted commits with conventional commit messages and emoji
What it loads into context
Frontmatter
17 tokensAlways available to the agent
SKILL.md
2,232 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Best Practices for Commits
- Guidelines for Splitting Commits
- Examples
- Command Options
- Branch Naming Convention
- Important Notes
Files
SKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcontext-engineering
When your agent uses it
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
10,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Hallucination Detection Workflow
- Lost-in-Middle Detection Workflow
- Error Propagation Analysis Workflow
- Context Relevance Scoring Workflow
- Context Health Monitoring Workflow
- Guidelines for Multi-Agent Verification
- Core Concepts
- Detailed Topics
- Practical Guidance
- Guidelines
Files
SKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-agent
When your agent uses it
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
4,537 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- What Are Agents?
- Agent File Structure
- Frontmatter Fields Reference
- Triggering Patterns
- System Prompt Design
- AI-Assisted Agent Generation
- Default Agent Standards
- Validation Rules
- Production Examples
- Agent Creation Process
- Best Practices Summary
- Integration with Workflows
- Create the Agent
Files
SKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-command
When your agent uses it
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
3,493 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Every Command Must Start with Frontmatter
- Slash Command Features
- Before Creating: Study Similar Commands
- Phase 1: Understanding Purpose
- Phase 2: Category Classification
- Phase 3: Pattern Selection
- Phase 4: Command Location
- Phase 5: Resource Planning
- Critical: Copy Patterns from Similar Commands
Files
SKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-hook
When your agent uses it
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
24,116 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Task (/create-hook)
- Your Workflow
- Hook Templates
- Quick Reference
- Success Criteria
- Set up your first hook
- What you can automate
- How hooks work
- Prompt-based hooks
- Agent-based hooks
- Limitations and troubleshooting
- Learn more
- Hook lifecycle
- Configuration
- Hook input and output
- Hook events
- Prompt-based hooks
- Agent-based hooks
- Run hooks in the background
- Security considerations
- Debug hooks
Files
SKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-ideas
When your agent uses it
Generate ideas in one shot using creative sampling
What it loads into context
Frontmatter
16 tokensAlways available to the agent
SKILL.md
147 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore721 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-pr
When your agent uses it
Create pull requests using GitHub CLI with proper templates and formatting
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,043 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Pre-flight Checks
- Creating a New Pull Request
- Best Practices
- Additional GitHub CLI PR Commands
- Using Templates for PR Creation
- Related Documentation
Files
SKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-rule
When your agent uses it
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
4,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Rules
- When to Create a Rule
- Rule Types
- Rule Structure: The Contrastive Pattern
- Writing Effective Rules
- Directory Structure
- Rule Creation Process
- Complete Rule Example
- Complete Path-Scoped Rule Example
- Anti-Patterns
- Rule Creation Checklist
- The Bottom Line
- Claude Code Official Rules Guidlines
Files
SKILL.mdcore21,996 bytesSKILL.mdcore21,996 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-skill
When your agent uses it
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
6,691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Skills
- What is a Skill?
- TDD Mapping for Skills
- When to Create a Skill
- Skill Types
- Directory Structure
- Anatomy of a Skill
- SKILL.md (required)
- Claude Search Optimization (CSO)
- Flowchart Usage
- Code Examples
- File Organization
- The Iron Law (Same as TDD)
- Testing All Skill Types
- Bulletproofing Skills Against Rationalization
- RED-GREEN-REFACTOR for Skills
- Anti-Patterns
- STOP: Before Moving to Next Skill
- Skill Creation Checklist (TDD Adapted)
- Discovery Workflow
- The Bottom Line
- Skill Creation Process
Files
SKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-workflow-command
When your agent uses it
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
2,734 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Architecture Overview
- Key Principles
- Implementation Process
- Execution Patterns
- Example: Feature Implementation Workflow
- Known Limitations
- Validation Checklist
- Create the Workflow
Files
SKILL.mdcore11,347 bytesSKILL.mdcore11,347 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcritique
When your agent uses it
Comprehensive multi-perspective review using specialized judges with debate and consensus building
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
2,926 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Important Guidelines
- Usage Examples
- Notes
Files
SKILL.mdcore12,895 bytesSKILL.mdcore12,895 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdecay
When your agent uses it
Manage evidence freshness by identifying stale decisions and providing governance actions
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,556 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Concepts
- Action (Run-Time)
- Natural Language Usage
- WLNK Principle
- Audit Trail
- Common Workflows
Files
SKILL.mdcore5,946 bytesSKILL.mdcore5,946 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdesign-testing-strategy
When your agent uses it
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
11,321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How To Use This Skill
- Decision Gates
- Test Type Reference
- Case Design Techniques
- Dependency Decision
- Strategic Skip Heuristics
- Test Matrix Schema
- Case Listing Schema
- Sources & Further Reading
- Worked Examples
- Skill Self-Check
- Coverage Analysis
Files
SKILL.mdcore45,601 bytesSKILL.mdcore45,601 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-and-judge
When your agent uses it
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
12,591 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Task
- Arguments
- Context
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
Files
SKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-competitively
When your agent uses it
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
6,512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Generate-Critique-Synthesize (GCS)
- Process
- Output
- Instructions
- Output
- Best Practices
- Examples
Files
SKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-parallel
When your agent uses it
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
25,908 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Implementation Outputs
- Instructions
- Output
- Examples
- Best Practices
Files
SKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-steps
When your agent uses it
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
16,948 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
- Context Format Reference
Files
SKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfix-tests
When your agent uses it
Systematically fix all failing tests after business logic changes or refactoring
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
807 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Template
Files
SKILL.mdcore3,662 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-notes
When your agent uses it
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,493 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Patterns
- Common Mistakes
- Best Practices
- Basic Operations
- Using Multiple Namespaces
- Merging Notes
- Configuration Options
- Workflow Examples
Files
SKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-worktrees
When your agent uses it
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
10,084 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Commands
- Workflow Patterns
- Comparing and Merging Changes Between Worktrees
- Directory Structure Conventions
- Best Practices
- Common Issues and Solutions
- Common Mistakes
- Agent Workflow Integration
- Verification Checklist
- Instructions
- Comparison Modes
- Worktree Detection
- Examples
- Output Format
- Common Workflows
- Important Notes
- Integration with Create Worktree
- Troubleshooting
- Instructions
- Worktree Path Convention
- Examples
- Setup Detection Examples
- Common Workflows
- Important Notes
- Cleanup
- Troubleshooting
- Instructions
- Merge Strategies Reference
- Examples
- Interactive Patch Mode Guide
- Cherry-Pick Selective Workflow
- Multi-Worktree Merge Workflow
- Common Workflows
- Important Notes
- Cleanup After Merge
- Troubleshooting
- Integration with Other Commands
Files
SKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimplement-task
When your agent uses it
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
19,553 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Vocabulary (read this first — two different things are called "phase")
- Command Arguments
- Task Selection and Status Management
- CRITICAL: You Are an ORCHESTRATOR ONLY
- CRITICAL
- Overview
- Complete Workflow Overview
- Workflow Phase 0: Parse User Input and Select Task
- Workflow Phase 1: Load and Analyze Task
- Workflow Phase 2: Execute Implementation Phases
- ⚠<U+FE0F> CHECKPOINT: Before Proceeding to Definition-of-Done Verification
- Workflow Phase 3: Definition of Done Verification
- Workflow Phase 4: Move Task to Done
- Workflow Phase 5: Aggregation and Reporting
- Execution Flow Diagram
- Usage Examples
- Error Handling
- Checklist
- Appendix A: What the Task File and Sub-Task Files Provide
Files
SKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge
When your agent uses it
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
1,721 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Instructions
Files
SKILL.mdcore8,119 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge-with-debate
When your agent uses it
Evaluate solutions through multi-round debate between independent judges until consensus
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
3,889 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Debate-Based Evaluation
- Process
- Output File
- Instructions
- Output File
- Instructions
- Best Practices
- Example Usage
Files
SKILL.mdcore17,167 bytesSKILL.mdcore17,167 bytesSKILL.mdcore17,167 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubkaizen
When your agent uses it
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
4,185 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Four Pillars
- Integration with Commands
- Red Flags
- Remember
Files
SKILL.mdcore17,876 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublaunch-sub-agent
When your agent uses it
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
2,657 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Process
- Examples
- Best Practices
Files
SKILL.mdcore11,928 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-issues
When your agent uses it
Load all open issues from GitHub and save them as markdown files
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
366 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,474 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-pr-comments
When your agent uses it
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,999 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Group and Rewrite as Tasks
- Step 4: .gitignore Handling
- Step 5: Write Files
- Step 6: Report
- Edge Cases
Files
SKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmemorize
When your agent uses it
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
2,391 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Memory Consolidation Workflow
- Usage
- Output
- Notes
Files
SKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulti-agent-patterns
When your agent uses it
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,195 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Why Multi-Agent Architectures
- Architectural Patterns
- Context Isolation as Design Principle
- Consensus and Coordination
- Failure Modes and Mitigations
- Applying Patterns in Claude Code
- Guidelines
- Memory and State Management
- Core Concepts
- Detailed Topics
Files
SKILL.mdcore23,989 bytesSKILL.mdcore23,989 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-do-check-act
When your agent uses it
Iterative PDCA cycle for systematic experimentation and continuous improvement
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore7,516 bytesSKILL.mdcore7,516 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-task
When your agent uses it
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
16,845 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- User Input
- Command Arguments
- Usage Examples
- Pre-Flight Checks
- CRITICAL
- Model Selection Policy
- Workflow Execution
- Phase 2: Parallel Analysis
- Phase 3: Architecture Synthesis
- Phase 4: Decomposition
- Promote Task
- Completion
- Error Handling
Files
SKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubprompt-engineering
When your agent uses it
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
3,611 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Key Patterns
- Best Practices
- Common Pitfalls
- Integration Patterns
- Performance Optimization
- Core principles
- Overview
- The Seven Principles
- Principle Combinations by Prompt Type
- Why This Works: The Psychology
- Ethical Use
- Quick Reference
Files
SKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpropose-hypotheses
When your agent uses it
Execute complete FPF cycle from hypothesis generation to decision
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,650 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Workflow Execution
- Completion
Files
SKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubquery
When your agent uses it
Search the FPF knowledge base and display hypothesis details with assurance information
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
1,038 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Search Locations
- Output Format
- Search Methods
- R_eff Display
- Dependency Tree Display
- Examples
Files
SKILL.mdcore3,469 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreflect
When your agent uses it
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
5,057 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity (NON-NEGOTIABLE)
- TASK COMPLEXITY TRIAGE
- IMMEDIATE REFLECTION PROTOCOL
- CODE-SPECIFIC REFLECTION CRITERIA
- FACT-CHECKING AND CLAIM VERIFICATION
- NON-CODE OUTPUT REFLECTION
- Report Format
- ITERATIVE REFINEMENT WORKFLOW
- REFINEMENT TRIGGERS
- FINAL VERIFICATION
- IMPROVEMENT DIRECTIVE
- CONFIDENCE ASSESSMENT
- REFINEMENT METRICS
Files
SKILL.mdcore22,391 bytesSKILL.mdcore22,391 bytesSKILL.mdcore22,391 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreset
When your agent uses it
Reset the FPF reasoning cycle to start fresh
What it loads into context
Frontmatter
17 tokensAlways available to the agent
SKILL.md
737 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
Files
SKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresolve-fixed-pr-comments
When your agent uses it
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,991 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Red Flags - STOP and Leave Unresolved
- How to Use
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Verify Each Thread Against the CURRENT Codebase
- Step 4: Resolve the Genuinely-Fixed Threads
- Step 5: Report
- Examples
- Troubleshooting / Common Issues
Files
SKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-local-changes
When your agent uses it
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
4,173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
- Improvements
- Evaluation Guidelines
- Remember
Files
SKILL.mdcore18,539 bytesSKILL.mdcore18,539 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-pr
When your agent uses it
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
3,446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
Files
SKILL.mdcore15,176 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubroot-cause-tracing
When your agent uses it
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
1,367 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Tracing Process
- Adding Stack Traces
- Finding Which Test Causes Pollution
- Real Example: Empty projectDir
- Key Principle
- Stack Trace Tips
- Real-World Impact
Files
SKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-arxiv-mcp
When your agent uses it
Guide for setup arXiv paper search MCP server using Docker MCP
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,044 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Docker MCP is available
- 3. Search and add paper-search MCP server
- 4. Test the setup
- 5. Update CLAUDE.md file
- 6. Alternative: arxiv-mcp-server
Files
SKILL.mdcore4,116 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-codemap-cli
When your agent uses it
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,575 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Codemap is already installed
- 3. Load Codemap documentation
- 4. Guide user through installation
- 5. Verify installation
- 6. Update CLAUDE.md file
- 8. Test Codemap
- 9. Add hooks to settings file
Files
SKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-context7-mcp
When your agent uses it
Guide for setup Context7 MCP server to load documentation for specific technologies.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
409 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Context7 MCP server is already setup
- 3. Update CLAUDE.md file
Files
SKILL.mdcore1,804 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-serena-mcp
When your agent uses it
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,102 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Serena MCP server is already setup
- 3. Load Serena documentation
- 4. Guide user through setup process
- 5. Update CLAUDE.md file
- 6. Project initialization (if needed)
Files
SKILL.mdcore4,713 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubstatus
When your agent uses it
Display the current state of the FPF knowledge base
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Status Report Format
- Phase Detection Logic
- Evidence Freshness Check
- Example Output
Files
SKILL.mdcore2,938 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsubagent-driven-development
When your agent uses it
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,476 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Supported types of execution
- Sequential Execution Process
- Parallel Execution Process
- Parallel Investigation Process
Files
SKILL.mdcore11,059 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-coverage
When your agent uses it
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
12,159 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Coverage Analysis Is
- Per-Type Structure
- Structural / Code Coverage
- Mutation Testing as Coverage Analysis
- Requirements / Feature Coverage
- API / Integration Coverage
- Additional Coverage Types
- Cross-Cutting Topics
- Decision Reference Tables
- Sources & Further Reading
Files
SKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-driven-development
When your agent uses it
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
4,271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Iron Law
- Red-Green-Refactor
- Good Tests
- Why Order Matters
- Common Rationalizations
- Red Flags - STOP and Start Over
- Example: Bug Fix
- Verification Checklist
- When Stuck
- Debugging Integration
- Final Rule
- Overview
- The Iron Laws
- Anti-Pattern 1: Testing Mock Behavior
- Anti-Pattern 2: Test-Only Methods in Production
- Anti-Pattern 3: Mocking Without Understanding
- Anti-Pattern 4: Incomplete Mocks
- Anti-Pattern 5: Integration Tests as Afterthought
- When Mocks Become Too Complex
- TDD Prevents These Anti-Patterns
- Quick Reference
- Red Flags
- The Bottom Line
Files
SKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-prompt
When your agent uses it
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,396 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Prompt Types & Testing Strategies
- TDD Mapping for Prompt Testing
- Why Use Subagents for Testing?
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Prompt (Make It Pass)
- REFACTOR Phase: Optimize Prompt (Stay Green)
- Subagent Testing Patterns
- Testing Checklist (TDD for Prompts)
- Common Mistakes (Same as Code TDD)
- Example: Testing a Command
- Quick Reference
- Integration with Prompt Engineering
- The Bottom Line
Files
SKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-skill
When your agent uses it
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,911 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- TDD Mapping for Skill Testing
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Skill (Make It Pass)
- VERIFY GREEN: Pressure Testing
- REFACTOR Phase: Close Loopholes (Stay Green)
- Meta-Testing (When GREEN Isn't Working)
- When Skill is Bulletproof
- Example: TDD Skill Bulletproofing
- Testing Checklist (TDD for Skills)
- Common Mistakes (Same as TDD)
- Quick Reference (TDD Cycle)
- The Bottom Line
- Real-World Impact
Files
SKILL.mdcore12,796 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubthought-based-reasoning
When your agent uses it
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
5,353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Reference
- Core Techniques
- Decision Matrix: Which Technique to Use
- Best Practices
- Common Mistakes
- References
Files
SKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtraiage-review
When your agent uses it
This skill should be used when need prioritize what changed code in repository human must review.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
2,264 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Rules
- Process
- Agents
- Random Sample Script
- Output Format
Files
SKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtree-of-thoughts
When your agent uses it
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
7,899 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Tree of Thoughts (ToT)
- Process
- Output
- Instructions
- Output
- Instructions
- Best Practices
- Example: API Design
Files
SKILL.mdcore34,989 bytesSKILL.mdcore34,989 bytesSKILL.mdcore34,989 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubupdate-docs
When your agent uses it
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,900 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
- Core Documentation Philosophy
- Documentation Discovery Process
- Smart Documentation Strategy
- Documentation Audit Guidelines
- Documentation Patterns Reference
- Quality Gates
- Documentation Update Summary Template
Files
SKILL.mdcore22,741 bytesSKILL.mdcore22,741 bytesSKILL.mdcore22,741 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwhy
When your agent uses it
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
745 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore3,284 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-concisely
When your agent uses it
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
16,199 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- All Rules
- Contents
- I. Introductory
- II. Elementary Rules Of Usage
- III. Elementary Principles Of Composition
- V. Words And Expressions Commonly Misused
Files
SKILL.mdcore72,863 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-tests
When your agent uses it
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,773 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
Files
SKILL.mdcore8,039 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubagent-evaluation
When your agent uses it
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
12,599 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Evaluation Challenges
- Evaluation Rubric Design
- Evaluation Methodologies
- Test Set Design
- Context Engineering Evaluation
- Advanced Evaluation: LLM-as-Judge
- Evaluation Metrics Reference
- Evaluation Approaches
- Rubric Generation
- Practical Guidance
- Examples
- Guidelines
- Example: Evaluating a Claude Code Command
- Position Bias
- Length Bias
- Self-Enhancement Bias
- Verbosity Bias
- Authority Bias
- Aggregate Bias Detection
- Summary Table
- Pattern 1: Structured Evaluation Workflow
- Pattern 2: Hierarchical Evaluation Workflow
- Pattern 3: Panel of LLM Judges (PoLL)
- Pattern 4: Confidence Calibration
- Pattern 5: Structured Output Format
- Evaluation Workflows for Claude Code Development
- Anti-Patterns to Avoid
- Handling Evaluation Failures
- Validating Evaluation Prompts (Meta-Evaluation)
- Metric Categories
- Selection Decision Tree
- Metric Selection by Use Case
- Interpreting Metric Results
- Reporting Template
Files
SKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubapply-anthropic-skill-best-practices
When your agent uses it
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
10,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core principles
- Skill structure
- Workflows and feedback loops
- Content guidelines
- Common patterns
- Evaluation and iteration
- Anti-patterns to avoid
- Advanced: Skills with executable code
- Technical notes
- Checklist for effective Skills
Files
SKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytesSKILL.mdcore42,366 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcontext-engineering
When your agent uses it
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
10,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Hallucination Detection Workflow
- Lost-in-Middle Detection Workflow
- Error Propagation Analysis Workflow
- Context Relevance Scoring Workflow
- Context Health Monitoring Workflow
- Guidelines for Multi-Agent Verification
- Core Concepts
- Detailed Topics
- Practical Guidance
- Guidelines
Files
SKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-agent
When your agent uses it
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
4,571 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- What Are Agents?
- Agent File Structure
- Frontmatter Fields Reference
- Triggering Patterns
- System Prompt Design
- AI-Assisted Agent Generation
- Default Agent Standards
- Validation Rules
- Production Examples
- Agent Creation Process
- Best Practices Summary
- Integration with Workflows
- Create the Agent
Files
SKILL.mdcore20,241 bytesSKILL.mdcore20,241 bytesSKILL.mdcore20,241 bytesSKILL.mdcore20,241 bytesSKILL.mdcore20,241 bytesSKILL.mdcore20,241 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-command
When your agent uses it
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
3,506 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Every Command Must Start with Frontmatter
- Slash Command Features
- Before Creating: Study Similar Commands
- Phase 1: Understanding Purpose
- Phase 2: Category Classification
- Phase 3: Pattern Selection
- Phase 4: Command Location
- Phase 5: Resource Planning
- Critical: Copy Patterns from Similar Commands
Files
SKILL.mdcore15,019 bytesSKILL.mdcore15,019 bytesSKILL.mdcore15,019 bytesSKILL.mdcore15,019 bytesSKILL.mdcore15,019 bytesSKILL.mdcore15,019 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-hook
When your agent uses it
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
24,129 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Task (/create-hook)
- Your Workflow
- Hook Templates
- Quick Reference
- Success Criteria
- Set up your first hook
- What you can automate
- How hooks work
- Prompt-based hooks
- Agent-based hooks
- Limitations and troubleshooting
- Learn more
- Hook lifecycle
- Configuration
- Hook input and output
- Hook events
- Prompt-based hooks
- Agent-based hooks
- Run hooks in the background
- Security considerations
- Debug hooks
Files
SKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytesSKILL.mdcore110,475 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-rule
When your agent uses it
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
4,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Rules
- When to Create a Rule
- Rule Types
- Rule Structure: The Contrastive Pattern
- Writing Effective Rules
- Directory Structure
- Rule Creation Process
- Complete Rule Example
- Complete Path-Scoped Rule Example
- Anti-Patterns
- Rule Creation Checklist
- The Bottom Line
- Claude Code Official Rules Guidlines
Files
SKILL.mdcore21,996 bytesSKILL.mdcore21,996 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-skill
When your agent uses it
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
6,691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Skills
- What is a Skill?
- TDD Mapping for Skills
- When to Create a Skill
- Skill Types
- Directory Structure
- Anatomy of a Skill
- SKILL.md (required)
- Claude Search Optimization (CSO)
- Flowchart Usage
- Code Examples
- File Organization
- The Iron Law (Same as TDD)
- Testing All Skill Types
- Bulletproofing Skills Against Rationalization
- RED-GREEN-REFACTOR for Skills
- Anti-Patterns
- STOP: Before Moving to Next Skill
- Skill Creation Checklist (TDD Adapted)
- Discovery Workflow
- The Bottom Line
- Skill Creation Process
Files
SKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-workflow-command
When your agent uses it
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
2,762 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Architecture Overview
- Key Principles
- Implementation Process
- Execution Patterns
- Example: Feature Implementation Workflow
- Known Limitations
- Validation Checklist
- Create the Workflow
Files
SKILL.mdcore11,448 bytesSKILL.mdcore11,448 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubprompt-engineering
When your agent uses it
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
3,611 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Key Patterns
- Best Practices
- Common Pitfalls
- Integration Patterns
- Performance Optimization
- Core principles
- Overview
- The Seven Principles
- Principle Combinations by Prompt Type
- Why This Works: The Psychology
- Ethical Use
- Quick Reference
Files
SKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-prompt
When your agent uses it
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,396 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Prompt Types & Testing Strategies
- TDD Mapping for Prompt Testing
- Why Use Subagents for Testing?
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Prompt (Make It Pass)
- REFACTOR Phase: Optimize Prompt (Stay Green)
- Subagent Testing Patterns
- Testing Checklist (TDD for Prompts)
- Common Mistakes (Same as Code TDD)
- Example: Testing a Command
- Quick Reference
- Integration with Prompt Engineering
- The Bottom Line
Files
SKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-skill
When your agent uses it
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,911 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- TDD Mapping for Skill Testing
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Skill (Make It Pass)
- VERIFY GREEN: Pressure Testing
- REFACTOR Phase: Close Loopholes (Stay Green)
- Meta-Testing (When GREEN Isn't Working)
- When Skill is Bulletproof
- Example: TDD Skill Bulletproofing
- Testing Checklist (TDD for Skills)
- Common Mistakes (Same as TDD)
- Quick Reference (TDD Cycle)
- The Bottom Line
- Real-World Impact
Files
SKILL.mdcore12,796 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubthought-based-reasoning
When your agent uses it
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
5,353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Reference
- Core Techniques
- Decision Matrix: Which Technique to Use
- Best Practices
- Common Mistakes
- References
Files
SKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubupdate-docs
When your agent uses it
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
4,926 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
- Core Documentation Philosophy
- Documentation Discovery Process
- Smart Documentation Strategy
- Documentation Audit Guidelines
- Documentation Patterns Reference
- Quality Gates
- Documentation Update Summary Template
Files
SKILL.mdcore22,855 bytesSKILL.mdcore22,855 bytesSKILL.mdcore22,855 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-concisely
When your agent uses it
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
16,199 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- All Rules
- Contents
- I. Introductory
- II. Elementary Rules Of Usage
- III. Elementary Principles Of Composition
- V. Words And Expressions Commonly Misused
Files
SKILL.mdcore72,863 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubactualize
When your agent uses it
Reconcile the project's FPF state with recent repository changes
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
944 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- File: .fpf/.baseline
- When to Run
Files
SKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdecay
When your agent uses it
Manage evidence freshness by identifying stale decisions and providing governance actions
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,556 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Concepts
- Action (Run-Time)
- Natural Language Usage
- WLNK Principle
- Audit Trail
- Common Workflows
Files
SKILL.mdcore5,946 bytesSKILL.mdcore5,946 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpropose-hypotheses
When your agent uses it
Execute complete FPF cycle from hypothesis generation to decision
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,674 tokensWhen the skill is activated
Reference documents
12,179 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Workflow Execution
- Completion
Files
SKILL.mdcore6,040 bytesSKILL.mdcore6,040 bytes../../tasks/add-user-hypothesis.mddoc6,013 bytes../../tasks/audit-trust.mddoc7,303 bytes../../tasks/decide.mddoc7,937 bytes../../tasks/generate-hypotheses.mddoc7,438 bytes../../tasks/init-context.mddoc6,990 bytes../../tasks/validate-evidence.mddoc7,285 bytes../../tasks/verify-logic.mddoc6,837 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubquery
When your agent uses it
Search the FPF knowledge base and display hypothesis details with assurance information
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
1,038 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Search Locations
- Output Format
- Search Methods
- R_eff Display
- Dependency Tree Display
- Examples
Files
SKILL.mdcore3,469 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreset
When your agent uses it
Reset the FPF reasoning cycle to start fresh
What it loads into context
Frontmatter
17 tokensAlways available to the agent
SKILL.md
737 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
Files
SKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubstatus
When your agent uses it
Display the current state of the FPF knowledge base
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Status Report Format
- Phase Detection Logic
- Evidence Freshness Check
- Example Output
Files
SKILL.mdcore2,938 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyze-issue
When your agent uses it
Analyze a GitHub issue and create a detailed technical specification
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
585 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Issue Summary
- Problem Statement
- Technical Approach
- Implementation Plan
- Test Plan
- Files to Modify
- Files to Create
- Existing Utilities to Leverage
- Success Criteria
- Out of Scope
Files
SKILL.mdcore2,325 bytesSKILL.mdcore2,325 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubattach-review-to-pr
When your agent uses it
Add line-specific review comments to pull requests using GitHub CLI API
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
3,880 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preferred Approach: Using MCP GitHub Tools
- Overview
- Prerequisites
- Understanding GitHub's Review Comment System
- Adding a Single Line-Specific Comment
- Adding Multiple Line-Specific Comments Together
- Common Issues and Solutions
- Best Practices
- Workflow Examples
- Helpful Helper Scripts
- Related Documentation
- API Reference
Files
SKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytesSKILL.mdcore14,617 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcommit
When your agent uses it
Create well-formatted commits with conventional commit messages and emoji
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,325 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Best Practices for Commits
- Guidelines for Splitting Commits
- Examples
- Command Options
- Branch Naming Convention
- Important Notes
Files
SKILL.mdcore9,203 bytesSKILL.mdcore9,203 bytesSKILL.mdcore9,203 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-pr
When your agent uses it
Create pull requests using GitHub CLI with proper templates and formatting
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,095 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Pre-flight Checks
- Creating a New Pull Request
- Best Practices
- Additional GitHub CLI PR Commands
- Using Templates for PR Creation
- Related Documentation
Files
SKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytesSKILL.mdcore4,528 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-notes
When your agent uses it
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,493 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Patterns
- Common Mistakes
- Best Practices
- Basic Operations
- Using Multiple Namespaces
- Merging Notes
- Configuration Options
- Workflow Examples
Files
SKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-worktrees
When your agent uses it
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
10,084 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Commands
- Workflow Patterns
- Comparing and Merging Changes Between Worktrees
- Directory Structure Conventions
- Best Practices
- Common Issues and Solutions
- Common Mistakes
- Agent Workflow Integration
- Verification Checklist
- Instructions
- Comparison Modes
- Worktree Detection
- Examples
- Output Format
- Common Workflows
- Important Notes
- Integration with Create Worktree
- Troubleshooting
- Instructions
- Worktree Path Convention
- Examples
- Setup Detection Examples
- Common Workflows
- Important Notes
- Cleanup
- Troubleshooting
- Instructions
- Merge Strategies Reference
- Examples
- Interactive Patch Mode Guide
- Cherry-Pick Selective Workflow
- Multi-Worktree Merge Workflow
- Common Workflows
- Important Notes
- Cleanup After Merge
- Troubleshooting
- Integration with Other Commands
Files
SKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-issues
When your agent uses it
Load all open issues from GitHub and save them as markdown files
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
395 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,595 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-pr-comments
When your agent uses it
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
2,019 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Group and Rewrite as Tasks
- Step 4: .gitignore Handling
- Step 5: Write Files
- Step 6: Report
- Edge Cases
Files
SKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytesSKILL.mdcore8,389 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresolve-fixed-pr-comments
When your agent uses it
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,991 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Red Flags - STOP and Leave Unresolved
- How to Use
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Verify Each Thread Against the CURRENT Codebase
- Step 4: Resolve the Genuinely-Fixed Threads
- Step 5: Report
- Examples
- Troubleshooting / Common Issues
Files
SKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse
When your agent uses it
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
3,683 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Method Selection Logic
- Steps
- Method 1: Gemba Walk
- Method 2: Value Stream Mapping
- Method 3: Muda (Waste Analysis)
- Notes
Files
SKILL.mdcore15,190 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse-problem
When your agent uses it
Comprehensive A3 one-page problem analysis with root cause and action plan
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
3,916 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- A3 Template
- Examples
- Notes
Files
SKILL.mdcore31,338 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcause-and-effect
When your agent uses it
Systematic Fishbone analysis exploring problem causes across six categories
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
1,474 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore6,802 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubkaizen
When your agent uses it
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
4,185 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Four Pillars
- Integration with Commands
- Red Flags
- Remember
Files
SKILL.mdcore17,876 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-do-check-act
When your agent uses it
Iterative PDCA cycle for systematic experimentation and continuous improvement
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
1,872 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore7,579 bytesSKILL.mdcore7,579 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubroot-cause-tracing
When your agent uses it
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
1,367 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Tracing Process
- Adding Stack Traces
- Finding Which Test Causes Pollution
- Real Example: Empty projectDir
- Key Principle
- Stack Trace Tips
- Real-World Impact
Files
SKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwhy
When your agent uses it
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
755 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore3,337 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbuild-mcp
When your agent uses it
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
2,857 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- 🚀 High-Level Workflow
- 📚 Documentation Library
Files
SKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-arxiv-mcp
When your agent uses it
Guide for setup arXiv paper search MCP server using Docker MCP
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
1,059 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Docker MCP is available
- 3. Search and add paper-search MCP server
- 4. Test the setup
- 5. Update CLAUDE.md file
- 6. Alternative: arxiv-mcp-server
Files
SKILL.mdcore4,197 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-codemap-cli
When your agent uses it
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
1,588 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Codemap is already installed
- 3. Load Codemap documentation
- 4. Guide user through installation
- 5. Verify installation
- 6. Update CLAUDE.md file
- 8. Test Codemap
- 9. Add hooks to settings file
Files
SKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytesSKILL.mdcore6,423 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-context7-mcp
When your agent uses it
Guide for setup Context7 MCP server to load documentation for specific technologies.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
423 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Context7 MCP server is already setup
- 3. Update CLAUDE.md file
Files
SKILL.mdcore1,878 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-serena-mcp
When your agent uses it
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
1,115 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Serena MCP server is already setup
- 3. Load Serena documentation
- 4. Guide user through setup process
- 5. Update CLAUDE.md file
- 6. Project initialization (if needed)
Files
SKILL.mdcore4,789 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcritique
When your agent uses it
Comprehensive multi-perspective review using specialized judges with debate and consensus building
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
2,946 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Important Guidelines
- Usage Examples
- Notes
Files
SKILL.mdcore12,990 bytesSKILL.mdcore12,990 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmemorize
When your agent uses it
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
2,414 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Memory Consolidation Workflow
- Usage
- Output
- Notes
Files
SKILL.mdcore11,154 bytesSKILL.mdcore11,154 bytesSKILL.mdcore11,154 bytesSKILL.mdcore11,154 bytesSKILL.mdcore11,154 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreflect
When your agent uses it
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
5,087 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity (NON-NEGOTIABLE)
- TASK COMPLEXITY TRIAGE
- IMMEDIATE REFLECTION PROTOCOL
- CODE-SPECIFIC REFLECTION CRITERIA
- FACT-CHECKING AND CLAIM VERIFICATION
- NON-CODE OUTPUT REFLECTION
- Report Format
- ITERATIVE REFINEMENT WORKFLOW
- REFINEMENT TRIGGERS
- FINAL VERIFICATION
- IMPROVEMENT DIRECTIVE
- CONFIDENCE ASSESSMENT
- REFINEMENT METRICS
Files
SKILL.mdcore22,527 bytesSKILL.mdcore22,527 bytesSKILL.mdcore22,527 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-local-changes
When your agent uses it
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
4,201 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
- Improvements
- Evaluation Guidelines
- Remember
Files
SKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-pr
When your agent uses it
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
3,470 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
Files
SKILL.mdcore15,261 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtraiage-review
When your agent uses it
This skill should be used when need prioritize what changed code in repository human must review.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
2,264 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Rules
- Process
- Agents
- Random Sample Script
- Output Format
Files
SKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-and-judge
When your agent uses it
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
12,628 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Task
- Arguments
- Context
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
Files
SKILL.mdcore57,645 bytesSKILL.mdcore57,645 bytesSKILL.mdcore57,645 bytesSKILL.mdcore57,645 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-competitively
When your agent uses it
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
6,525 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Generate-Critique-Synthesize (GCS)
- Process
- Output
- Instructions
- Output
- Best Practices
- Examples
Files
SKILL.mdcore26,599 bytesSKILL.mdcore26,599 bytesSKILL.mdcore26,599 bytesSKILL.mdcore26,599 bytesSKILL.mdcore26,599 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-parallel
When your agent uses it
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
25,957 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Implementation Outputs
- Instructions
- Output
- Examples
- Best Practices
Files
SKILL.mdcore118,390 bytesSKILL.mdcore118,390 bytesSKILL.mdcore118,390 bytesSKILL.mdcore118,390 bytesSKILL.mdcore118,390 bytesSKILL.mdcore118,390 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-steps
When your agent uses it
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
16,984 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
- Context Format Reference
Files
SKILL.mdcore76,096 bytesSKILL.mdcore76,096 bytesSKILL.mdcore76,096 bytesSKILL.mdcore76,096 bytesSKILL.mdcore76,096 bytesSKILL.mdcore76,096 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge
When your agent uses it
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
1,729 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Instructions
Files
SKILL.mdcore8,155 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge-with-debate
When your agent uses it
Evaluate solutions through multi-round debate between independent judges until consensus
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
3,901 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Debate-Based Evaluation
- Process
- Output File
- Instructions
- Output File
- Instructions
- Best Practices
- Example Usage
Files
SKILL.mdcore17,223 bytesSKILL.mdcore17,223 bytesSKILL.mdcore17,223 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublaunch-sub-agent
When your agent uses it
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
2,703 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Process
- Examples
- Best Practices
Files
SKILL.mdcore12,102 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulti-agent-patterns
When your agent uses it
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,195 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Why Multi-Agent Architectures
- Architectural Patterns
- Context Isolation as Design Principle
- Consensus and Coordination
- Failure Modes and Mitigations
- Applying Patterns in Claude Code
- Guidelines
- Memory and State Management
- Core Concepts
- Detailed Topics
Files
SKILL.mdcore23,989 bytesSKILL.mdcore23,989 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsubagent-driven-development
When your agent uses it
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,476 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Supported types of execution
- Sequential Execution Process
- Parallel Execution Process
- Parallel Investigation Process
Files
SKILL.mdcore11,059 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtree-of-thoughts
When your agent uses it
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
7,912 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Tree of Thoughts (ToT)
- Process
- Output
- Instructions
- Output
- Instructions
- Best Practices
- Example: API Design
Files
SKILL.mdcore35,055 bytesSKILL.mdcore35,055 bytesSKILL.mdcore35,055 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubadd-task
When your agent uses it
creates draft task file in .specs/tasks/draft/ with original user intent
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,533 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- Input
- Instructions
- Constraints
- Expected Output
- Success Criteria
- Examples
Scripts executed separately
../../scripts/create-folders.sh
Files
../../scripts/create-folders.shruns2,291 bytesSKILL.mdcore6,134 bytesSKILL.mdcore6,134 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbrainstorm
When your agent uses it
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
624 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Process
- After the Design
- Key Principles
Files
SKILL.mdcore3,093 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-ideas
When your agent uses it
Generate ideas in one shot using creative sampling
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
166 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore814 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimplement-task
When your agent uses it
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
19,607 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Vocabulary (read this first — two different things are called "phase")
- Command Arguments
- Task Selection and Status Management
- CRITICAL: You Are an ORCHESTRATOR ONLY
- CRITICAL
- Overview
- Complete Workflow Overview
- Workflow Phase 0: Parse User Input and Select Task
- Workflow Phase 1: Load and Analyze Task
- Workflow Phase 2: Execute Implementation Phases
- ⚠<U+FE0F> CHECKPOINT: Before Proceeding to Definition-of-Done Verification
- Workflow Phase 3: Definition of Done Verification
- Workflow Phase 4: Move Task to Done
- Workflow Phase 5: Aggregation and Reporting
- Execution Flow Diagram
- Usage Examples
- Error Handling
- Checklist
- Appendix A: What the Task File and Sub-Task Files Provide
Scripts executed separately
../../scripts/create-scratchpad.sh
Files
../../scripts/create-scratchpad.shruns1,431 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytesSKILL.mdcore84,998 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-task
When your agent uses it
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
16,937 tokensWhen the skill is activated
Reference documents
3,124 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- User Input
- Command Arguments
- Usage Examples
- Pre-Flight Checks
- CRITICAL
- Model Selection Policy
- Workflow Execution
- Phase 2: Parallel Analysis
- Phase 3: Architecture Synthesis
- Phase 4: Decomposition
- Promote Task
- Completion
- Error Handling
Scripts executed separately
../../scripts/create-folders.sh../../scripts/create-scratchpad.sh
Files
../../prompts/judge.mddoc12,897 bytes../../scripts/create-folders.shruns2,291 bytes../../scripts/create-scratchpad.shruns1,431 bytesSKILL.mdcore68,452 bytesSKILL.mdcore68,452 bytesSKILL.mdcore68,452 bytesSKILL.mdcore68,452 bytesSKILL.mdcore68,452 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdesign-testing-strategy
When your agent uses it
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
11,321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How To Use This Skill
- Decision Gates
- Test Type Reference
- Case Design Techniques
- Dependency Decision
- Strategic Skip Heuristics
- Test Matrix Schema
- Case Listing Schema
- Sources & Further Reading
- Worked Examples
- Skill Self-Check
- Coverage Analysis
Files
SKILL.mdcore45,601 bytesSKILL.mdcore45,601 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfix-tests
When your agent uses it
Systematically fix all failing tests after business logic changes or refactoring
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
819 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Template
Files
SKILL.mdcore3,711 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-coverage
When your agent uses it
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
12,159 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Coverage Analysis Is
- Per-Type Structure
- Structural / Code Coverage
- Mutation Testing as Coverage Analysis
- Requirements / Feature Coverage
- API / Integration Coverage
- Additional Coverage Types
- Cross-Cutting Topics
- Decision Reference Tables
- Sources & Further Reading
Files
SKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-driven-development
When your agent uses it
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
4,271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Iron Law
- Red-Green-Refactor
- Good Tests
- Why Order Matters
- Common Rationalizations
- Red Flags - STOP and Start Over
- Example: Bug Fix
- Verification Checklist
- When Stuck
- Debugging Integration
- Final Rule
- Overview
- The Iron Laws
- Anti-Pattern 1: Testing Mock Behavior
- Anti-Pattern 2: Test-Only Methods in Production
- Anti-Pattern 3: Mocking Without Understanding
- Anti-Pattern 4: Incomplete Mocks
- Anti-Pattern 5: Integration Tests as Afterthought
- When Mocks Become Too Complex
- TDD Prevents These Anti-Patterns
- Quick Reference
- Red Flags
- The Bottom Line
Files
SKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-tests
When your agent uses it
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,785 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
Files
SKILL.mdcore8,088 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubactualize
When your agent uses it
Reconcile the project's FPF state with recent repository changes
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
944 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- File: .fpf/.baseline
- When to Run
Files
SKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytesSKILL.mdcore3,727 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubadd-task
When your agent uses it
creates draft task file in .specs/tasks/draft/ with original user intent
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,503 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- Input
- Instructions
- Constraints
- Expected Output
- Success Criteria
- Examples
Files
SKILL.mdcore6,006 bytesSKILL.mdcore6,006 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubagent-evaluation
When your agent uses it
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
12,599 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Evaluation Challenges
- Evaluation Rubric Design
- Evaluation Methodologies
- Test Set Design
- Context Engineering Evaluation
- Advanced Evaluation: LLM-as-Judge
- Evaluation Metrics Reference
- Evaluation Approaches
- Rubric Generation
- Practical Guidance
- Examples
- Guidelines
- Example: Evaluating a Claude Code Command
- Position Bias
- Length Bias
- Self-Enhancement Bias
- Verbosity Bias
- Authority Bias
- Aggregate Bias Detection
- Summary Table
- Pattern 1: Structured Evaluation Workflow
- Pattern 2: Hierarchical Evaluation Workflow
- Pattern 3: Panel of LLM Judges (PoLL)
- Pattern 4: Confidence Calibration
- Pattern 5: Structured Output Format
- Evaluation Workflows for Claude Code Development
- Anti-Patterns to Avoid
- Handling Evaluation Failures
- Validating Evaluation Prompts (Meta-Evaluation)
- Metric Categories
- Selection Decision Tree
- Metric Selection by Use Case
- Interpreting Metric Results
- Reporting Template
Files
SKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytesSKILL.mdcore57,295 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse
When your agent uses it
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
3,664 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Method Selection Logic
- Steps
- Method 1: Gemba Walk
- Method 2: Value Stream Mapping
- Method 3: Muda (Waste Analysis)
- Notes
Files
SKILL.mdcore15,105 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyse-problem
When your agent uses it
Comprehensive A3 one-page problem analysis with root cause and action plan
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
3,906 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- A3 Template
- Examples
- Notes
Files
SKILL.mdcore31,282 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyze-issue
When your agent uses it
Analyze a GitHub issue and create a detailed technical specification
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
554 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Issue Summary
- Problem Statement
- Technical Approach
- Implementation Plan
- Test Plan
- Files to Modify
- Files to Create
- Existing Utilities to Leverage
- Success Criteria
- Out of Scope
Files
SKILL.mdcore2,229 bytesSKILL.mdcore2,229 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubapply-anthropic-skill-best-practices
When your agent uses it
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
10,120 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core principles
- Skill structure
- Workflows and feedback loops
- Content guidelines
- Common patterns
- Evaluation and iteration
- Anti-patterns to avoid
- Advanced: Skills with executable code
- Technical notes
- Checklist for effective Skills
Files
SKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytesSKILL.mdcore42,299 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubattach-review-to-pr
When your agent uses it
Add line-specific review comments to pull requests using GitHub CLI API
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
3,831 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preferred Approach: Using MCP GitHub Tools
- Overview
- Prerequisites
- Understanding GitHub's Review Comment System
- Adding a Single Line-Specific Comment
- Adding Multiple Line-Specific Comments Together
- Common Issues and Solutions
- Best Practices
- Workflow Examples
- Helpful Helper Scripts
- Related Documentation
- API Reference
Files
SKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytesSKILL.mdcore14,430 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbrainstorm
When your agent uses it
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
607 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Process
- After the Design
- Key Principles
Files
SKILL.mdcore2,996 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbuild-mcp
When your agent uses it
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
2,857 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- 🚀 High-Level Workflow
- 📚 Documentation Library
Files
SKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcause-and-effect
When your agent uses it
Systematic Fishbone analysis exploring problem causes across six categories
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,464 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore6,747 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcommit
When your agent uses it
Create well-formatted commits with conventional commit messages and emoji
What it loads into context
Frontmatter
17 tokensAlways available to the agent
SKILL.md
2,232 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Best Practices for Commits
- Guidelines for Splitting Commits
- Examples
- Command Options
- Branch Naming Convention
- Important Notes
Files
SKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytesSKILL.mdcore8,888 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcontext-engineering
When your agent uses it
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
10,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Core Concepts
- Detailed Topics
- Practical Guidance
- Examples
- Guidelines
- Hallucination Detection Workflow
- Lost-in-Middle Detection Workflow
- Error Propagation Analysis Workflow
- Context Relevance Scoring Workflow
- Context Health Monitoring Workflow
- Guidelines for Multi-Agent Verification
- Core Concepts
- Detailed Topics
- Practical Guidance
- Guidelines
Files
SKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytesSKILL.mdcore53,651 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-agent
When your agent uses it
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
4,537 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- What Are Agents?
- Agent File Structure
- Frontmatter Fields Reference
- Triggering Patterns
- System Prompt Design
- AI-Assisted Agent Generation
- Default Agent Standards
- Validation Rules
- Production Examples
- Agent Creation Process
- Best Practices Summary
- Integration with Workflows
- Create the Agent
Files
SKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytesSKILL.mdcore20,111 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-command
When your agent uses it
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
3,493 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Every Command Must Start with Frontmatter
- Slash Command Features
- Before Creating: Study Similar Commands
- Phase 1: Understanding Purpose
- Phase 2: Category Classification
- Phase 3: Pattern Selection
- Phase 4: Command Location
- Phase 5: Resource Planning
- Critical: Copy Patterns from Similar Commands
Files
SKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytesSKILL.mdcore14,948 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-hook
When your agent uses it
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
24,116 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Task (/create-hook)
- Your Workflow
- Hook Templates
- Quick Reference
- Success Criteria
- Set up your first hook
- What you can automate
- How hooks work
- Prompt-based hooks
- Agent-based hooks
- Limitations and troubleshooting
- Learn more
- Hook lifecycle
- Configuration
- Hook input and output
- Hook events
- Prompt-based hooks
- Agent-based hooks
- Run hooks in the background
- Security considerations
- Debug hooks
Files
SKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytesSKILL.mdcore110,406 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-ideas
When your agent uses it
Generate ideas in one shot using creative sampling
What it loads into context
Frontmatter
16 tokensAlways available to the agent
SKILL.md
147 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore721 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-pr
When your agent uses it
Create pull requests using GitHub CLI with proper templates and formatting
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,043 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Pre-flight Checks
- Creating a New Pull Request
- Best Practices
- Additional GitHub CLI PR Commands
- Using Templates for PR Creation
- Related Documentation
Files
SKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytesSKILL.mdcore4,340 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-rule
When your agent uses it
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
4,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Rules
- When to Create a Rule
- Rule Types
- Rule Structure: The Contrastive Pattern
- Writing Effective Rules
- Directory Structure
- Rule Creation Process
- Complete Rule Example
- Complete Path-Scoped Rule Example
- Anti-Patterns
- Rule Creation Checklist
- The Bottom Line
- Claude Code Official Rules Guidlines
Files
SKILL.mdcore21,996 bytesSKILL.mdcore21,996 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-skill
When your agent uses it
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
6,691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- About Skills
- What is a Skill?
- TDD Mapping for Skills
- When to Create a Skill
- Skill Types
- Directory Structure
- Anatomy of a Skill
- SKILL.md (required)
- Claude Search Optimization (CSO)
- Flowchart Usage
- Code Examples
- File Organization
- The Iron Law (Same as TDD)
- Testing All Skill Types
- Bulletproofing Skills Against Rationalization
- RED-GREEN-REFACTOR for Skills
- Anti-Patterns
- STOP: Before Moving to Next Skill
- Skill Creation Checklist (TDD Adapted)
- Discovery Workflow
- The Bottom Line
- Skill Creation Process
Files
SKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytesSKILL.mdcore30,456 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-workflow-command
When your agent uses it
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
2,734 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Architecture Overview
- Key Principles
- Implementation Process
- Execution Patterns
- Example: Feature Implementation Workflow
- Known Limitations
- Validation Checklist
- Create the Workflow
Files
SKILL.mdcore11,347 bytesSKILL.mdcore11,347 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcritique
When your agent uses it
Comprehensive multi-perspective review using specialized judges with debate and consensus building
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
2,926 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Important Guidelines
- Usage Examples
- Notes
Files
SKILL.mdcore12,895 bytesSKILL.mdcore12,895 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdecay
When your agent uses it
Manage evidence freshness by identifying stale decisions and providing governance actions
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
1,556 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Concepts
- Action (Run-Time)
- Natural Language Usage
- WLNK Principle
- Audit Trail
- Common Workflows
Files
SKILL.mdcore5,946 bytesSKILL.mdcore5,946 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdesign-testing-strategy
When your agent uses it
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
11,321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How To Use This Skill
- Decision Gates
- Test Type Reference
- Case Design Techniques
- Dependency Decision
- Strategic Skip Heuristics
- Test Matrix Schema
- Case Listing Schema
- Sources & Further Reading
- Worked Examples
- Skill Self-Check
- Coverage Analysis
Files
SKILL.mdcore45,601 bytesSKILL.mdcore45,601 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-and-judge
When your agent uses it
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
12,591 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Task
- Arguments
- Context
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
Files
SKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytesSKILL.mdcore57,505 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-competitively
When your agent uses it
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
6,512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Generate-Critique-Synthesize (GCS)
- Process
- Output
- Instructions
- Output
- Best Practices
- Examples
Files
SKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytesSKILL.mdcore26,533 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-parallel
When your agent uses it
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
25,908 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Implementation Outputs
- Instructions
- Output
- Examples
- Best Practices
Files
SKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytesSKILL.mdcore118,233 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdo-in-steps
When your agent uses it
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
16,948 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- RED FLAGS - Never Do These
- Model Selection Policy
- Process
- Implementation Output
- Instructions
- Output
- Error Handling
- Examples
- Best Practices
- Context Format Reference
Files
SKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytesSKILL.mdcore75,963 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfix-tests
When your agent uses it
Systematically fix all failing tests after business logic changes or refactoring
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
807 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Template
Files
SKILL.mdcore3,662 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-notes
When your agent uses it
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,493 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Patterns
- Common Mistakes
- Best Practices
- Basic Operations
- Using Multiple Namespaces
- Merging Notes
- Configuration Options
- Workflow Examples
Files
SKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytesSKILL.mdcore9,735 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubgit-worktrees
When your agent uses it
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
10,084 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Quick Reference
- Essential Commands
- Workflow Patterns
- Comparing and Merging Changes Between Worktrees
- Directory Structure Conventions
- Best Practices
- Common Issues and Solutions
- Common Mistakes
- Agent Workflow Integration
- Verification Checklist
- Instructions
- Comparison Modes
- Worktree Detection
- Examples
- Output Format
- Common Workflows
- Important Notes
- Integration with Create Worktree
- Troubleshooting
- Instructions
- Worktree Path Convention
- Examples
- Setup Detection Examples
- Common Workflows
- Important Notes
- Cleanup
- Troubleshooting
- Instructions
- Merge Strategies Reference
- Examples
- Interactive Patch Mode Guide
- Cherry-Pick Selective Workflow
- Multi-Worktree Merge Workflow
- Common Workflows
- Important Notes
- Cleanup After Merge
- Troubleshooting
- Integration with Other Commands
Files
SKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytesSKILL.mdcore41,512 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimplement-task
When your agent uses it
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
19,553 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Vocabulary (read this first — two different things are called "phase")
- Command Arguments
- Task Selection and Status Management
- CRITICAL: You Are an ORCHESTRATOR ONLY
- CRITICAL
- Overview
- Complete Workflow Overview
- Workflow Phase 0: Parse User Input and Select Task
- Workflow Phase 1: Load and Analyze Task
- Workflow Phase 2: Execute Implementation Phases
- ⚠<U+FE0F> CHECKPOINT: Before Proceeding to Definition-of-Done Verification
- Workflow Phase 3: Definition of Done Verification
- Workflow Phase 4: Move Task to Done
- Workflow Phase 5: Aggregation and Reporting
- Execution Flow Diagram
- Usage Examples
- Error Handling
- Checklist
- Appendix A: What the Task File and Sub-Task Files Provide
Files
SKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytesSKILL.mdcore84,833 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge
When your agent uses it
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
1,721 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Workflow
- Instructions
Files
SKILL.mdcore8,119 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjudge-with-debate
When your agent uses it
Evaluate solutions through multi-round debate between independent judges until consensus
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
3,889 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Debate-Based Evaluation
- Process
- Output File
- Instructions
- Output File
- Instructions
- Best Practices
- Example Usage
Files
SKILL.mdcore17,167 bytesSKILL.mdcore17,167 bytesSKILL.mdcore17,167 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubkaizen
When your agent uses it
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
4,185 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Four Pillars
- Integration with Commands
- Red Flags
- Remember
Files
SKILL.mdcore17,876 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublaunch-sub-agent
When your agent uses it
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
2,657 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Process
- Examples
- Best Practices
Files
SKILL.mdcore11,928 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-issues
When your agent uses it
Load all open issues from GitHub and save them as markdown files
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
366 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,474 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubload-pr-comments
When your agent uses it
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,999 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Group and Rewrite as Tasks
- Step 4: .gitignore Handling
- Step 5: Write Files
- Step 6: Report
- Edge Cases
Files
SKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytesSKILL.mdcore8,301 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmemorize
When your agent uses it
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
2,391 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Memory Consolidation Workflow
- Usage
- Output
- Notes
Files
SKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytesSKILL.mdcore11,055 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulti-agent-patterns
When your agent uses it
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,195 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concepts
- Why Multi-Agent Architectures
- Architectural Patterns
- Context Isolation as Design Principle
- Consensus and Coordination
- Failure Modes and Mitigations
- Applying Patterns in Claude Code
- Guidelines
- Memory and State Management
- Core Concepts
- Detailed Topics
Files
SKILL.mdcore23,989 bytesSKILL.mdcore23,989 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-do-check-act
When your agent uses it
Iterative PDCA cycle for systematic experimentation and continuous improvement
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore7,516 bytesSKILL.mdcore7,516 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplan-task
When your agent uses it
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
16,845 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Goal
- User Input
- Command Arguments
- Usage Examples
- Pre-Flight Checks
- CRITICAL
- Model Selection Policy
- Workflow Execution
- Phase 2: Parallel Analysis
- Phase 3: Architecture Synthesis
- Phase 4: Decomposition
- Promote Task
- Completion
- Error Handling
Files
SKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytesSKILL.mdcore68,168 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubprompt-engineering
When your agent uses it
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
3,611 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Key Patterns
- Best Practices
- Common Pitfalls
- Integration Patterns
- Performance Optimization
- Core principles
- Overview
- The Seven Principles
- Principle Combinations by Prompt Type
- Why This Works: The Psychology
- Ethical Use
- Quick Reference
Files
SKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytesSKILL.mdcore16,936 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpropose-hypotheses
When your agent uses it
Execute complete FPF cycle from hypothesis generation to decision
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
1,650 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Input
- Workflow Execution
- Completion
Files
SKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubquery
When your agent uses it
Search the FPF knowledge base and display hypothesis details with assurance information
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
1,038 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Search Locations
- Output Format
- Search Methods
- R_eff Display
- Dependency Tree Display
- Examples
Files
SKILL.mdcore3,469 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreflect
When your agent uses it
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
5,057 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Your Identity (NON-NEGOTIABLE)
- TASK COMPLEXITY TRIAGE
- IMMEDIATE REFLECTION PROTOCOL
- CODE-SPECIFIC REFLECTION CRITERIA
- FACT-CHECKING AND CLAIM VERIFICATION
- NON-CODE OUTPUT REFLECTION
- Report Format
- ITERATIVE REFINEMENT WORKFLOW
- REFINEMENT TRIGGERS
- FINAL VERIFICATION
- IMPROVEMENT DIRECTIVE
- CONFIDENCE ASSESSMENT
- REFINEMENT METRICS
Files
SKILL.mdcore22,391 bytesSKILL.mdcore22,391 bytesSKILL.mdcore22,391 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreset
When your agent uses it
Reset the FPF reasoning cycle to start fresh
What it loads into context
Frontmatter
17 tokensAlways available to the agent
SKILL.md
737 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
Files
SKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresolve-fixed-pr-comments
When your agent uses it
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,991 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Guidelines
- Red Flags - STOP and Leave Unresolved
- How to Use
- Step 0: Verify what tools are available
- Step 1: Resolve the Target PR
- Step 2: Retrieve UNRESOLVED Comments
- Step 3: Verify Each Thread Against the CURRENT Codebase
- Step 4: Resolve the Genuinely-Fixed Threads
- Step 5: Report
- Examples
- Troubleshooting / Common Issues
Files
SKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytesSKILL.mdcore16,506 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-local-changes
When your agent uses it
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
4,173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
- Improvements
- Evaluation Guidelines
- Remember
Files
SKILL.mdcore18,539 bytesSKILL.mdcore18,539 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-pr
When your agent uses it
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
3,446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Command Arguments
- Review Workflow
Files
SKILL.mdcore15,176 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubroot-cause-tracing
When your agent uses it
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
1,367 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Tracing Process
- Adding Stack Traces
- Finding Which Test Causes Pollution
- Real Example: Empty projectDir
- Key Principle
- Stack Trace Tips
- Real-World Impact
Files
SKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytesSKILL.mdcore5,616 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-arxiv-mcp
When your agent uses it
Guide for setup arXiv paper search MCP server using Docker MCP
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,044 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Docker MCP is available
- 3. Search and add paper-search MCP server
- 4. Test the setup
- 5. Update CLAUDE.md file
- 6. Alternative: arxiv-mcp-server
Files
SKILL.mdcore4,116 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-codemap-cli
When your agent uses it
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,575 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Codemap is already installed
- 3. Load Codemap documentation
- 4. Guide user through installation
- 5. Verify installation
- 6. Update CLAUDE.md file
- 8. Test Codemap
- 9. Add hooks to settings file
Files
SKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytesSKILL.mdcore6,351 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-context7-mcp
When your agent uses it
Guide for setup Context7 MCP server to load documentation for specific technologies.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
409 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Context7 MCP server is already setup
- 3. Update CLAUDE.md file
Files
SKILL.mdcore1,804 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-serena-mcp
When your agent uses it
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
1,102 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Determine setup context
- 2. Check if Serena MCP server is already setup
- 3. Load Serena documentation
- 4. Guide user through setup process
- 5. Update CLAUDE.md file
- 6. Project initialization (if needed)
Files
SKILL.mdcore4,713 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubstatus
When your agent uses it
Display the current state of the FPF knowledge base
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
860 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action (Run-Time)
- Status Report Format
- Phase Detection Logic
- Evidence Freshness Check
- Example Output
Files
SKILL.mdcore2,938 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsubagent-driven-development
When your agent uses it
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,476 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Supported types of execution
- Sequential Execution Process
- Parallel Execution Process
- Parallel Investigation Process
Files
SKILL.mdcore11,059 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-coverage
When your agent uses it
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
12,159 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Coverage Analysis Is
- Per-Type Structure
- Structural / Code Coverage
- Mutation Testing as Coverage Analysis
- Requirements / Feature Coverage
- API / Integration Coverage
- Additional Coverage Types
- Cross-Cutting Topics
- Decision Reference Tables
- Sources & Further Reading
Files
SKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytesSKILL.mdcore51,644 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-driven-development
When your agent uses it
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
4,271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Iron Law
- Red-Green-Refactor
- Good Tests
- Why Order Matters
- Common Rationalizations
- Red Flags - STOP and Start Over
- Example: Bug Fix
- Verification Checklist
- When Stuck
- Debugging Integration
- Final Rule
- Overview
- The Iron Laws
- Anti-Pattern 1: Testing Mock Behavior
- Anti-Pattern 2: Test-Only Methods in Production
- Anti-Pattern 3: Mocking Without Understanding
- Anti-Pattern 4: Incomplete Mocks
- Anti-Pattern 5: Integration Tests as Afterthought
- When Mocks Become Too Complex
- TDD Prevents These Anti-Patterns
- Quick Reference
- Red Flags
- The Bottom Line
Files
SKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytesSKILL.mdcore17,899 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-prompt
When your agent uses it
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,396 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Prompt Types & Testing Strategies
- TDD Mapping for Prompt Testing
- Why Use Subagents for Testing?
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Prompt (Make It Pass)
- REFACTOR Phase: Optimize Prompt (Stay Green)
- Subagent Testing Patterns
- Testing Checklist (TDD for Prompts)
- Common Mistakes (Same as Code TDD)
- Example: Testing a Command
- Quick Reference
- Integration with Prompt Engineering
- The Bottom Line
Files
SKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytesSKILL.mdcore19,978 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtest-skill
When your agent uses it
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,911 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- TDD Mapping for Skill Testing
- RED Phase: Baseline Testing (Watch It Fail)
- GREEN Phase: Write Minimal Skill (Make It Pass)
- VERIFY GREEN: Pressure Testing
- REFACTOR Phase: Close Loopholes (Stay Green)
- Meta-Testing (When GREEN Isn't Working)
- When Skill is Bulletproof
- Example: TDD Skill Bulletproofing
- Testing Checklist (TDD for Skills)
- Common Mistakes (Same as TDD)
- Quick Reference (TDD Cycle)
- The Bottom Line
- Real-World Impact
Files
SKILL.mdcore12,796 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubthought-based-reasoning
When your agent uses it
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
5,353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Reference
- Core Techniques
- Decision Matrix: Which Technique to Use
- Best Practices
- Common Mistakes
- References
Files
SKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytesSKILL.mdcore21,949 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtraiage-review
When your agent uses it
This skill should be used when need prioritize what changed code in repository human must review.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
2,264 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Rules
- Process
- Agents
- Random Sample Script
- Output Format
Files
SKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytesSKILL.mdcore10,043 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtree-of-thoughts
When your agent uses it
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
7,899 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pattern: Tree of Thoughts (ToT)
- Process
- Output
- Instructions
- Output
- Instructions
- Best Practices
- Example: API Design
Files
SKILL.mdcore34,989 bytesSKILL.mdcore34,989 bytesSKILL.mdcore34,989 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubupdate-docs
When your agent uses it
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,900 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
- Core Documentation Philosophy
- Documentation Discovery Process
- Smart Documentation Strategy
- Documentation Audit Guidelines
- Documentation Patterns Reference
- Quality Gates
- Documentation Update Summary Template
Files
SKILL.mdcore22,741 bytesSKILL.mdcore22,741 bytesSKILL.mdcore22,741 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwhy
When your agent uses it
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
745 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Usage
- Variables
- Steps
- Examples
- Notes
Files
SKILL.mdcore3,284 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-concisely
When your agent uses it
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
16,199 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- All Rules
- Contents
- I. Introductory
- II. Elementary Rules Of Usage
- III. Elementary Principles Of Composition
- V. Words And Expressions Commonly Misused
Files
SKILL.mdcore72,863 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-tests
When your agent uses it
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,773 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- User Arguments
- Context
- Goal
- Important Constraints
- Workflow Steps
- Success Criteria
- Agent Instructions Templates
Files
SKILL.mdcore8,039 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- actualize
- add-task
- agent-evaluation
- analyse
- analyse-problem
- analyze-issue
- apply-anthropic-skill-best-practices
- attach-review-to-pr
- brainstorm
- build-mcp
- cause-and-effect
- commit
- context-engineering
- create-agent
- create-command
- create-hook
- create-ideas
- create-pr
- create-rule
- create-skill
- create-workflow-command
- critique
- decay
- design-testing-strategy
- do-and-judge
- do-competitively
- do-in-parallel
- do-in-steps
- fix-tests
- git-notes
- git-worktrees
- implement-task
- judge
- judge-with-debate
- kaizen
- launch-sub-agent
- load-issues
- load-pr-comments
- memorize
- multi-agent-patterns
- plan-do-check-act
- plan-task
- prompt-engineering
- propose-hypotheses
- query
- reflect
- reset
- resolve-fixed-pr-comments
- review-local-changes
- review-pr
- root-cause-tracing
- setup-arxiv-mcp
- setup-codemap-cli
- setup-context7-mcp
- setup-serena-mcp
- status
- subagent-driven-development
- test-coverage
- test-driven-development
- test-prompt
- test-skill
- thought-based-reasoning
- traiage-review
- tree-of-thoughts
- update-docs
- why
- write-concisely
- write-tests
- agent-evaluation
- apply-anthropic-skill-best-practices
- context-engineering
- create-agent
- create-command
- create-hook
- create-rule
- create-skill
- create-workflow-command
- prompt-engineering
- test-prompt
- test-skill
- thought-based-reasoning
- update-docs
- write-concisely
- actualize
- decay
- propose-hypotheses
- query
- reset
- status
- analyze-issue
- attach-review-to-pr
- commit
- create-pr
- git-notes
- git-worktrees
- load-issues
- load-pr-comments
- resolve-fixed-pr-comments
- analyse
- analyse-problem
- cause-and-effect
- kaizen
- plan-do-check-act
- root-cause-tracing
- why
- build-mcp
- setup-arxiv-mcp
- setup-codemap-cli
- setup-context7-mcp
- setup-serena-mcp
- critique
- memorize
- reflect
- review-local-changes
- review-pr
- traiage-review
- do-and-judge
- do-competitively
- do-in-parallel
- do-in-steps
- judge
- judge-with-debate
- launch-sub-agent
- multi-agent-patterns
- subagent-driven-development
- tree-of-thoughts
- add-task
- brainstorm
- create-ideas
- implement-task
- plan-task
- design-testing-strategy
- fix-tests
- test-coverage
- test-driven-development
- write-tests
- actualize
- add-task
- agent-evaluation
- analyse
- analyse-problem
- analyze-issue
- apply-anthropic-skill-best-practices
- attach-review-to-pr
- brainstorm
- build-mcp
- cause-and-effect
- commit
- context-engineering
- create-agent
- create-command
- create-hook
- create-ideas
- create-pr
- create-rule
- create-skill
- create-workflow-command
- critique
- decay
- design-testing-strategy
- do-and-judge
- do-competitively
- do-in-parallel
- do-in-steps
- fix-tests
- git-notes
- git-worktrees
- implement-task
- judge
- judge-with-debate
- kaizen
- launch-sub-agent
- load-issues
- load-pr-comments
- memorize
- multi-agent-patterns
- plan-do-check-act
- plan-task
- prompt-engineering
- propose-hypotheses
- query
- reflect
- reset
- resolve-fixed-pr-comments
- review-local-changes
- review-pr
- root-cause-tracing
- setup-arxiv-mcp
- setup-codemap-cli
- setup-context7-mcp
- setup-serena-mcp
- status
- subagent-driven-development
- test-coverage
- test-driven-development
- test-prompt
- test-skill
- thought-based-reasoning
- traiage-review
- tree-of-thoughts
- update-docs
- why
- write-concisely
- write-tests
Repository facts
- License
- GPL-3.0
- Created
- Nov 13, 2025
- Last pushed
- Aug 26, 2026
- Forks
- 167
- Open issues
- 7
- Project activity
- Slowing
Rank over the last 12 weeks
Now #582 · best #450 · down 93 in 30 days
- #571 on Nov 1
- #572 on Nov 2
- #576 on Nov 3
- #577 on Nov 4
- #581 on Nov 5
- #582 since Nov 6
78 earlier periods
- #462 on Aug 2
- #467 on Aug 7
- #478 on Aug 11
- #476 on Aug 12
- #484 on Aug 13
- #483 on Aug 14
- #467 on Aug 15
- #471 on Aug 16
- #488 on Aug 18
- #485 on Aug 19
- #486 on Aug 20
- #481 on Aug 21
- #468 on Aug 22
- #489 on Aug 23
- #487 on Aug 24
- #488 on Aug 25
- #475 on Aug 26
- #482 on Aug 27
- #475 on Aug 28
- #465 on Aug 29
- #455 on Aug 30
- #474 on Aug 31
- #480 on Sep 1
- #481 on Sep 2
- #485 on Sep 3
- #462 on Sep 4
- #450 on Sep 5
- #456 on Sep 6
- #460 on Sep 7
- #472 on Sep 8
- #466 on Sep 9
- #469 on Sep 10
- #465 on Sep 11
- #464 on Sep 12
- #462 on Sep 13
- #476 on Sep 14
- #471 on Sep 15
- #480 on Sep 16
- #472 on Sep 17
- #480 on Sep 18
- #463 on Sep 19
- #474 on Sep 20
- #477 on Sep 21
- #486 on Sep 22
- #480 on Sep 23
- #469 on Sep 24
- #471 on Sep 25
- #465 on Sep 26
- #480 on Sep 27
- #487 on Sep 28
- #495 on Sep 29
- #493 on Sep 30
- #485 on Oct 1
- #483 on Oct 2
- #470 on Oct 3
- #466 on Oct 4
- #489 on Oct 6
- #503 on Oct 8
- #502 on Oct 9
- #497 on Oct 10
- #500 on Oct 11
- #511 on Oct 12
- #507 on Oct 13
- #511 on Oct 14
- #508 on Oct 15
- #513 on Oct 16
- #502 on Oct 17
- #508 on Oct 18
- #525 on Oct 20
- #529 on Oct 21
- #522 on Oct 22
- #515 on Oct 23
- #502 on Oct 24
- #553 on Oct 25
- #562 on Oct 28
- #565 on Oct 29
- #567 on Oct 30
- #568 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 898 notes
antigravity/skills/actualize/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/actualize/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/add-task/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/agent-evaluation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/analyze-issue/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/apply-anthropic-skill-best-practices/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/apply-anthropic-skill-best-practices/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/apply-anthropic-skill-best-practices/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/apply-anthropic-skill-best-practices/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedantigravity/skills/apply-anthropic-skill-best-practices/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 3 broad permissionsin 3 files: propose-hypotheses/SKILL.md:1 commit/SKILL.md:1 create-pr/SKILL.md:1
- 49 dangerous shell commandsin 10 files: create-hook/SKILL.md:679 create-hook/SKILL.md:680 create-hook/SKILL.md:679 and 7 more
- 869 network referencesin 64 files: test-coverage/SKILL.md:39 test-coverage/SKILL.md:39 test-coverage/SKILL.md:39 and 61 more
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 3 files: plugins/sdd/scripts/create-folders.sh:1 plugins/sdd/scripts/create-scratchpad.sh:1 plugins/reflexion/hooks/src/index.ts:1
- 15 references to secretsin 9 files: analyse/SKILL.md:157 kaizen/SKILL.md:304 analyse/SKILL.md:158 and 6 more
- No requests to vote in Hot
Show all 941 signals by file
.claude-plugin/marketplace.json
antigravity/skills/analyse/SKILL.md
antigravity/skills/apply-anthropic-skill-best-practices/SKILL.md
- Network accessline 135
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and - Network accessline 139
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like refe - Network accessline 805
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instr
antigravity/skills/attach-review-to-pr/SKILL.md
- Network accessline 107
"line": 26, "body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 108
"body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", "created_at": "2025-11-16T22:40:46Z" - Network accessline 109
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 193
"id": 3470546747, "state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 194
"state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", "submitted_at": "2025-11-16T22:42:43Z", - Network accessline 195
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 329
\`\`\`typescript async function getData() { const result = await fetch(url); - Network accessline 330
async function getData() { const result = await fetch(url); return result.json(); - Network accessline 331
const result = await fetch(url); - Network accessline 465
- [GitHub API: Pull Request Review Comments](https://docs.github.com/rest/pulls/comments) - Network accessline 466
- [GitHub API: Pull Request Reviews](https://docs.github.com/rest/pulls/reviews) - Network accessline 467
- [GitHub CLI Manual](https://cli.github.com/manual/) - Network accessline 477
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/comments` - Network accessline 493
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/reviews`
antigravity/skills/build-mcp/SKILL.md
- Network accessline 64
Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt` - Network accessline 76
- **Python SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 81
- **TypeScript SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - Network accessline 321
- **MCP Protocol**: Fetch from `https://modelcontextprotocol.io/llms-full.txt` - Complete MCP specification - Network accessline 332
- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 333
- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
antigravity/skills/create-hook/SKILL.md
- Network accessline 182
_Complete templates available at: <https://docs.claude.com/en/docs/claude-code/hooks#examples>_ - Network accessline 186
**📖 Official Docs**: <https://docs.claude.com/en/docs/claude-code/hooks.md> - Network accessline 223
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 224
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 225
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 258
<Tabs> <Tab title="macOS"> Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 260
Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 375
Automatically run [Prettier](https://prettier.io/) on every file Claude edits, so formatting stays consistent without manual intervention. - Network accessline 377
This hook uses the `PostToolUse` event with an `Edit|Write` matcher, so it runs only after file-editing tools. The command extracts the edited file path with [`jq`](https://jqlang.github.io/jq/) and passes it to Prettier. Add this to `.clau - Network accessline 397
<Note> The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Network accessline 398
The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Access to secretsline 418
[Credential-related source omitted] - Dangerous shell operationline 679
"command": "rm -f /tmp/claude-scratch-*.txt" - Network accessline 854
- [Hooks reference](/en/hooks): full event schemas, JSON output format, async hooks, and MCP tool hooks - [Security considerations](/en/hooks#security-considerations): review before deploying hooks in shared or production environments - [Ba - Network accessline 856
- [Bash command validator example](https://github.com/anthropics/claude-code/blob/main/examples/hooks/bash_command_validator_example.py): complete reference implementation - Network accessline 860
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 861
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 862
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 879
<div style={{maxWidth: "500px", margin: "0 auto"}}> <Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hoo - Network accessline 880
<Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from - Network accessline 881
<img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStar - Dangerous shell operationline 924
The script reads the JSON input from stdin, extracts the command, and returns a `permissionDecision` of `"deny"` if it contains `rm -rf`: - Dangerous shell operationline 931
if echo "$COMMAND" | grep -q 'rm -rf'; then - Dangerous shell operationline 944
Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens: - Network accessline 946
<Frame> <img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher check - Network accessline 947
<img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash - Dangerous shell operationline 955
{ "tool_name": "Bash", "tool_input": { "command": "rm -rf /tmp/build" }, ... } - Dangerous shell operationline 964
The script extracts `"rm -rf /tmp/build"` from the input and finds `rm -rf`, so it prints a decision to stdout: - Dangerous shell operationline 1292
echo "Blocked: rm commands are not allowed" >&2 - Network accessline 1404
For extended examples including Bash command validation, prompt filtering, and auto-approval scripts, see [What you can automate](/en/hooks-guide#what-you-can-automate) in the guide and the [Bash command validator reference implementation]( - Network accessline 1634
| Field | Type | Example | Description | | :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | - Network accessline 1635
| :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | URL to fetch content from | | `prompt` | string | `"Extract the API endpoints"` | - Network accessline 1636
| `url` | string | `"https://example.com/api"` | URL to fetch content from | - Dangerous shell operationline 1709
"command": "rm -rf node_modules",
antigravity/skills/create-pr/SKILL.md
- Network accessline 25
# Linux # Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 26
# Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 139
- [PR Template](.github/pull_request_template.md) - [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 140
- [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 141
- [GitHub CLI documentation](https://cli.github.com/manual/)
antigravity/skills/create-rule/SKILL.md
- Network accessline 400
- [Flattening Arrow Code](https://blog.codinghorror.com/flattening-arrow-code/)
antigravity/skills/create-skill/SKILL.md
- Network accessline 388
See [graphviz-conventions.dot](https://github.com/obra/superpowers/blob/main/skills/writing-skills/graphviz-conventions.dot) for graphviz style rules.
antigravity/skills/design-testing-strategy/SKILL.md
- Network accessline 27
| # | Type | ON when | OFF when | Source | |---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with b - Network accessline 28
|---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or - Network accessline 29
| 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or user-visible behavior | [Pragmatic Program - Network accessline 30
| 1 | **Unit** | Code contains any logic: branches, loops, conditionals, computation, transformation, parsing, validation, formatting | Pure declarative wiring (DI registration, route table) with no behavior | [Test Pyramid (Vocke)](https:/ - Network accessline 31
| 2 | **Integration** | Boundary crossing: HTTP call, DB query, external SDK, message queue, filesystem I/O, OR collaboration with >=2 distinct collaborators where unit doubles distort behavior | Pure function with no I/O and 0-1 stable col - Network accessline 32
| 3 | **Component or E2E** | UI surface AND criticality >= MEDIUM-HIGH AND user-facing critical path (signup, checkout, auth, payment, primary CTA) | Internal admin-only screens, dev tooling, or non-critical UI | [Test Pyramid top](https:// - Network accessline 33
| 4 | **Contract** | Public API consumed by >=1 distinct clients (mobile + web, multiple internal services, external partners) AND independent deploy cadence | API where consumer and provider deploy together | [Pact / CDC](https://docs.pact - Network accessline 34
| 5 | **Smoke** | Deployable surface (web app, API, service) AND a deploy/CI pipeline exists where post-deploy validation is meaningful | Library, internal helper, or no deploy pipeline | [Google "What Makes a Good End-to-End Test"](https:/ - Network accessline 35
| 6 | **Property-Based** | Input domain is large or unbounded (numeric ranges, strings, lists, parsers, serializers, encoders, math) AND invariants are stable (round-trip, idempotency, monotonicity, commutativity) AND criticality >= MEDIUM- - Network accessline 64
| Type | Use when | Do NOT use when | Frameworks | Typical dependencies | Google Size | |------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, determini - Network accessline 65
|------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go te - Network accessline 66
| **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go test, JUnit, xUnit, RSpec | None (or in-memory fakes) | [Small](https://testing.googleblog - Network accessline 67
| **integration** | Boundary crossing (DB, HTTP, queue, FS); multiple collaborators where mocking distorts behavior | Pure function with no boundary | vitest, jest, pytest, go test, JUnit + [Testcontainers](https://testcontainers.com/), sup - Network accessline 68
| **component** | UI rendering + interaction within a single component, no full app context | Backend-only logic; multi-page user flow | React Testing Library, Vue Test Utils, Angular TestBed, Storybook interaction tests | jsdom or happy-do - Network accessline 69
| **e2e** | Full user path through running app: real browser, real backend, real DB | Internal helper, single component, non-critical UI | [Playwright](https://playwright.dev/), [Cypress](https://www.cypress.io/), Selenium | Real running ap - Network accessline 70
| **smoke** | Post-deploy go/no-go: hit / health, key endpoints respond, login works | Detailed correctness; smoke is shallow by design | Playwright (1-3 critical paths), HTTP probe scripts, k6 minimal scenarios | Real deployed environment - Network accessline 71
| **contract** | Public API consumed by 2+ distinct clients with independent deploy cadence | Single-consumer internal API; provider and consumer deploy together | [Pact](https://docs.pact.io/), Spring Cloud Contract, OpenAPI schema validat - Network accessline 72
| **property-based** | Large/unbounded input domain with stable invariants (parser, serializer, encoder, math) | Small finite input space; unstable invariants | [Hypothesis](https://hypothesis.works/) (Python), fast-check (TS), QuickCheck ( - Network accessline 76
[Google Test Sizes (Bland)](https://mike-bland.com/2011/11/01/small-medium-large.html) and [SWE at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html) classify tests by **resources** (size), independent of **scope** (paths co - Network accessline 89
| Dimension | [Playwright](https://playwright.dev/) | [Cypress](https://www.cypress.io/) | - Network accessline 101
Use ISTQB Foundation Level black-box techniques to derive **what** to test inside each chosen test type. References: [ISTQB BVA white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf), [ASTQB black - Network accessline 168
When EP, BVA, or decision-table analysis yields **3+ cases with the same shape** (same setup, same assertion, only inputs and expected outputs differ — e.g., parsing valid/invalid date formats; computing tax across brackets; routing rules) - Network accessline 201
| Dependency style | Use when | Avoid when | Notes | |------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic - Network accessline 202
|------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker avail - Network accessline 203
| **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker available | Default for integration tests on Postgres / Re - Network accessline 215
Explicit "don't bother" rules. Skipping these is not laziness — it is risk-adjusted ROI per [ISO/IEC/IEEE 29119 risk-based testing](https://en.wikipedia.org/wiki/ISO/IEC_29119) and [Risk-Based Testing](https://www.softwaretestinghelp.com/ri - Network accessline 223
| **No component test for static markup** | If the component has no state, no events, no conditional rendering, a snapshot is enough — or skip entirely. | | **No unit test for declarative wiring** | DI bindings, route registration, schema d - Network accessline 224
| **No unit test for declarative wiring** | DI bindings, route registration, schema declarations: assert at integration level (does the route serve the right handler) instead. | | **No e2e for things integration covers reliably** | Per [Goo - Network accessline 225
| **No e2e for things integration covers reliably** | Per [Google e2e principles](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html): the smaller the test you can use to cover a behavior, the better. e2e is t - Network accessline 226
| **No tests for spike/throwaway code** | Per [Beck TDD](https://www.oreilly.com/library/view/test-driven-development/0321146530/): if the artifact will be deleted within hours, document the exception with the human partner. Then write test - Network accessline 335
- `type` matches one of `selected_types[*].type` from the matrix - `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange - Network accessline 336
- `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange-act-assert/) - Network accessline 369
1. **Test Pyramid** — Mike Cohn (2009, *Succeeding with Agile*) + Ham Vocke, [The Practical Test Pyramid](https://martinfowler.com/articles/practical-test-pyramid.html), martinfowler.com. - Network accessline 370
2. **Testing Trophy** — Kent C. Dodds (2018), [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) and [Write Tests](https://kentcdodds.com/blog/write-tests). - Network accessline 371
3. **Google Test Sizes** — Mike Bland (2011), [Small / Medium / Large](https://mike-bland.com/2011/11/01/small-medium-large.html); [Software Engineering at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html); [Test Sizes (Goo - Network accessline 372
4. **Google Testing on the Toilet** — [What Makes a Good End-to-End Test](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html), [Testing UI Logic - Follow the User](https://testing.googleblog.com/2020/10/testin - Network accessline 373
5. **ISTQB Foundation Level** — Black-box techniques: [Boundary Value Analysis white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf); [ASTQB Black-Box Techniques](https://astqb.org/4-2-black-box- - Network accessline 374
6. **ISO/IEC/IEEE 29119** — Risk-based test process standard. [Wikipedia overview](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 375
7. **Kent Beck — *Test Driven Development: By Example*** (Addison-Wesley, 2002). [Publisher page](https://www.oreilly.com/library/view/test-driven-development/0321146530/). ISBN 978-0321146533. - Network accessline 376
8. **The Pragmatic Programmer (20th Anniversary Edition)** — Hunt & Thomas (2019). [pragprog.com](https://pragprog.com/titles/tpp20/the-pragmatic-programmer-20th-anniversary-edition/). - Network accessline 377
9. **AAA pattern** — Bill Wake (2001), [3A — Arrange, Act, Assert](https://xp123.com/articles/3a-arrange-act-assert/). **Given-When-Then** — Dan North, [Introducing BDD](https://dannorth.net/introducing-bdd/). - Network accessline 378
10. **Property-based testing** — [Hypothesis: What is property-based testing?](https://hypothesis.works/articles/what-is-property-based-testing/); QuickCheck (Haskell), fast-check (TS). - Network accessline 379
11. **Contract testing / Consumer-Driven Contracts** — [Pact docs](https://docs.pact.io/); [Pactflow CDC explainer](https://pactflow.io/what-is-consumer-driven-contract-testing/). - Network accessline 380
12. **Testcontainers** — [testcontainers.com](https://testcontainers.com/). - Network accessline 381
13. **Table-driven tests** — Dave Cheney, [Prefer table-driven tests](https://dave.cheney.net/2019/05/07/prefer-table-driven-tests); [Go wiki: TableDrivenTests](https://go.dev/wiki/TableDrivenTests). - Network accessline 382
14. **Risk-based testing** — [Risk Management During Test Planning (softwaretestinghelp.com)](https://www.softwaretestinghelp.com/risk-management-during-test-planning-risk-based-testing/). - Network accessline 419
|------|----------|--------| | 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 420
| 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic - Network accessline 421
| 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 422
| 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic: no integration for pure functions](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) | - Network accessline 424
| 4 Contract | OFF | Not a public API | | 5 Smoke | OFF | Not deployable | | 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypoth - Network accessline 426
| 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypothesis.works/articles/what-is-property-based-testing/). Promote at MEDIUM-HIG - Network accessline 521
|------|----------|--------| | 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 522
| 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | **ON** | Boundary crossin - Network accessline 523
| 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 524
| 2 Integration | **ON** | Boundary crossing: HTTP, Postgres, Kafka — [Testing Trophy](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) ROI sweet spot | - Network accessline 525
| 3 Component/E2E | OFF (here) | No UI in this artifact; UI lives in mobile + web repos and tests itself | | 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is - Network accessline 526
| 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is-consumer-driven-contract-testing/) | - Network accessline 527
| 5 Smoke | **ON** | Deployable HTTP service; post-deploy probe of `/users` registration is meaningful — [Google e2e](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html) | - Network accessline 528
| 6 Property-Based | OFF | Input domain (email, password, age) is constrained and well-covered by EP+BVA at unit; criticality is MEDIUM-HIGH but Gate 6 OFF on bounded inputs — [Skip Heuristic](https://hypothesis.works/articles/what-is-prope - Network accessline 645
| 1 Unit | **ON** | Validation helpers (`validateEmail`, `passwordsMatch`, `parseAge`) are pure logic | | 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integratio - Network accessline 646
| 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integration is owned by `POST /users` (Example B) | | 3 Component/E2E | **ON** (component) + **ON** (e2e for the r - Network accessline 647
| 3 Component/E2E | **ON** (component) + **ON** (e2e for the registration path) | UI surface, criticality MEDIUM-HIGH, user-facing critical path — [Test Pyramid top](https://martinfowler.com/articles/practical-test-pyramid.html) + [Follow t - Network accessline 749
- [ ] Each AC is referenced by at least one test case. - [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/ht - Network accessline 750
- [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html). - [ ] Test names contain no "and" (per [ - Network accessline 751
- [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html).
antigravity/skills/git-notes/SKILL.md
antigravity/skills/git-worktrees/SKILL.md
antigravity/skills/kaizen/SKILL.md
- Access to secretsline 304
[Credential-related source omitted] - Access to secretsline 306
[Credential-related source omitted] - Network accessline 372
class UserAPIClient { async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); - Network accessline 373
async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); } - Network accessline 374
return this.fetch(`/users/${id}`); - Network accessline 379
class OrderAPIClient { async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); - Network accessline 380
async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); } - Network accessline 381
return this.fetch(`/orders/${id}`); - Network accessline 446
* @example * const result = await retry( * () => fetch('https://api.example.com/data'), - Network accessline 447
* const result = await retry( * () => fetch('https://api.example.com/data'), * { maxAttempts: 3, baseDelay: 1000 } - Network accessline 448
* () => fetch('https://api.example.com/data'),
antigravity/skills/load-pr-comments/SKILL.md
- Network accessline 32
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 33
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 34
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 39
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch.
antigravity/skills/memorize/SKILL.md
- Network accessline 296
- This command is the counterpart to `/reflexion:reflect`: reflect → curate → memorize. - The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/25 - Network accessline 297
- The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/2510.04618`).
antigravity/skills/reset/SKILL.md
- Dangerous shell operationline 85
rm -rf .fpf/knowledge/L0/*.md - Dangerous shell operationline 86
rm -rf .fpf/knowledge/L1/*.md - Dangerous shell operationline 87
rm -rf .fpf/knowledge/L2/*.md - Dangerous shell operationline 88
rm -rf .fpf/knowledge/invalid/*.md - Dangerous shell operationline 89
rm -rf .fpf/evidence/*.md - Dangerous shell operationline 90
rm -rf .fpf/decisions/*.md
antigravity/skills/resolve-fixed-pr-comments/SKILL.md
- Network accessline 69
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 70
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 71
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 76
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch. - Network accessline 227
**Input:** `resolve-fixed-pr-comments https://github.com/acme/app/pull/7`
antigravity/skills/review-pr/SKILL.md
- Network accessline 266
- Use full git sha + line range, eg. `https://github.com/owner/repo/blob/1d54823877c4de72b2316a64032a54afc404e619/README.md#L13-L17`
antigravity/skills/setup-arxiv-mcp/SKILL.md
antigravity/skills/setup-codemap-cli/SKILL.md
antigravity/skills/setup-context7-mcp/SKILL.md
- Network accessline 36
if no, load <https://raw.githubusercontent.com/upstash/context7/refs/heads/master/README.md> file and guide user through setup process that applicable to agent/operation system.
antigravity/skills/setup-serena-mcp/SKILL.md
- Network accessline 42
- Load <https://raw.githubusercontent.com/oraios/serena/refs/heads/main/README.md> to understand what Serena is and its capabilities - Network accessline 43
- Load <https://oraios.github.io/serena/02-usage/020_running.html> to learn how to run Serena - Network accessline 44
- Load <https://oraios.github.io/serena/02-usage/030_clients.html> to learn how to configure your MCP client - Network accessline 45
- Load <https://oraios.github.io/serena/02-usage/040_workflow.html> to learn how to setup Serena for your project
antigravity/skills/test-coverage/SKILL.md
- Network accessline 39
Coverage is *necessary-but-not-sufficient*. A test can execute a line without asserting anything meaningful; 100% line coverage is routinely achievable with zero assertions ([thinkinglabs.io](https://thinkinglabs.io/articles/2022/03/19/the- - Network accessline 44
- **NOT a measure of correctness.** Coverage proves the test ran, not that it would have failed on a bug. - **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitut - Network accessline 45
- **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - - Network accessline 46
- **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 72
- **Definition.** Percentage of source-code lines (or statements) executed at least once. - **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were t - Network accessline 73
- **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were tested. Multiple statements on one line distort the metric ([Metridev](https://www.metridev - Network accessline 76
| Ecosystem | Tool | |-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 77
|-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | | Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 78
| JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 79
| Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 80
| JVM | [JaCoCo](https://www.eclemma.org/jacoco/) — bytecode instrumentation, industry standard | - Network accessline 81
| C/C++ | `gcov` / `lcov` / `gcovr`, [llvm-cov](https://llvm.org/docs/CommandGuide/llvm-cov.html) | - Network accessline 82
| Go | `go test -cover`, `go tool cover` ([build-cover](https://go.dev/doc/build-cover) added integration-test mode in Go 1.20) | - Network accessline 83
| .NET | [Coverlet](https://github.com/coverlet-coverage/coverlet) (open-source default), [JetBrains dotCover](https://www.jetbrains.com/dotcover/), AltCover. **OpenCover is in maintenance mode — prefer Coverlet / dotCover / AltCover** ([ND - Network accessline 84
| Ruby | [SimpleCov](https://github.com/simplecov-ruby/simplecov) | - Network accessline 89
- **When to use vs skip.** Always-on; cost is near-zero (a CI flag). Never use as a quality goal in itself. - **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blo - Network accessline 90
- **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough)). Apply only with the risk caveat (see Risk-Based Interpreta - Network accessline 95
- **Definition.** Percentage of decision branches (true/false outcomes of `if`, `while`, `for`, `?:`, `switch` cases) executed. - **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, - Network accessline 96
- **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, B=false`). Order of evaluation. Loop iteration counts. Assertion strength. - **Typical tools.** Same as line coverage; enable w - Network accessline 97
- **Typical tools.** Same as line coverage; enable with `--branch` (coverage.py), branch mode (Istanbul is branch-aware by default), JaCoCo reports branches natively. Strictly stronger than line/statement coverage ([Graph AI](https://www.gr - Network accessline 98
- **When to use vs skip.** Default for any non-trivial logic. Prefer branch over line as the primary structural metric. - **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](htt - Network accessline 99
- **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](https://www.leadwithskills.com/blogs/test-coverage-metrics-lines-branches-conditions-paths)) — always paired with the risk - Network accessline 100
- **Cost-benefit ROI.** High — best single structural metric for general-purpose code ([LinearB](https://linearb.io/blog/what-is-branch-coverage)). - Network accessline 120
- **Definition** (per [Wikipedia](https://en.wikipedia.org/wiki/Modified_condition/decision_coverage)): - Network accessline 126
For `n` conditions, MC/DC is achievable with `n+1` to `2n` tests via independence pairs — vastly cheaper than the `2^n` of exhaustive multiple-condition coverage ([LDRA](https://ldra.com/capabilities/mc-dc/)). - Network accessline 128
- **What it does NOT measure.** Loop iteration counts, data values, integration paths, assertion strength. - **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/ - Network accessline 129
- **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc), Parasoft C/C++test. Mostly commercial — open-source MC/ - Network accessline 130
- **When to use vs skip.** When mandated by a standard (DO-178C DAL A, ISO 26262 ASIL D, IEC 62304 Class C high-risk modules, EN 50128 SIL 4, IEC 61508 SIL 4). Outside regulated domains, branch coverage + mutation testing covers the same in - Network accessline 131
- **Targets / thresholds & pitfalls.** 100% by definition in regulated domains. Short-circuit evaluation in C-like languages can make some independence pairs unreachable; compiler optimizations can collapse conditions, so coverage builds mu - Network accessline 153
- **Definition.** Percentage of unique linearly-independent paths through a function. Bounded by cyclomatic complexity `V(G) = decisions + 1` ([Cyclomatic complexity](https://en.wikipedia.org/wiki/Cyclomatic_complexity)). - Network accessline 174
Mutation testing introduces small, syntactic modifications ("mutants") to the source and re-runs the existing test suite against each mutant. If at least one test **fails** for a given mutant, the mutant is **killed** (the suite detected th - Network accessline 186
### Mutant states ([Stryker docs](https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/)) - Network accessline 202
- **Semantic correctness** of assertions — a wrong-but-strict assertion still kills mutants. - **Boundary data values** — operator mutants approximate this but do not replace BVA. - **Equivalent mutants** — variants that produce identical o - Network accessline 204
- **Equivalent mutants** — variants that produce identical observable behavior. Detection is undecidable in general; manual review is the only certain method. Modern tools (Stryker TypeScript Checker, PIT with Major) reduce these heuristica - Network accessline 208
| Ecosystem | Tool | |-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 209
|-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | | .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documen - Network accessline 210
| JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 211
| .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documented in [Microsoft Learn](https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing) | - Network accessline 212
| Java / JVM | [PIT (Pitest)](https://pitest.org/) — reference standard for JVM; Major Mutator for research | - Network accessline 213
| Python | [mutmut](https://mutmut.readthedocs.io/), [Cosmic Ray](https://cosmic-ray.readthedocs.io/), [MutPy](https://github.com/mutpy/mutpy) | - Network accessline 214
| Go | [go-mutesting](https://github.com/avito-tech/go-mutesting), [ooze](https://github.com/gtramontina/ooze) | - Network accessline 215
| PHP | [Infection](https://infection.github.io/) | - Network accessline 216
| Ruby | [mutant](https://github.com/mbj/mutant) | - Network accessline 217
| Rust | [cargo-mutants](https://mutants.rs/) | - Network accessline 218
| C / C++ | [Mull](https://github.com/mull-project/mull) — LLVM-based | - Network accessline 219
| Scala | [Stryker4s](https://stryker-mutator.io/docs/stryker4s/introduction/) | - Network accessline 239
Stryker defaults ([config](https://stryker-mutator.io/docs/stryker-js/configuration/)): `high: 80`, `low: 60`, `break: null`. Set `break` to fail the build below a floor. Apply with the risk caveat: 60–80% on a mature unit suite over pure-l - Network accessline 243
- **Cost.** CPU-quadratic-ish. A 60-second suite generating 1,000 mutants is up to 1,000 × 60s without optimization. Modern tools mitigate via incremental analysis, per-mutant test selection, and parallel runners. - **Benefit.** Catches *mi - Network accessline 244
- **Benefit.** Catches *missing assertions* and *over-mocked* tests that structural coverage cannot detect. It is the **only practical coverage technique that scores assertion strength** — the chief failure mode of "100% coverage with no as - Network accessline 245
- **CI pattern.** Incremental mutation on PR diff; nightly full run on critical modules ([oneuptime](https://oneuptime.com/blog/post/2026-01-24-mutation-testing/view); see also research roundup at [greg4cr.github.io](https://greg4cr.github. - Network accessline 266
The foundational artifact is the **Requirements Traceability Matrix (RTM)** — a two-dimensional table correlating requirements to test cases ([ISTQB Glossary](https://istqb-glossary.page/traceability-matrix/)). Enables: - Network accessline 288
In BDD ecosystems, Gherkin `Scenario:` blocks are the unit of acceptance coverage; each AC ideally maps to one or more scenarios (the Cardinal Rule of BDD: one scenario, one behavior — [Automation Panda](https://automationpanda.com/bdd/)). - Network accessline 290
Foundational standards: **ISTQB Foundation Level** treats RTM as a foundational artifact for systematic test design. **[ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)** parts 1–5 require traceability at the test-plan, test - Network accessline 320
- **Definition.** `(unique_endpoint_method_pairs_hit) / (total_documented_endpoint_method_pairs)`. Often broken down further by `(endpoint, method, status_code)` triples. - **What it does NOT measure.** Whether responses are *correct* — onl - Network accessline 321
- **What it does NOT measure.** Whether responses are *correct* — only that endpoints were hit. The combinatorial inputs leading to each status code. - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL - Network accessline 322
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL-driven test generator that reports endpoint and status-code coverage), [Dredd](https://dredd.org/) (validates HTTP API against API Blueprint / OpenAP - Network accessline 329
- **Definition.** Percentage of consumer-side **interactions** (request/response examples) that the provider has verified. Consumer generates Pact files (JSON contracts) capturing specific interactions; provider runs verification suites aga - Network accessline 330
- **What it does NOT measure.** Provider behavior on inputs no consumer ever sends (negative space). Performance, security, or schema completeness. - **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow - Network accessline 331
- **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow](https://pactflow.io/what-is-consumer-driven-contract-testing/) for storage and verification reports. [Spring Cloud Contract](https://spring.io/pro - Network accessline 332
- **When to use vs skip.** Use when there are multiple independent consumers with independent deploy cadences (microservices, mobile + web sharing a backend). Skip for single-consumer APIs that deploy with the provider, or for library APIs. - Network accessline 333
- **Targets / thresholds & pitfalls.** "Schema valid" is weaker than "contract honored" — schema tells you what shapes are *legal*; contract tells you which fields and behaviors a consumer *actually depends on* ([Speakeasy: Pact vs OpenAPI] - Network accessline 338
- **Definition.** Percentage of schema fields, enum values, and `oneOf` / `anyOf` variants exercised across the test suite. - **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - - Network accessline 339
- **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits - Network accessline 340
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits coverage metrics over schema elements), [Dredd](https://dredd.org/) with hooks for field-level instrumentation, [S - Network accessline 360
- **Definition.** Coverage measured against **input partitions** rather than code. Each Equivalence Partition (EP) and Boundary Value Analysis (BVA) slot from ISTQB Foundation Level black-box techniques becomes a coverage element ([ISTQB BV - Network accessline 369
- **Definition.** **Pairwise (all-pairs)** testing requires that every pair of parameter values appears in at least one test case. Most multi-parameter defects manifest at the 2-way interaction level ([Wikipedia](https://en.wikipedia.org/wi - Network accessline 370
- **What it does NOT measure.** Three-way+ interactions (unless escalated to `t=3`); ordering effects in workflows. - **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports - Network accessline 371
- **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports constraints, weighting, seeding), AllPairs (Satisfice), [NIST ACTS](https://csrc.nist.gov/projects/automated-combina - Network accessline 387
- **Definition.** Percentage of declared transitions (and optionally forbidden transitions) in a state machine exercised by tests. - **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecu - Network accessline 388
- **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecutive transitions. *2-switch* — every triple. *Round-trip* — every cycle in the state graph ([Lead With Skills](https://www.leadwith - Network accessline 467
Coverage targets should be **proportional to risk** ([ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)). The same artifact at different criticalities should not have the same coverage gate. Use the table below as a starting - Network accessline 478
**Delta thresholds** ("must not drop more than X%") are generally safer than absolute floors — they protect against regression in testing discipline without rewarding gaming ([Optivem](https://journal.optivem.com/p/code-coverage-targets-rec - Network accessline 502
| Standard | Domain | Coverage requirement | |----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; St - Network accessline 503
|----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E - Network accessline 504
| **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E ([LDRA structural coverage](https://ldra.com/ - Network accessline 505
| **[ISO 26262](https://www.parasoft.com/learning-center/iso-26262/code-coverage/)** Part 6 Table 9 | Automotive | MC/DC highly recommended for ASIL D; branch for ASIL B–C; statement minimum for ASIL A ([Verifysoft](https://www.verifysoft.c - Network accessline 506
| **[IEC 62304](https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide)** | Medical | Coverage scales with safety class A → B → C; auditors expect MC/DC for Class C high-risk modules; MISRA C/C++ coding standards customar - Network accessline 507
| **[MISRA C / MISRA C++](https://www.misra.org.uk/)** | Embedded (cross-industry) | Coding-rule conformance is the primary signal; coverage is complementary; MC/DC expected for safety-critical components | - Network accessline 562
- **Playwright trace coverage** — Playwright records traces (DOM, network, console) per test; the [trace viewer](https://playwright.dev/docs/trace-viewer) makes UI coverage **auditable** in a way DOM-snapshot tests cannot. Trace artifacts g - Network accessline 563
- **Storybook coverage** — [Storybook Test](https://storybook.js.org/docs/writing-tests) reports which stories (component states) have an interaction test (`play` function) vs only a rendered snapshot. - Network accessline 564
- **Visual coverage** — pixel-diff regressions across stories ([Chromatic](https://www.chromatic.com/), Percy, Applitools, Playwright `toHaveScreenshot`). Coverage element = component-state visual baseline. - Network accessline 574
- **DO-178C** — RTCA; overview: <https://www.consunova.com/do178c-info.html>; LDRA structural coverage analysis: <https://ldra.com/ldra-blog/do-178c-structural-coverage-analysis/>. - Network accessline 575
- **ISO 26262** — Road vehicles functional safety; Parasoft summary: <https://www.parasoft.com/learning-center/iso-26262/code-coverage/>; Verifysoft: <https://www.verifysoft.com/en_ISO_26262_Road_Vehicles_Functional_Safety.html>. - Network accessline 576
- **IEC 62304** — Medical device software lifecycle; <https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide>. - Network accessline 577
- **MISRA C / C++** — <https://www.misra.org.uk/>. - Network accessline 578
- **ISO/IEC/IEEE 29119** — Software testing process; <https://en.wikipedia.org/wiki/ISO/IEC_29119>; ISTQB-to-29119 mapping: <https://www.rcolomo.com/papers/326.pdf>. - Network accessline 579
- **ISTQB Foundation Level** — RTM glossary entry: <https://istqb-glossary.page/traceability-matrix/>; BVA white paper: <https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf>. - Network accessline 583
- LDRA MC/DC capability: <https://ldra.com/capabilities/mc-dc/>. - Network accessline 584
- Wikipedia MC/DC: <https://en.wikipedia.org/wiki/Modified_condition/decision_coverage>. - Network accessline 585
- Qt Coco MC/DC: <https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc>. - Network accessline 586
- Cyclomatic complexity: <https://en.wikipedia.org/wiki/Cyclomatic_complexity>. - Network accessline 590
- Istanbul: <https://istanbul.js.org/>. - Network accessline 591
- JaCoCo: <https://www.eclemma.org/jacoco/>. - Network accessline 592
- Coverage.py: <https://coverage.readthedocs.io/>. - Network accessline 593
- llvm-cov: <https://llvm.org/docs/CommandGuide/llvm-cov.html>. - Network accessline 594
- Go coverage: <https://go.dev/doc/build-cover>. - Network accessline 595
- Coverlet: <https://github.com/coverlet-coverage/coverlet>; NDepend guide (OpenCover deprecation notice): <https://blog.ndepend.com/guide-code-coverage-tools/>. - Network accessline 596
- SimpleCov: <https://github.com/simplecov-ruby/simplecov>. - Network accessline 600
- Stryker (JS / .NET / Scala): <https://stryker-mutator.io/>; config: <https://stryker-mutator.io/docs/stryker-js/configuration/>; mutant states: <https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/>; equiva - Network accessline 601
- Microsoft Learn on Stryker .NET: <https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing>. - Network accessline 602
- PIT (Pitest): <https://pitest.org/>. - Network accessline 603
- mutmut: <https://mutmut.readthedocs.io/>; Cosmic Ray: <https://cosmic-ray.readthedocs.io/>. - Network accessline 604
- go-mutesting: <https://github.com/avito-tech/go-mutesting>. - Network accessline 605
- Infection (PHP): <https://infection.github.io/>. - Network accessline 606
- Mull (LLVM): <https://github.com/mull-project/mull>. - Network accessline 607
- cargo-mutants (Rust): <https://mutants.rs/>. - Network accessline 608
- Mutant (Ruby): <https://github.com/mbj/mutant>. - Network accessline 609
- Mutation in CI (research): <https://greg4cr.github.io/pdf/23mutationci.pdf>. - Network accessline 613
- Cucumber: <https://cucumber.io/>; behave: <https://behave.readthedocs.io/>; Reqnroll (active SpecFlow fork): <https://reqnroll.net/>. - Network accessline 614
- BDD Cardinal Rule — Automation Panda: <https://automationpanda.com/bdd/>. - Network accessline 618
- Pact: <https://docs.pact.io/>; Pactflow CDC explainer: <https://pactflow.io/what-is-consumer-driven-contract-testing/>; Pact vs OpenAPI: <https://www.speakeasy.com/blog/pact-vs-openapi>; bi-directional contract testing: <https://pactflow. - Network accessline 619
- Spring Cloud Contract: <https://spring.io/projects/spring-cloud-contract/>. - Network accessline 620
- Specmatic: <https://specmatic.io/>. - Network accessline 621
- Schemathesis: <https://schemathesis.readthedocs.io/>. - Network accessline 622
- Dredd: <https://dredd.org/>. - Network accessline 626
- PICT: <https://github.com/microsoft/pict>. - Network accessline 627
- NIST ACTS: <https://csrc.nist.gov/projects/automated-combinatorial-testing-for-software>. - Network accessline 628
- All-pairs testing overview: <https://en.wikipedia.org/wiki/All-pairs_testing>. - Network accessline 629
- State transition testing (ISTQB-aligned): <https://www.leadwithskills.com/blogs/state-transition-testing-behavior-based-systems-istqb>. - Network accessline 630
- Playwright trace viewer: <https://playwright.dev/docs/trace-viewer>. - Network accessline 631
- Storybook Test: <https://storybook.js.org/docs/writing-tests>; Chromatic: <https://www.chromatic.com/>. - Network accessline 635
- "The Fallacy of the 100% Code Coverage" — Thierry de Pauw: <https://thinkinglabs.io/articles/2022/03/19/the-fallacy-of-the-100-code-coverage.html>. - Network accessline 636
- "Code Coverage Targets — Recipe for Disaster" — Optivem Journal: <https://journal.optivem.com/p/code-coverage-targets-recipe-for-disaster>. - Network accessline 637
- "Is 70/80/90/100% coverage good enough?" — Qt: <https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough>. - Network accessline 638
- "AI-Generated Tests Give False Confidence" — CodeIntelligently: <https://codeintelligently.com/blog/ai-generated-tests-false-confidence>.
antigravity/skills/test-prompt/SKILL.md
antigravity/skills/thought-based-reasoning/SKILL.md
- Network accessline 642
1. Wei, J. et al. (2022). "Chain of Thought Prompting Elicits Reasoning in Large Language Models." [arXiv:2201.11903](https://arxiv.org/abs/2201.11903) - Network accessline 644
2. Kojima, T. et al. (2022). "Large Language Models are Zero-Shot Reasoners." [arXiv:2205.11916](https://arxiv.org/abs/2205.11916) - Network accessline 646
3. Wang, X. et al. (2022). "Self-Consistency Improves Chain of Thought Reasoning in Language Models." [arXiv:2203.11171](https://arxiv.org/abs/2203.11171) - Network accessline 648
4. Yao, S. et al. (2023). "Tree of Thoughts: Deliberate Problem Solving with Large Language Models." [arXiv:2305.10601](https://arxiv.org/abs/2305.10601) - Network accessline 650
5. Zhou, D. et al. (2022). "Least-to-Most Prompting Enables Complex Reasoning in Large Language Models." [arXiv:2205.10625](https://arxiv.org/abs/2205.10625) - Network accessline 652
6. Yao, S. et al. (2022). "ReAct: Synergizing Reasoning and Acting in Language Models." [arXiv:2210.03629](https://arxiv.org/abs/2210.03629) - Network accessline 654
7. Gao, L. et al. (2022). "PAL: Program-aided Language Models." [arXiv:2211.10435](https://arxiv.org/abs/2211.10435) - Network accessline 656
8. Zhang, Z. et al. (2022). "Automatic Chain of Thought Prompting in Large Language Models." [arXiv:2210.03493](https://arxiv.org/abs/2210.03493) - Network accessline 658
9. Shinn, N. et al. (2023). "Reflexion: Language Agents with Verbal Reinforcement Learning." [arXiv:2303.11366](https://arxiv.org/abs/2303.11366)
plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md
- Network accessline 136
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and - Network accessline 140
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like refe - Network accessline 806
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instr
plugins/customaize-agent/skills/create-hook/SKILL.md
- Network accessline 183
_Complete templates available at: <https://docs.claude.com/en/docs/claude-code/hooks#examples>_ - Network accessline 187
**📖 Official Docs**: <https://docs.claude.com/en/docs/claude-code/hooks.md> - Network accessline 224
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 225
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 226
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 259
<Tabs> <Tab title="macOS"> Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 261
Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 376
Automatically run [Prettier](https://prettier.io/) on every file Claude edits, so formatting stays consistent without manual intervention. - Network accessline 378
This hook uses the `PostToolUse` event with an `Edit|Write` matcher, so it runs only after file-editing tools. The command extracts the edited file path with [`jq`](https://jqlang.github.io/jq/) and passes it to Prettier. Add this to `.clau - Network accessline 398
<Note> The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Network accessline 399
The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Access to secretsline 419
[Credential-related source omitted] - Dangerous shell operationline 680
"command": "rm -f /tmp/claude-scratch-*.txt" - Network accessline 855
- [Hooks reference](/en/hooks): full event schemas, JSON output format, async hooks, and MCP tool hooks - [Security considerations](/en/hooks#security-considerations): review before deploying hooks in shared or production environments - [Ba - Network accessline 857
- [Bash command validator example](https://github.com/anthropics/claude-code/blob/main/examples/hooks/bash_command_validator_example.py): complete reference implementation - Network accessline 861
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 862
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 863
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 880
<div style={{maxWidth: "500px", margin: "0 auto"}}> <Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hoo - Network accessline 881
<Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from - Network accessline 882
<img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStar - Dangerous shell operationline 925
The script reads the JSON input from stdin, extracts the command, and returns a `permissionDecision` of `"deny"` if it contains `rm -rf`: - Dangerous shell operationline 932
if echo "$COMMAND" | grep -q 'rm -rf'; then - Dangerous shell operationline 945
Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens: - Network accessline 947
<Frame> <img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher check - Network accessline 948
<img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash - Dangerous shell operationline 956
{ "tool_name": "Bash", "tool_input": { "command": "rm -rf /tmp/build" }, ... } - Dangerous shell operationline 965
The script extracts `"rm -rf /tmp/build"` from the input and finds `rm -rf`, so it prints a decision to stdout: - Dangerous shell operationline 1293
echo "Blocked: rm commands are not allowed" >&2 - Network accessline 1405
For extended examples including Bash command validation, prompt filtering, and auto-approval scripts, see [What you can automate](/en/hooks-guide#what-you-can-automate) in the guide and the [Bash command validator reference implementation]( - Network accessline 1635
| Field | Type | Example | Description | | :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | - Network accessline 1636
| :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | URL to fetch content from | | `prompt` | string | `"Extract the API endpoints"` | - Network accessline 1637
| `url` | string | `"https://example.com/api"` | URL to fetch content from | - Dangerous shell operationline 1710
"command": "rm -rf node_modules",
plugins/customaize-agent/skills/create-rule/SKILL.md
- Network accessline 400
- [Flattening Arrow Code](https://blog.codinghorror.com/flattening-arrow-code/)
plugins/customaize-agent/skills/create-skill/SKILL.md
- Network accessline 388
See [graphviz-conventions.dot](https://github.com/obra/superpowers/blob/main/skills/writing-skills/graphviz-conventions.dot) for graphviz style rules.
plugins/customaize-agent/skills/test-prompt/SKILL.md
plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md
- Network accessline 642
1. Wei, J. et al. (2022). "Chain of Thought Prompting Elicits Reasoning in Large Language Models." [arXiv:2201.11903](https://arxiv.org/abs/2201.11903) - Network accessline 644
2. Kojima, T. et al. (2022). "Large Language Models are Zero-Shot Reasoners." [arXiv:2205.11916](https://arxiv.org/abs/2205.11916) - Network accessline 646
3. Wang, X. et al. (2022). "Self-Consistency Improves Chain of Thought Reasoning in Language Models." [arXiv:2203.11171](https://arxiv.org/abs/2203.11171) - Network accessline 648
4. Yao, S. et al. (2023). "Tree of Thoughts: Deliberate Problem Solving with Large Language Models." [arXiv:2305.10601](https://arxiv.org/abs/2305.10601) - Network accessline 650
5. Zhou, D. et al. (2022). "Least-to-Most Prompting Enables Complex Reasoning in Large Language Models." [arXiv:2205.10625](https://arxiv.org/abs/2205.10625) - Network accessline 652
6. Yao, S. et al. (2022). "ReAct: Synergizing Reasoning and Acting in Language Models." [arXiv:2210.03629](https://arxiv.org/abs/2210.03629) - Network accessline 654
7. Gao, L. et al. (2022). "PAL: Program-aided Language Models." [arXiv:2211.10435](https://arxiv.org/abs/2211.10435) - Network accessline 656
8. Zhang, Z. et al. (2022). "Automatic Chain of Thought Prompting in Large Language Models." [arXiv:2210.03493](https://arxiv.org/abs/2210.03493) - Network accessline 658
9. Shinn, N. et al. (2023). "Reflexion: Language Agents with Verbal Reinforcement Learning." [arXiv:2303.11366](https://arxiv.org/abs/2303.11366)
plugins/fpf/skills/propose-hypotheses/SKILL.md
- Broad permissionsline 1
Task, Read, Write, Bash, AskUserQuestion
plugins/fpf/skills/reset/SKILL.md
- Dangerous shell operationline 85
rm -rf .fpf/knowledge/L0/*.md - Dangerous shell operationline 86
rm -rf .fpf/knowledge/L1/*.md - Dangerous shell operationline 87
rm -rf .fpf/knowledge/L2/*.md - Dangerous shell operationline 88
rm -rf .fpf/knowledge/invalid/*.md - Dangerous shell operationline 89
rm -rf .fpf/evidence/*.md - Dangerous shell operationline 90
rm -rf .fpf/decisions/*.md
plugins/git/skills/attach-review-to-pr/SKILL.md
- Network accessline 109
"line": 26, "body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 110
"body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", "created_at": "2025-11-16T22:40:46Z" - Network accessline 111
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 195
"id": 3470546747, "state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 196
"state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", "submitted_at": "2025-11-16T22:42:43Z", - Network accessline 197
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 331
\`\`\`typescript async function getData() { const result = await fetch(url); - Network accessline 332
async function getData() { const result = await fetch(url); return result.json(); - Network accessline 333
const result = await fetch(url); - Network accessline 467
- [GitHub API: Pull Request Review Comments](https://docs.github.com/rest/pulls/comments) - Network accessline 468
- [GitHub API: Pull Request Reviews](https://docs.github.com/rest/pulls/reviews) - Network accessline 469
- [GitHub CLI Manual](https://cli.github.com/manual/) - Network accessline 479
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/comments` - Network accessline 495
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/reviews`
plugins/git/skills/commit/SKILL.md
- Broad permissionsline 1
Bash(git status:*), Bash(git add:*), Bash(git diff:*), Bash(git commit:*), Bash(git config:*), Bash(git branch:*), Bash(git checkout:*), Bash(pnpm lint:*), Bash(npm run lint:*), Bash(yarn lint:*), Bash(bun lint:*)
plugins/git/skills/create-pr/SKILL.md
- Broad permissionsline 1
Bash(gh pr:*), Bash(gh auth:*), Bash(git status:*), Bash(git push:*), Bash(git branch:*), Skill(git:commit) - Network accessline 27
# Linux # Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 28
# Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 141
- [PR Template](.github/pull_request_template.md) - [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 142
- [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 143
- [GitHub CLI documentation](https://cli.github.com/manual/)
plugins/git/skills/git-notes/SKILL.md
plugins/git/skills/git-worktrees/SKILL.md
plugins/git/skills/load-pr-comments/SKILL.md
- Network accessline 33
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 34
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 35
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 40
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch.
plugins/git/skills/resolve-fixed-pr-comments/SKILL.md
- Network accessline 69
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 70
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 71
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 76
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch. - Network accessline 227
**Input:** `resolve-fixed-pr-comments https://github.com/acme/app/pull/7`
plugins/kaizen/skills/analyse/SKILL.md
plugins/kaizen/skills/kaizen/SKILL.md
- Access to secretsline 304
[Credential-related source omitted] - Access to secretsline 306
[Credential-related source omitted] - Network accessline 372
class UserAPIClient { async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); - Network accessline 373
async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); } - Network accessline 374
return this.fetch(`/users/${id}`); - Network accessline 379
class OrderAPIClient { async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); - Network accessline 380
async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); } - Network accessline 381
return this.fetch(`/orders/${id}`); - Network accessline 446
* @example * const result = await retry( * () => fetch('https://api.example.com/data'), - Network accessline 447
* const result = await retry( * () => fetch('https://api.example.com/data'), * { maxAttempts: 3, baseDelay: 1000 } - Network accessline 448
* () => fetch('https://api.example.com/data'),
plugins/mcp/skills/build-mcp/SKILL.md
- Network accessline 64
Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt` - Network accessline 76
- **Python SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 81
- **TypeScript SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - Network accessline 321
- **MCP Protocol**: Fetch from `https://modelcontextprotocol.io/llms-full.txt` - Complete MCP specification - Network accessline 332
- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 333
- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
plugins/mcp/skills/setup-arxiv-mcp/SKILL.md
plugins/mcp/skills/setup-codemap-cli/SKILL.md
plugins/mcp/skills/setup-context7-mcp/SKILL.md
- Network accessline 37
if no, load <https://raw.githubusercontent.com/upstash/context7/refs/heads/master/README.md> file and guide user through setup process that applicable to agent/operation system.
plugins/mcp/skills/setup-serena-mcp/SKILL.md
- Network accessline 43
- Load <https://raw.githubusercontent.com/oraios/serena/refs/heads/main/README.md> to understand what Serena is and its capabilities - Network accessline 44
- Load <https://oraios.github.io/serena/02-usage/020_running.html> to learn how to run Serena - Network accessline 45
- Load <https://oraios.github.io/serena/02-usage/030_clients.html> to learn how to configure your MCP client - Network accessline 46
- Load <https://oraios.github.io/serena/02-usage/040_workflow.html> to learn how to setup Serena for your project
plugins/reflexion/hooks/src/index.ts
plugins/reflexion/skills/memorize/SKILL.md
- Network accessline 297
- This command is the counterpart to `/reflexion:reflect`: reflect → curate → memorize. - The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/25 - Network accessline 298
- The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/2510.04618`).
plugins/review/skills/review-pr/SKILL.md
- Network accessline 267
- Use full git sha + line range, eg. `https://github.com/owner/repo/blob/1d54823877c4de72b2316a64032a54afc404e619/README.md#L13-L17`
plugins/sdd/scripts/create-folders.sh
plugins/sdd/scripts/create-scratchpad.sh
plugins/tdd/skills/design-testing-strategy/SKILL.md
- Network accessline 27
| # | Type | ON when | OFF when | Source | |---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with b - Network accessline 28
|---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or - Network accessline 29
| 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or user-visible behavior | [Pragmatic Program - Network accessline 30
| 1 | **Unit** | Code contains any logic: branches, loops, conditionals, computation, transformation, parsing, validation, formatting | Pure declarative wiring (DI registration, route table) with no behavior | [Test Pyramid (Vocke)](https:/ - Network accessline 31
| 2 | **Integration** | Boundary crossing: HTTP call, DB query, external SDK, message queue, filesystem I/O, OR collaboration with >=2 distinct collaborators where unit doubles distort behavior | Pure function with no I/O and 0-1 stable col - Network accessline 32
| 3 | **Component or E2E** | UI surface AND criticality >= MEDIUM-HIGH AND user-facing critical path (signup, checkout, auth, payment, primary CTA) | Internal admin-only screens, dev tooling, or non-critical UI | [Test Pyramid top](https:// - Network accessline 33
| 4 | **Contract** | Public API consumed by >=1 distinct clients (mobile + web, multiple internal services, external partners) AND independent deploy cadence | API where consumer and provider deploy together | [Pact / CDC](https://docs.pact - Network accessline 34
| 5 | **Smoke** | Deployable surface (web app, API, service) AND a deploy/CI pipeline exists where post-deploy validation is meaningful | Library, internal helper, or no deploy pipeline | [Google "What Makes a Good End-to-End Test"](https:/ - Network accessline 35
| 6 | **Property-Based** | Input domain is large or unbounded (numeric ranges, strings, lists, parsers, serializers, encoders, math) AND invariants are stable (round-trip, idempotency, monotonicity, commutativity) AND criticality >= MEDIUM- - Network accessline 64
| Type | Use when | Do NOT use when | Frameworks | Typical dependencies | Google Size | |------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, determini - Network accessline 65
|------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go te - Network accessline 66
| **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go test, JUnit, xUnit, RSpec | None (or in-memory fakes) | [Small](https://testing.googleblog - Network accessline 67
| **integration** | Boundary crossing (DB, HTTP, queue, FS); multiple collaborators where mocking distorts behavior | Pure function with no boundary | vitest, jest, pytest, go test, JUnit + [Testcontainers](https://testcontainers.com/), sup - Network accessline 68
| **component** | UI rendering + interaction within a single component, no full app context | Backend-only logic; multi-page user flow | React Testing Library, Vue Test Utils, Angular TestBed, Storybook interaction tests | jsdom or happy-do - Network accessline 69
| **e2e** | Full user path through running app: real browser, real backend, real DB | Internal helper, single component, non-critical UI | [Playwright](https://playwright.dev/), [Cypress](https://www.cypress.io/), Selenium | Real running ap - Network accessline 70
| **smoke** | Post-deploy go/no-go: hit / health, key endpoints respond, login works | Detailed correctness; smoke is shallow by design | Playwright (1-3 critical paths), HTTP probe scripts, k6 minimal scenarios | Real deployed environment - Network accessline 71
| **contract** | Public API consumed by 2+ distinct clients with independent deploy cadence | Single-consumer internal API; provider and consumer deploy together | [Pact](https://docs.pact.io/), Spring Cloud Contract, OpenAPI schema validat - Network accessline 72
| **property-based** | Large/unbounded input domain with stable invariants (parser, serializer, encoder, math) | Small finite input space; unstable invariants | [Hypothesis](https://hypothesis.works/) (Python), fast-check (TS), QuickCheck ( - Network accessline 76
[Google Test Sizes (Bland)](https://mike-bland.com/2011/11/01/small-medium-large.html) and [SWE at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html) classify tests by **resources** (size), independent of **scope** (paths co - Network accessline 89
| Dimension | [Playwright](https://playwright.dev/) | [Cypress](https://www.cypress.io/) | - Network accessline 101
Use ISTQB Foundation Level black-box techniques to derive **what** to test inside each chosen test type. References: [ISTQB BVA white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf), [ASTQB black - Network accessline 168
When EP, BVA, or decision-table analysis yields **3+ cases with the same shape** (same setup, same assertion, only inputs and expected outputs differ — e.g., parsing valid/invalid date formats; computing tax across brackets; routing rules) - Network accessline 201
| Dependency style | Use when | Avoid when | Notes | |------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic - Network accessline 202
|------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker avail - Network accessline 203
| **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker available | Default for integration tests on Postgres / Re - Network accessline 215
Explicit "don't bother" rules. Skipping these is not laziness — it is risk-adjusted ROI per [ISO/IEC/IEEE 29119 risk-based testing](https://en.wikipedia.org/wiki/ISO/IEC_29119) and [Risk-Based Testing](https://www.softwaretestinghelp.com/ri - Network accessline 223
| **No component test for static markup** | If the component has no state, no events, no conditional rendering, a snapshot is enough — or skip entirely. | | **No unit test for declarative wiring** | DI bindings, route registration, schema d - Network accessline 224
| **No unit test for declarative wiring** | DI bindings, route registration, schema declarations: assert at integration level (does the route serve the right handler) instead. | | **No e2e for things integration covers reliably** | Per [Goo - Network accessline 225
| **No e2e for things integration covers reliably** | Per [Google e2e principles](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html): the smaller the test you can use to cover a behavior, the better. e2e is t - Network accessline 226
| **No tests for spike/throwaway code** | Per [Beck TDD](https://www.oreilly.com/library/view/test-driven-development/0321146530/): if the artifact will be deleted within hours, document the exception with the human partner. Then write test - Network accessline 335
- `type` matches one of `selected_types[*].type` from the matrix - `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange - Network accessline 336
- `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange-act-assert/) - Network accessline 369
1. **Test Pyramid** — Mike Cohn (2009, *Succeeding with Agile*) + Ham Vocke, [The Practical Test Pyramid](https://martinfowler.com/articles/practical-test-pyramid.html), martinfowler.com. - Network accessline 370
2. **Testing Trophy** — Kent C. Dodds (2018), [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) and [Write Tests](https://kentcdodds.com/blog/write-tests). - Network accessline 371
3. **Google Test Sizes** — Mike Bland (2011), [Small / Medium / Large](https://mike-bland.com/2011/11/01/small-medium-large.html); [Software Engineering at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html); [Test Sizes (Goo - Network accessline 372
4. **Google Testing on the Toilet** — [What Makes a Good End-to-End Test](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html), [Testing UI Logic - Follow the User](https://testing.googleblog.com/2020/10/testin - Network accessline 373
5. **ISTQB Foundation Level** — Black-box techniques: [Boundary Value Analysis white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf); [ASTQB Black-Box Techniques](https://astqb.org/4-2-black-box- - Network accessline 374
6. **ISO/IEC/IEEE 29119** — Risk-based test process standard. [Wikipedia overview](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 375
7. **Kent Beck — *Test Driven Development: By Example*** (Addison-Wesley, 2002). [Publisher page](https://www.oreilly.com/library/view/test-driven-development/0321146530/). ISBN 978-0321146533. - Network accessline 376
8. **The Pragmatic Programmer (20th Anniversary Edition)** — Hunt & Thomas (2019). [pragprog.com](https://pragprog.com/titles/tpp20/the-pragmatic-programmer-20th-anniversary-edition/). - Network accessline 377
9. **AAA pattern** — Bill Wake (2001), [3A — Arrange, Act, Assert](https://xp123.com/articles/3a-arrange-act-assert/). **Given-When-Then** — Dan North, [Introducing BDD](https://dannorth.net/introducing-bdd/). - Network accessline 378
10. **Property-based testing** — [Hypothesis: What is property-based testing?](https://hypothesis.works/articles/what-is-property-based-testing/); QuickCheck (Haskell), fast-check (TS). - Network accessline 379
11. **Contract testing / Consumer-Driven Contracts** — [Pact docs](https://docs.pact.io/); [Pactflow CDC explainer](https://pactflow.io/what-is-consumer-driven-contract-testing/). - Network accessline 380
12. **Testcontainers** — [testcontainers.com](https://testcontainers.com/). - Network accessline 381
13. **Table-driven tests** — Dave Cheney, [Prefer table-driven tests](https://dave.cheney.net/2019/05/07/prefer-table-driven-tests); [Go wiki: TableDrivenTests](https://go.dev/wiki/TableDrivenTests). - Network accessline 382
14. **Risk-based testing** — [Risk Management During Test Planning (softwaretestinghelp.com)](https://www.softwaretestinghelp.com/risk-management-during-test-planning-risk-based-testing/). - Network accessline 419
|------|----------|--------| | 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 420
| 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic - Network accessline 421
| 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 422
| 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic: no integration for pure functions](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) | - Network accessline 424
| 4 Contract | OFF | Not a public API | | 5 Smoke | OFF | Not deployable | | 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypoth - Network accessline 426
| 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypothesis.works/articles/what-is-property-based-testing/). Promote at MEDIUM-HIG - Network accessline 521
|------|----------|--------| | 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 522
| 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | **ON** | Boundary crossin - Network accessline 523
| 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 524
| 2 Integration | **ON** | Boundary crossing: HTTP, Postgres, Kafka — [Testing Trophy](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) ROI sweet spot | - Network accessline 525
| 3 Component/E2E | OFF (here) | No UI in this artifact; UI lives in mobile + web repos and tests itself | | 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is - Network accessline 526
| 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is-consumer-driven-contract-testing/) | - Network accessline 527
| 5 Smoke | **ON** | Deployable HTTP service; post-deploy probe of `/users` registration is meaningful — [Google e2e](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html) | - Network accessline 528
| 6 Property-Based | OFF | Input domain (email, password, age) is constrained and well-covered by EP+BVA at unit; criticality is MEDIUM-HIGH but Gate 6 OFF on bounded inputs — [Skip Heuristic](https://hypothesis.works/articles/what-is-prope - Network accessline 645
| 1 Unit | **ON** | Validation helpers (`validateEmail`, `passwordsMatch`, `parseAge`) are pure logic | | 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integratio - Network accessline 646
| 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integration is owned by `POST /users` (Example B) | | 3 Component/E2E | **ON** (component) + **ON** (e2e for the r - Network accessline 647
| 3 Component/E2E | **ON** (component) + **ON** (e2e for the registration path) | UI surface, criticality MEDIUM-HIGH, user-facing critical path — [Test Pyramid top](https://martinfowler.com/articles/practical-test-pyramid.html) + [Follow t - Network accessline 749
- [ ] Each AC is referenced by at least one test case. - [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/ht - Network accessline 750
- [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html). - [ ] Test names contain no "and" (per [ - Network accessline 751
- [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html).
plugins/tdd/skills/test-coverage/SKILL.md
- Network accessline 39
Coverage is *necessary-but-not-sufficient*. A test can execute a line without asserting anything meaningful; 100% line coverage is routinely achievable with zero assertions ([thinkinglabs.io](https://thinkinglabs.io/articles/2022/03/19/the- - Network accessline 44
- **NOT a measure of correctness.** Coverage proves the test ran, not that it would have failed on a bug. - **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitut - Network accessline 45
- **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - - Network accessline 46
- **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 72
- **Definition.** Percentage of source-code lines (or statements) executed at least once. - **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were t - Network accessline 73
- **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were tested. Multiple statements on one line distort the metric ([Metridev](https://www.metridev - Network accessline 76
| Ecosystem | Tool | |-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 77
|-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | | Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 78
| JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 79
| Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 80
| JVM | [JaCoCo](https://www.eclemma.org/jacoco/) — bytecode instrumentation, industry standard | - Network accessline 81
| C/C++ | `gcov` / `lcov` / `gcovr`, [llvm-cov](https://llvm.org/docs/CommandGuide/llvm-cov.html) | - Network accessline 82
| Go | `go test -cover`, `go tool cover` ([build-cover](https://go.dev/doc/build-cover) added integration-test mode in Go 1.20) | - Network accessline 83
| .NET | [Coverlet](https://github.com/coverlet-coverage/coverlet) (open-source default), [JetBrains dotCover](https://www.jetbrains.com/dotcover/), AltCover. **OpenCover is in maintenance mode — prefer Coverlet / dotCover / AltCover** ([ND - Network accessline 84
| Ruby | [SimpleCov](https://github.com/simplecov-ruby/simplecov) | - Network accessline 89
- **When to use vs skip.** Always-on; cost is near-zero (a CI flag). Never use as a quality goal in itself. - **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blo - Network accessline 90
- **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough)). Apply only with the risk caveat (see Risk-Based Interpreta - Network accessline 95
- **Definition.** Percentage of decision branches (true/false outcomes of `if`, `while`, `for`, `?:`, `switch` cases) executed. - **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, - Network accessline 96
- **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, B=false`). Order of evaluation. Loop iteration counts. Assertion strength. - **Typical tools.** Same as line coverage; enable w - Network accessline 97
- **Typical tools.** Same as line coverage; enable with `--branch` (coverage.py), branch mode (Istanbul is branch-aware by default), JaCoCo reports branches natively. Strictly stronger than line/statement coverage ([Graph AI](https://www.gr - Network accessline 98
- **When to use vs skip.** Default for any non-trivial logic. Prefer branch over line as the primary structural metric. - **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](htt - Network accessline 99
- **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](https://www.leadwithskills.com/blogs/test-coverage-metrics-lines-branches-conditions-paths)) — always paired with the risk - Network accessline 100
- **Cost-benefit ROI.** High — best single structural metric for general-purpose code ([LinearB](https://linearb.io/blog/what-is-branch-coverage)). - Network accessline 120
- **Definition** (per [Wikipedia](https://en.wikipedia.org/wiki/Modified_condition/decision_coverage)): - Network accessline 126
For `n` conditions, MC/DC is achievable with `n+1` to `2n` tests via independence pairs — vastly cheaper than the `2^n` of exhaustive multiple-condition coverage ([LDRA](https://ldra.com/capabilities/mc-dc/)). - Network accessline 128
- **What it does NOT measure.** Loop iteration counts, data values, integration paths, assertion strength. - **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/ - Network accessline 129
- **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc), Parasoft C/C++test. Mostly commercial — open-source MC/ - Network accessline 130
- **When to use vs skip.** When mandated by a standard (DO-178C DAL A, ISO 26262 ASIL D, IEC 62304 Class C high-risk modules, EN 50128 SIL 4, IEC 61508 SIL 4). Outside regulated domains, branch coverage + mutation testing covers the same in - Network accessline 131
- **Targets / thresholds & pitfalls.** 100% by definition in regulated domains. Short-circuit evaluation in C-like languages can make some independence pairs unreachable; compiler optimizations can collapse conditions, so coverage builds mu - Network accessline 153
- **Definition.** Percentage of unique linearly-independent paths through a function. Bounded by cyclomatic complexity `V(G) = decisions + 1` ([Cyclomatic complexity](https://en.wikipedia.org/wiki/Cyclomatic_complexity)). - Network accessline 174
Mutation testing introduces small, syntactic modifications ("mutants") to the source and re-runs the existing test suite against each mutant. If at least one test **fails** for a given mutant, the mutant is **killed** (the suite detected th - Network accessline 186
### Mutant states ([Stryker docs](https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/)) - Network accessline 202
- **Semantic correctness** of assertions — a wrong-but-strict assertion still kills mutants. - **Boundary data values** — operator mutants approximate this but do not replace BVA. - **Equivalent mutants** — variants that produce identical o - Network accessline 204
- **Equivalent mutants** — variants that produce identical observable behavior. Detection is undecidable in general; manual review is the only certain method. Modern tools (Stryker TypeScript Checker, PIT with Major) reduce these heuristica - Network accessline 208
| Ecosystem | Tool | |-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 209
|-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | | .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documen - Network accessline 210
| JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 211
| .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documented in [Microsoft Learn](https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing) | - Network accessline 212
| Java / JVM | [PIT (Pitest)](https://pitest.org/) — reference standard for JVM; Major Mutator for research | - Network accessline 213
| Python | [mutmut](https://mutmut.readthedocs.io/), [Cosmic Ray](https://cosmic-ray.readthedocs.io/), [MutPy](https://github.com/mutpy/mutpy) | - Network accessline 214
| Go | [go-mutesting](https://github.com/avito-tech/go-mutesting), [ooze](https://github.com/gtramontina/ooze) | - Network accessline 215
| PHP | [Infection](https://infection.github.io/) | - Network accessline 216
| Ruby | [mutant](https://github.com/mbj/mutant) | - Network accessline 217
| Rust | [cargo-mutants](https://mutants.rs/) | - Network accessline 218
| C / C++ | [Mull](https://github.com/mull-project/mull) — LLVM-based | - Network accessline 219
| Scala | [Stryker4s](https://stryker-mutator.io/docs/stryker4s/introduction/) | - Network accessline 239
Stryker defaults ([config](https://stryker-mutator.io/docs/stryker-js/configuration/)): `high: 80`, `low: 60`, `break: null`. Set `break` to fail the build below a floor. Apply with the risk caveat: 60–80% on a mature unit suite over pure-l - Network accessline 243
- **Cost.** CPU-quadratic-ish. A 60-second suite generating 1,000 mutants is up to 1,000 × 60s without optimization. Modern tools mitigate via incremental analysis, per-mutant test selection, and parallel runners. - **Benefit.** Catches *mi - Network accessline 244
- **Benefit.** Catches *missing assertions* and *over-mocked* tests that structural coverage cannot detect. It is the **only practical coverage technique that scores assertion strength** — the chief failure mode of "100% coverage with no as - Network accessline 245
- **CI pattern.** Incremental mutation on PR diff; nightly full run on critical modules ([oneuptime](https://oneuptime.com/blog/post/2026-01-24-mutation-testing/view); see also research roundup at [greg4cr.github.io](https://greg4cr.github. - Network accessline 266
The foundational artifact is the **Requirements Traceability Matrix (RTM)** — a two-dimensional table correlating requirements to test cases ([ISTQB Glossary](https://istqb-glossary.page/traceability-matrix/)). Enables: - Network accessline 288
In BDD ecosystems, Gherkin `Scenario:` blocks are the unit of acceptance coverage; each AC ideally maps to one or more scenarios (the Cardinal Rule of BDD: one scenario, one behavior — [Automation Panda](https://automationpanda.com/bdd/)). - Network accessline 290
Foundational standards: **ISTQB Foundation Level** treats RTM as a foundational artifact for systematic test design. **[ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)** parts 1–5 require traceability at the test-plan, test - Network accessline 320
- **Definition.** `(unique_endpoint_method_pairs_hit) / (total_documented_endpoint_method_pairs)`. Often broken down further by `(endpoint, method, status_code)` triples. - **What it does NOT measure.** Whether responses are *correct* — onl - Network accessline 321
- **What it does NOT measure.** Whether responses are *correct* — only that endpoints were hit. The combinatorial inputs leading to each status code. - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL - Network accessline 322
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL-driven test generator that reports endpoint and status-code coverage), [Dredd](https://dredd.org/) (validates HTTP API against API Blueprint / OpenAP - Network accessline 329
- **Definition.** Percentage of consumer-side **interactions** (request/response examples) that the provider has verified. Consumer generates Pact files (JSON contracts) capturing specific interactions; provider runs verification suites aga - Network accessline 330
- **What it does NOT measure.** Provider behavior on inputs no consumer ever sends (negative space). Performance, security, or schema completeness. - **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow - Network accessline 331
- **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow](https://pactflow.io/what-is-consumer-driven-contract-testing/) for storage and verification reports. [Spring Cloud Contract](https://spring.io/pro - Network accessline 332
- **When to use vs skip.** Use when there are multiple independent consumers with independent deploy cadences (microservices, mobile + web sharing a backend). Skip for single-consumer APIs that deploy with the provider, or for library APIs. - Network accessline 333
- **Targets / thresholds & pitfalls.** "Schema valid" is weaker than "contract honored" — schema tells you what shapes are *legal*; contract tells you which fields and behaviors a consumer *actually depends on* ([Speakeasy: Pact vs OpenAPI] - Network accessline 338
- **Definition.** Percentage of schema fields, enum values, and `oneOf` / `anyOf` variants exercised across the test suite. - **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - - Network accessline 339
- **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits - Network accessline 340
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits coverage metrics over schema elements), [Dredd](https://dredd.org/) with hooks for field-level instrumentation, [S - Network accessline 360
- **Definition.** Coverage measured against **input partitions** rather than code. Each Equivalence Partition (EP) and Boundary Value Analysis (BVA) slot from ISTQB Foundation Level black-box techniques becomes a coverage element ([ISTQB BV - Network accessline 369
- **Definition.** **Pairwise (all-pairs)** testing requires that every pair of parameter values appears in at least one test case. Most multi-parameter defects manifest at the 2-way interaction level ([Wikipedia](https://en.wikipedia.org/wi - Network accessline 370
- **What it does NOT measure.** Three-way+ interactions (unless escalated to `t=3`); ordering effects in workflows. - **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports - Network accessline 371
- **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports constraints, weighting, seeding), AllPairs (Satisfice), [NIST ACTS](https://csrc.nist.gov/projects/automated-combina - Network accessline 387
- **Definition.** Percentage of declared transitions (and optionally forbidden transitions) in a state machine exercised by tests. - **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecu - Network accessline 388
- **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecutive transitions. *2-switch* — every triple. *Round-trip* — every cycle in the state graph ([Lead With Skills](https://www.leadwith - Network accessline 467
Coverage targets should be **proportional to risk** ([ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)). The same artifact at different criticalities should not have the same coverage gate. Use the table below as a starting - Network accessline 478
**Delta thresholds** ("must not drop more than X%") are generally safer than absolute floors — they protect against regression in testing discipline without rewarding gaming ([Optivem](https://journal.optivem.com/p/code-coverage-targets-rec - Network accessline 502
| Standard | Domain | Coverage requirement | |----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; St - Network accessline 503
|----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E - Network accessline 504
| **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E ([LDRA structural coverage](https://ldra.com/ - Network accessline 505
| **[ISO 26262](https://www.parasoft.com/learning-center/iso-26262/code-coverage/)** Part 6 Table 9 | Automotive | MC/DC highly recommended for ASIL D; branch for ASIL B–C; statement minimum for ASIL A ([Verifysoft](https://www.verifysoft.c - Network accessline 506
| **[IEC 62304](https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide)** | Medical | Coverage scales with safety class A → B → C; auditors expect MC/DC for Class C high-risk modules; MISRA C/C++ coding standards customar - Network accessline 507
| **[MISRA C / MISRA C++](https://www.misra.org.uk/)** | Embedded (cross-industry) | Coding-rule conformance is the primary signal; coverage is complementary; MC/DC expected for safety-critical components | - Network accessline 562
- **Playwright trace coverage** — Playwright records traces (DOM, network, console) per test; the [trace viewer](https://playwright.dev/docs/trace-viewer) makes UI coverage **auditable** in a way DOM-snapshot tests cannot. Trace artifacts g - Network accessline 563
- **Storybook coverage** — [Storybook Test](https://storybook.js.org/docs/writing-tests) reports which stories (component states) have an interaction test (`play` function) vs only a rendered snapshot. - Network accessline 564
- **Visual coverage** — pixel-diff regressions across stories ([Chromatic](https://www.chromatic.com/), Percy, Applitools, Playwright `toHaveScreenshot`). Coverage element = component-state visual baseline. - Network accessline 574
- **DO-178C** — RTCA; overview: <https://www.consunova.com/do178c-info.html>; LDRA structural coverage analysis: <https://ldra.com/ldra-blog/do-178c-structural-coverage-analysis/>. - Network accessline 575
- **ISO 26262** — Road vehicles functional safety; Parasoft summary: <https://www.parasoft.com/learning-center/iso-26262/code-coverage/>; Verifysoft: <https://www.verifysoft.com/en_ISO_26262_Road_Vehicles_Functional_Safety.html>. - Network accessline 576
- **IEC 62304** — Medical device software lifecycle; <https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide>. - Network accessline 577
- **MISRA C / C++** — <https://www.misra.org.uk/>. - Network accessline 578
- **ISO/IEC/IEEE 29119** — Software testing process; <https://en.wikipedia.org/wiki/ISO/IEC_29119>; ISTQB-to-29119 mapping: <https://www.rcolomo.com/papers/326.pdf>. - Network accessline 579
- **ISTQB Foundation Level** — RTM glossary entry: <https://istqb-glossary.page/traceability-matrix/>; BVA white paper: <https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf>. - Network accessline 583
- LDRA MC/DC capability: <https://ldra.com/capabilities/mc-dc/>. - Network accessline 584
- Wikipedia MC/DC: <https://en.wikipedia.org/wiki/Modified_condition/decision_coverage>. - Network accessline 585
- Qt Coco MC/DC: <https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc>. - Network accessline 586
- Cyclomatic complexity: <https://en.wikipedia.org/wiki/Cyclomatic_complexity>. - Network accessline 590
- Istanbul: <https://istanbul.js.org/>. - Network accessline 591
- JaCoCo: <https://www.eclemma.org/jacoco/>. - Network accessline 592
- Coverage.py: <https://coverage.readthedocs.io/>. - Network accessline 593
- llvm-cov: <https://llvm.org/docs/CommandGuide/llvm-cov.html>. - Network accessline 594
- Go coverage: <https://go.dev/doc/build-cover>. - Network accessline 595
- Coverlet: <https://github.com/coverlet-coverage/coverlet>; NDepend guide (OpenCover deprecation notice): <https://blog.ndepend.com/guide-code-coverage-tools/>. - Network accessline 596
- SimpleCov: <https://github.com/simplecov-ruby/simplecov>. - Network accessline 600
- Stryker (JS / .NET / Scala): <https://stryker-mutator.io/>; config: <https://stryker-mutator.io/docs/stryker-js/configuration/>; mutant states: <https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/>; equiva - Network accessline 601
- Microsoft Learn on Stryker .NET: <https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing>. - Network accessline 602
- PIT (Pitest): <https://pitest.org/>. - Network accessline 603
- mutmut: <https://mutmut.readthedocs.io/>; Cosmic Ray: <https://cosmic-ray.readthedocs.io/>. - Network accessline 604
- go-mutesting: <https://github.com/avito-tech/go-mutesting>. - Network accessline 605
- Infection (PHP): <https://infection.github.io/>. - Network accessline 606
- Mull (LLVM): <https://github.com/mull-project/mull>. - Network accessline 607
- cargo-mutants (Rust): <https://mutants.rs/>. - Network accessline 608
- Mutant (Ruby): <https://github.com/mbj/mutant>. - Network accessline 609
- Mutation in CI (research): <https://greg4cr.github.io/pdf/23mutationci.pdf>. - Network accessline 613
- Cucumber: <https://cucumber.io/>; behave: <https://behave.readthedocs.io/>; Reqnroll (active SpecFlow fork): <https://reqnroll.net/>. - Network accessline 614
- BDD Cardinal Rule — Automation Panda: <https://automationpanda.com/bdd/>. - Network accessline 618
- Pact: <https://docs.pact.io/>; Pactflow CDC explainer: <https://pactflow.io/what-is-consumer-driven-contract-testing/>; Pact vs OpenAPI: <https://www.speakeasy.com/blog/pact-vs-openapi>; bi-directional contract testing: <https://pactflow. - Network accessline 619
- Spring Cloud Contract: <https://spring.io/projects/spring-cloud-contract/>. - Network accessline 620
- Specmatic: <https://specmatic.io/>. - Network accessline 621
- Schemathesis: <https://schemathesis.readthedocs.io/>. - Network accessline 622
- Dredd: <https://dredd.org/>. - Network accessline 626
- PICT: <https://github.com/microsoft/pict>. - Network accessline 627
- NIST ACTS: <https://csrc.nist.gov/projects/automated-combinatorial-testing-for-software>. - Network accessline 628
- All-pairs testing overview: <https://en.wikipedia.org/wiki/All-pairs_testing>. - Network accessline 629
- State transition testing (ISTQB-aligned): <https://www.leadwithskills.com/blogs/state-transition-testing-behavior-based-systems-istqb>. - Network accessline 630
- Playwright trace viewer: <https://playwright.dev/docs/trace-viewer>. - Network accessline 631
- Storybook Test: <https://storybook.js.org/docs/writing-tests>; Chromatic: <https://www.chromatic.com/>. - Network accessline 635
- "The Fallacy of the 100% Code Coverage" — Thierry de Pauw: <https://thinkinglabs.io/articles/2022/03/19/the-fallacy-of-the-100-code-coverage.html>. - Network accessline 636
- "Code Coverage Targets — Recipe for Disaster" — Optivem Journal: <https://journal.optivem.com/p/code-coverage-targets-recipe-for-disaster>. - Network accessline 637
- "Is 70/80/90/100% coverage good enough?" — Qt: <https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough>. - Network accessline 638
- "AI-Generated Tests Give False Confidence" — CodeIntelligently: <https://codeintelligently.com/blog/ai-generated-tests-false-confidence>.
skills/analyse/SKILL.md
skills/apply-anthropic-skill-best-practices/SKILL.md
- Network accessline 135
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and - Network accessline 139
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like refe - Network accessline 805
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instr
skills/attach-review-to-pr/SKILL.md
- Network accessline 107
"line": 26, "body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 108
"body": "Consider adding error handling here...", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", "created_at": "2025-11-16T22:40:46Z" - Network accessline 109
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#discussion_r2532291222", - Network accessline 193
"id": 3470546747, "state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 194
"state": "COMMENTED", "html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", "submitted_at": "2025-11-16T22:42:43Z", - Network accessline 195
"html_url": "https://github.com/NeoLabHQ/learning-platform-app/pull/4#pullrequestreview-3470546747", - Network accessline 329
\`\`\`typescript async function getData() { const result = await fetch(url); - Network accessline 330
async function getData() { const result = await fetch(url); return result.json(); - Network accessline 331
const result = await fetch(url); - Network accessline 465
- [GitHub API: Pull Request Review Comments](https://docs.github.com/rest/pulls/comments) - Network accessline 466
- [GitHub API: Pull Request Reviews](https://docs.github.com/rest/pulls/reviews) - Network accessline 467
- [GitHub CLI Manual](https://cli.github.com/manual/) - Network accessline 477
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/comments` - Network accessline 493
**Endpoint:** `https://api.github.com/repos/{owner}/{repo}/pulls/{pull_number}/reviews`
skills/build-mcp/SKILL.md
- Network accessline 64
Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt` - Network accessline 76
- **Python SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 81
- **TypeScript SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - Network accessline 321
- **MCP Protocol**: Fetch from `https://modelcontextprotocol.io/llms-full.txt` - Complete MCP specification - Network accessline 332
- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 333
- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
skills/create-hook/SKILL.md
- Network accessline 182
_Complete templates available at: <https://docs.claude.com/en/docs/claude-code/hooks#examples>_ - Network accessline 186
**📖 Official Docs**: <https://docs.claude.com/en/docs/claude-code/hooks.md> - Network accessline 223
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 224
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 225
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 258
<Tabs> <Tab title="macOS"> Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 260
Uses [`osascript`](https://ss64.com/mac/osascript.html) to trigger a native macOS notification through AppleScript: - Network accessline 375
Automatically run [Prettier](https://prettier.io/) on every file Claude edits, so formatting stays consistent without manual intervention. - Network accessline 377
This hook uses the `PostToolUse` event with an `Edit|Write` matcher, so it runs only after file-editing tools. The command extracts the edited file path with [`jq`](https://jqlang.github.io/jq/) and passes it to Prettier. Add this to `.clau - Network accessline 397
<Note> The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Network accessline 398
The Bash examples on this page use `jq` for JSON parsing. Install it with `brew install jq` (macOS), `apt-get install jq` (Debian/Ubuntu), or see [`jq` downloads](https://jqlang.github.io/jq/download/). - Access to secretsline 418
[Credential-related source omitted] - Dangerous shell operationline 679
"command": "rm -f /tmp/claude-scratch-*.txt" - Network accessline 854
- [Hooks reference](/en/hooks): full event schemas, JSON output format, async hooks, and MCP tool hooks - [Security considerations](/en/hooks#security-considerations): review before deploying hooks in shared or production environments - [Ba - Network accessline 856
- [Bash command validator example](https://github.com/anthropics/claude-code/blob/main/examples/hooks/bash_command_validator_example.py): complete reference implementation - Network accessline 860
> ## Documentation Index > > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 861
> > Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> > Use this file to discover all available pages before exploring further. - Network accessline 862
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt> - Network accessline 879
<div style={{maxWidth: "500px", margin: "0 auto"}}> <Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hoo - Network accessline 880
<Frame> <img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from - Network accessline 881
<img src="https://mintcdn.com/claude-code/z2YM37Ycg6eMbID3/images/hooks-lifecycle.png?fit=max&auto=format&n=z2YM37Ycg6eMbID3&q=85&s=5c25fedbc3db6f8882af50c3cc478c32" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStar - Dangerous shell operationline 924
The script reads the JSON input from stdin, extracts the command, and returns a `permissionDecision` of `"deny"` if it contains `rm -rf`: - Dangerous shell operationline 931
if echo "$COMMAND" | grep -q 'rm -rf'; then - Dangerous shell operationline 944
Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens: - Network accessline 946
<Frame> <img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher check - Network accessline 947
<img src="https://mintcdn.com/claude-code/s7NM0vfd_wres2nf/images/hook-resolution.svg?fit=max&auto=format&n=s7NM0vfd_wres2nf&q=85&s=7c13f51ffcbc37d22a593b27e2f2de72" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash - Dangerous shell operationline 955
{ "tool_name": "Bash", "tool_input": { "command": "rm -rf /tmp/build" }, ... } - Dangerous shell operationline 964
The script extracts `"rm -rf /tmp/build"` from the input and finds `rm -rf`, so it prints a decision to stdout: - Dangerous shell operationline 1292
echo "Blocked: rm commands are not allowed" >&2 - Network accessline 1404
For extended examples including Bash command validation, prompt filtering, and auto-approval scripts, see [What you can automate](/en/hooks-guide#what-you-can-automate) in the guide and the [Bash command validator reference implementation]( - Network accessline 1634
| Field | Type | Example | Description | | :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | - Network accessline 1635
| :------- | :----- | :---------------------------- | :----------------------------------- | | `url` | string | `"https://example.com/api"` | URL to fetch content from | | `prompt` | string | `"Extract the API endpoints"` | - Network accessline 1636
| `url` | string | `"https://example.com/api"` | URL to fetch content from | - Dangerous shell operationline 1709
"command": "rm -rf node_modules",
skills/create-pr/SKILL.md
- Network accessline 25
# Linux # Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 26
# Follow instructions at https://github.com/cli/cli/blob/trunk/docs/install_linux.md - Network accessline 139
- [PR Template](.github/pull_request_template.md) - [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 140
- [Conventional Commits](https://www.conventionalcommits.org/) - Network accessline 141
- [GitHub CLI documentation](https://cli.github.com/manual/)
skills/create-rule/SKILL.md
- Network accessline 400
- [Flattening Arrow Code](https://blog.codinghorror.com/flattening-arrow-code/)
skills/create-skill/SKILL.md
- Network accessline 388
See [graphviz-conventions.dot](https://github.com/obra/superpowers/blob/main/skills/writing-skills/graphviz-conventions.dot) for graphviz style rules.
skills/design-testing-strategy/SKILL.md
- Network accessline 27
| # | Type | ON when | OFF when | Source | |---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with b - Network accessline 28
|---|------|---------|----------|--------| | 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or - Network accessline 29
| 0 | **Skip All** | Criticality is `NONE` (docs-only, comments, formatting, generated code, config without logic, throwaway prototypes) | Anything with branching, computed output, side effects, or user-visible behavior | [Pragmatic Program - Network accessline 30
| 1 | **Unit** | Code contains any logic: branches, loops, conditionals, computation, transformation, parsing, validation, formatting | Pure declarative wiring (DI registration, route table) with no behavior | [Test Pyramid (Vocke)](https:/ - Network accessline 31
| 2 | **Integration** | Boundary crossing: HTTP call, DB query, external SDK, message queue, filesystem I/O, OR collaboration with >=2 distinct collaborators where unit doubles distort behavior | Pure function with no I/O and 0-1 stable col - Network accessline 32
| 3 | **Component or E2E** | UI surface AND criticality >= MEDIUM-HIGH AND user-facing critical path (signup, checkout, auth, payment, primary CTA) | Internal admin-only screens, dev tooling, or non-critical UI | [Test Pyramid top](https:// - Network accessline 33
| 4 | **Contract** | Public API consumed by >=1 distinct clients (mobile + web, multiple internal services, external partners) AND independent deploy cadence | API where consumer and provider deploy together | [Pact / CDC](https://docs.pact - Network accessline 34
| 5 | **Smoke** | Deployable surface (web app, API, service) AND a deploy/CI pipeline exists where post-deploy validation is meaningful | Library, internal helper, or no deploy pipeline | [Google "What Makes a Good End-to-End Test"](https:/ - Network accessline 35
| 6 | **Property-Based** | Input domain is large or unbounded (numeric ranges, strings, lists, parsers, serializers, encoders, math) AND invariants are stable (round-trip, idempotency, monotonicity, commutativity) AND criticality >= MEDIUM- - Network accessline 64
| Type | Use when | Do NOT use when | Frameworks | Typical dependencies | Google Size | |------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, determini - Network accessline 65
|------|----------|-----------------|------------|----------------------|-------------| | **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go te - Network accessline 66
| **unit** | Pure logic, single function/method/class, deterministic inputs | Code is just I/O orchestration with no logic | vitest, jest, pytest, go test, JUnit, xUnit, RSpec | None (or in-memory fakes) | [Small](https://testing.googleblog - Network accessline 67
| **integration** | Boundary crossing (DB, HTTP, queue, FS); multiple collaborators where mocking distorts behavior | Pure function with no boundary | vitest, jest, pytest, go test, JUnit + [Testcontainers](https://testcontainers.com/), sup - Network accessline 68
| **component** | UI rendering + interaction within a single component, no full app context | Backend-only logic; multi-page user flow | React Testing Library, Vue Test Utils, Angular TestBed, Storybook interaction tests | jsdom or happy-do - Network accessline 69
| **e2e** | Full user path through running app: real browser, real backend, real DB | Internal helper, single component, non-critical UI | [Playwright](https://playwright.dev/), [Cypress](https://www.cypress.io/), Selenium | Real running ap - Network accessline 70
| **smoke** | Post-deploy go/no-go: hit / health, key endpoints respond, login works | Detailed correctness; smoke is shallow by design | Playwright (1-3 critical paths), HTTP probe scripts, k6 minimal scenarios | Real deployed environment - Network accessline 71
| **contract** | Public API consumed by 2+ distinct clients with independent deploy cadence | Single-consumer internal API; provider and consumer deploy together | [Pact](https://docs.pact.io/), Spring Cloud Contract, OpenAPI schema validat - Network accessline 72
| **property-based** | Large/unbounded input domain with stable invariants (parser, serializer, encoder, math) | Small finite input space; unstable invariants | [Hypothesis](https://hypothesis.works/) (Python), fast-check (TS), QuickCheck ( - Network accessline 76
[Google Test Sizes (Bland)](https://mike-bland.com/2011/11/01/small-medium-large.html) and [SWE at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html) classify tests by **resources** (size), independent of **scope** (paths co - Network accessline 89
| Dimension | [Playwright](https://playwright.dev/) | [Cypress](https://www.cypress.io/) | - Network accessline 101
Use ISTQB Foundation Level black-box techniques to derive **what** to test inside each chosen test type. References: [ISTQB BVA white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf), [ASTQB black - Network accessline 168
When EP, BVA, or decision-table analysis yields **3+ cases with the same shape** (same setup, same assertion, only inputs and expected outputs differ — e.g., parsing valid/invalid date formats; computing tax across brackets; routing rules) - Network accessline 201
| Dependency style | Use when | Avoid when | Notes | |------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic - Network accessline 202
|------------------|----------|------------|-------| | **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker avail - Network accessline 203
| **Real infra via [Testcontainers](https://testcontainers.com/)** | DB/Redis/Kafka/Browser, dev needs real driver behavior, hermetic CI required | Cold-start budget < 1s, no Docker available | Default for integration tests on Postgres / Re - Network accessline 215
Explicit "don't bother" rules. Skipping these is not laziness — it is risk-adjusted ROI per [ISO/IEC/IEEE 29119 risk-based testing](https://en.wikipedia.org/wiki/ISO/IEC_29119) and [Risk-Based Testing](https://www.softwaretestinghelp.com/ri - Network accessline 223
| **No component test for static markup** | If the component has no state, no events, no conditional rendering, a snapshot is enough — or skip entirely. | | **No unit test for declarative wiring** | DI bindings, route registration, schema d - Network accessline 224
| **No unit test for declarative wiring** | DI bindings, route registration, schema declarations: assert at integration level (does the route serve the right handler) instead. | | **No e2e for things integration covers reliably** | Per [Goo - Network accessline 225
| **No e2e for things integration covers reliably** | Per [Google e2e principles](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html): the smaller the test you can use to cover a behavior, the better. e2e is t - Network accessline 226
| **No tests for spike/throwaway code** | Per [Beck TDD](https://www.oreilly.com/library/view/test-driven-development/0321146530/): if the artifact will be deleted within hours, document the exception with the human partner. Then write test - Network accessline 335
- `type` matches one of `selected_types[*].type` from the matrix - `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange - Network accessline 336
- `description` follows AAA / [Given-When-Then (Dan North BDD)](https://dannorth.net/introducing-bdd/) shape — see [Bill Wake AAA (2001)](https://xp123.com/articles/3a-arrange-act-assert/) - Network accessline 369
1. **Test Pyramid** — Mike Cohn (2009, *Succeeding with Agile*) + Ham Vocke, [The Practical Test Pyramid](https://martinfowler.com/articles/practical-test-pyramid.html), martinfowler.com. - Network accessline 370
2. **Testing Trophy** — Kent C. Dodds (2018), [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) and [Write Tests](https://kentcdodds.com/blog/write-tests). - Network accessline 371
3. **Google Test Sizes** — Mike Bland (2011), [Small / Medium / Large](https://mike-bland.com/2011/11/01/small-medium-large.html); [Software Engineering at Google Ch.11](https://abseil.io/resources/swe-book/html/ch11.html); [Test Sizes (Goo - Network accessline 372
4. **Google Testing on the Toilet** — [What Makes a Good End-to-End Test](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html), [Testing UI Logic - Follow the User](https://testing.googleblog.com/2020/10/testin - Network accessline 373
5. **ISTQB Foundation Level** — Black-box techniques: [Boundary Value Analysis white paper](https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf); [ASTQB Black-Box Techniques](https://astqb.org/4-2-black-box- - Network accessline 374
6. **ISO/IEC/IEEE 29119** — Risk-based test process standard. [Wikipedia overview](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 375
7. **Kent Beck — *Test Driven Development: By Example*** (Addison-Wesley, 2002). [Publisher page](https://www.oreilly.com/library/view/test-driven-development/0321146530/). ISBN 978-0321146533. - Network accessline 376
8. **The Pragmatic Programmer (20th Anniversary Edition)** — Hunt & Thomas (2019). [pragprog.com](https://pragprog.com/titles/tpp20/the-pragmatic-programmer-20th-anniversary-edition/). - Network accessline 377
9. **AAA pattern** — Bill Wake (2001), [3A — Arrange, Act, Assert](https://xp123.com/articles/3a-arrange-act-assert/). **Given-When-Then** — Dan North, [Introducing BDD](https://dannorth.net/introducing-bdd/). - Network accessline 378
10. **Property-based testing** — [Hypothesis: What is property-based testing?](https://hypothesis.works/articles/what-is-property-based-testing/); QuickCheck (Haskell), fast-check (TS). - Network accessline 379
11. **Contract testing / Consumer-Driven Contracts** — [Pact docs](https://docs.pact.io/); [Pactflow CDC explainer](https://pactflow.io/what-is-consumer-driven-contract-testing/). - Network accessline 380
12. **Testcontainers** — [testcontainers.com](https://testcontainers.com/). - Network accessline 381
13. **Table-driven tests** — Dave Cheney, [Prefer table-driven tests](https://dave.cheney.net/2019/05/07/prefer-table-driven-tests); [Go wiki: TableDrivenTests](https://go.dev/wiki/TableDrivenTests). - Network accessline 382
14. **Risk-based testing** — [Risk Management During Test Planning (softwaretestinghelp.com)](https://www.softwaretestinghelp.com/risk-management-during-test-planning-risk-based-testing/). - Network accessline 419
|------|----------|--------| | 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 420
| 0 Skip | OFF | Has logic | | 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic - Network accessline 421
| 1 Unit | **ON** | Pure logic with branches per currency code — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 422
| 2 Integration | OFF | No I/O, no boundary — [Skip Heuristic: no integration for pure functions](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) | - Network accessline 424
| 4 Contract | OFF | Not a public API | | 5 Smoke | OFF | Not deployable | | 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypoth - Network accessline 426
| 6 Property-Based | **ON** (partial) | Numeric input is unbounded, but invariants exist (round-trip via parse, monotonicity in amount) — [Hypothesis](https://hypothesis.works/articles/what-is-property-based-testing/). Promote at MEDIUM-HIG - Network accessline 521
|------|----------|--------| | 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 522
| 0 Skip | OFF | Has substantial logic | | 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | | 2 Integration | **ON** | Boundary crossin - Network accessline 523
| 1 Unit | **ON** | Validators (email, password, age) are pure logic — [Test Pyramid base](https://martinfowler.com/articles/practical-test-pyramid.html) | - Network accessline 524
| 2 Integration | **ON** | Boundary crossing: HTTP, Postgres, Kafka — [Testing Trophy](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) ROI sweet spot | - Network accessline 525
| 3 Component/E2E | OFF (here) | No UI in this artifact; UI lives in mobile + web repos and tests itself | | 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is - Network accessline 526
| 4 Contract | **ON** | Two distinct consumers (mobile + web) on independent deploy cadences — [Pact CDC](https://pactflow.io/what-is-consumer-driven-contract-testing/) | - Network accessline 527
| 5 Smoke | **ON** | Deployable HTTP service; post-deploy probe of `/users` registration is meaningful — [Google e2e](https://testing.googleblog.com/2016/09/testing-on-toilet-what-makes-good-end.html) | - Network accessline 528
| 6 Property-Based | OFF | Input domain (email, password, age) is constrained and well-covered by EP+BVA at unit; criticality is MEDIUM-HIGH but Gate 6 OFF on bounded inputs — [Skip Heuristic](https://hypothesis.works/articles/what-is-prope - Network accessline 645
| 1 Unit | **ON** | Validation helpers (`validateEmail`, `passwordsMatch`, `parseAge`) are pure logic | | 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integratio - Network accessline 646
| 2 Integration | OFF (here) | The component itself does not cross a real boundary; network is mocked at fetch level. Network integration is owned by `POST /users` (Example B) | | 3 Component/E2E | **ON** (component) + **ON** (e2e for the r - Network accessline 647
| 3 Component/E2E | **ON** (component) + **ON** (e2e for the registration path) | UI surface, criticality MEDIUM-HIGH, user-facing critical path — [Test Pyramid top](https://martinfowler.com/articles/practical-test-pyramid.html) + [Follow t - Network accessline 749
- [ ] Each AC is referenced by at least one test case. - [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/ht - Network accessline 750
- [ ] BVA cases enumerate `B-1`, `B`, `B+1` for each numeric boundary. - [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html). - [ ] Test names contain no "and" (per [ - Network accessline 751
- [ ] Test sizes (small/medium/large) are assigned per [Google Test Sizes](https://abseil.io/resources/swe-book/html/ch11.html).
skills/git-notes/SKILL.md
skills/git-worktrees/SKILL.md
skills/kaizen/SKILL.md
- Access to secretsline 304
[Credential-related source omitted] - Access to secretsline 306
[Credential-related source omitted] - Network accessline 372
class UserAPIClient { async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); - Network accessline 373
async getUser(id: string): Promise<User> { return this.fetch(`/users/${id}`); } - Network accessline 374
return this.fetch(`/users/${id}`); - Network accessline 379
class OrderAPIClient { async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); - Network accessline 380
async getOrder(id: string): Promise<Order> { return this.fetch(`/orders/${id}`); } - Network accessline 381
return this.fetch(`/orders/${id}`); - Network accessline 446
* @example * const result = await retry( * () => fetch('https://api.example.com/data'), - Network accessline 447
* const result = await retry( * () => fetch('https://api.example.com/data'), * { maxAttempts: 3, baseDelay: 1000 } - Network accessline 448
* () => fetch('https://api.example.com/data'),
skills/load-pr-comments/SKILL.md
- Network accessline 32
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 33
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 34
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 39
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch.
skills/memorize/SKILL.md
- Network accessline 296
- This command is the counterpart to `/reflexion:reflect`: reflect → curate → memorize. - The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/25 - Network accessline 297
- The design follows ACE to avoid brevity bias and context collapse by accumulating granular, organized knowledge over time (`https://arxiv.org/pdf/2510.04618`).
skills/reset/SKILL.md
- Dangerous shell operationline 85
rm -rf .fpf/knowledge/L0/*.md - Dangerous shell operationline 86
rm -rf .fpf/knowledge/L1/*.md - Dangerous shell operationline 87
rm -rf .fpf/knowledge/L2/*.md - Dangerous shell operationline 88
rm -rf .fpf/knowledge/invalid/*.md - Dangerous shell operationline 89
rm -rf .fpf/evidence/*.md - Dangerous shell operationline 90
rm -rf .fpf/decisions/*.md
skills/resolve-fixed-pr-comments/SKILL.md
- Network accessline 69
- if both are available, use any that have enough accesses to the repository. - if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through - Network accessline 70
- if github mcp server avaiable but have different structure, adjust in order to fit the expected structure. - if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install - Network accessline 71
- if none is available, try to load directly through curl in case if it is public repository. If it is private, ask user to install GitHub CLI or GitHub MCP server. - Network accessline 76
- An explicit PR argument ALWAYS takes precedence over current-branch resolution. If a PR number or URL was passed, use it (a URL like `https://github.com/{owner}/{repo}/pull/{n}` → number `{n}`) and do NOT consult the current branch. - Network accessline 227
**Input:** `resolve-fixed-pr-comments https://github.com/acme/app/pull/7`
skills/review-pr/SKILL.md
- Network accessline 266
- Use full git sha + line range, eg. `https://github.com/owner/repo/blob/1d54823877c4de72b2316a64032a54afc404e619/README.md#L13-L17`
skills/setup-arxiv-mcp/SKILL.md
skills/setup-codemap-cli/SKILL.md
skills/setup-context7-mcp/SKILL.md
- Network accessline 36
if no, load <https://raw.githubusercontent.com/upstash/context7/refs/heads/master/README.md> file and guide user through setup process that applicable to agent/operation system.
skills/setup-serena-mcp/SKILL.md
- Network accessline 42
- Load <https://raw.githubusercontent.com/oraios/serena/refs/heads/main/README.md> to understand what Serena is and its capabilities - Network accessline 43
- Load <https://oraios.github.io/serena/02-usage/020_running.html> to learn how to run Serena - Network accessline 44
- Load <https://oraios.github.io/serena/02-usage/030_clients.html> to learn how to configure your MCP client - Network accessline 45
- Load <https://oraios.github.io/serena/02-usage/040_workflow.html> to learn how to setup Serena for your project
skills/test-coverage/SKILL.md
- Network accessline 39
Coverage is *necessary-but-not-sufficient*. A test can execute a line without asserting anything meaningful; 100% line coverage is routinely achievable with zero assertions ([thinkinglabs.io](https://thinkinglabs.io/articles/2022/03/19/the- - Network accessline 44
- **NOT a measure of correctness.** Coverage proves the test ran, not that it would have failed on a bug. - **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitut - Network accessline 45
- **NOT a synonym for "well tested".** Mutation testing routinely refutes 100%-coverage-with-no-assertions suites. - **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - - Network accessline 46
- **NOT a substitute for risk-based test selection** per [ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119). - Network accessline 72
- **Definition.** Percentage of source-code lines (or statements) executed at least once. - **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were t - Network accessline 73
- **What it does NOT measure.** Whether branches were taken in both directions. Whether assertions verified the result. Whether boundary values were tested. Multiple statements on one line distort the metric ([Metridev](https://www.metridev - Network accessline 76
| Ecosystem | Tool | |-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 77
|-----------|------| | JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | | Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 78
| JS/TS | [Istanbul / nyc](https://istanbul.js.org/) (built into Jest, Vitest, Karma); `--coverage` flag | - Network accessline 79
| Python | [Coverage.py](https://coverage.readthedocs.io/) + `pytest-cov`; supports branch mode | - Network accessline 80
| JVM | [JaCoCo](https://www.eclemma.org/jacoco/) — bytecode instrumentation, industry standard | - Network accessline 81
| C/C++ | `gcov` / `lcov` / `gcovr`, [llvm-cov](https://llvm.org/docs/CommandGuide/llvm-cov.html) | - Network accessline 82
| Go | `go test -cover`, `go tool cover` ([build-cover](https://go.dev/doc/build-cover) added integration-test mode in Go 1.20) | - Network accessline 83
| .NET | [Coverlet](https://github.com/coverlet-coverage/coverlet) (open-source default), [JetBrains dotCover](https://www.jetbrains.com/dotcover/), AltCover. **OpenCover is in maintenance mode — prefer Coverlet / dotCover / AltCover** ([ND - Network accessline 84
| Ruby | [SimpleCov](https://github.com/simplecov-ruby/simplecov) | - Network accessline 89
- **When to use vs skip.** Always-on; cost is near-zero (a CI flag). Never use as a quality goal in itself. - **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blo - Network accessline 90
- **Targets / thresholds & pitfalls.** 70–85% is typical for general-purpose code ([Qt blog](https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough)). Apply only with the risk caveat (see Risk-Based Interpreta - Network accessline 95
- **Definition.** Percentage of decision branches (true/false outcomes of `if`, `while`, `for`, `?:`, `switch` cases) executed. - **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, - Network accessline 96
- **What it does NOT measure.** Compound-condition independence (`A && B` taken `true` might never test `A=true, B=false`). Order of evaluation. Loop iteration counts. Assertion strength. - **Typical tools.** Same as line coverage; enable w - Network accessline 97
- **Typical tools.** Same as line coverage; enable with `--branch` (coverage.py), branch mode (Istanbul is branch-aware by default), JaCoCo reports branches natively. Strictly stronger than line/statement coverage ([Graph AI](https://www.gr - Network accessline 98
- **When to use vs skip.** Default for any non-trivial logic. Prefer branch over line as the primary structural metric. - **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](htt - Network accessline 99
- **Targets / thresholds & pitfalls.** 70–80% branch is a "respectable" target for business apps ([Lead With Skills](https://www.leadwithskills.com/blogs/test-coverage-metrics-lines-branches-conditions-paths)) — always paired with the risk - Network accessline 100
- **Cost-benefit ROI.** High — best single structural metric for general-purpose code ([LinearB](https://linearb.io/blog/what-is-branch-coverage)). - Network accessline 120
- **Definition** (per [Wikipedia](https://en.wikipedia.org/wiki/Modified_condition/decision_coverage)): - Network accessline 126
For `n` conditions, MC/DC is achievable with `n+1` to `2n` tests via independence pairs — vastly cheaper than the `2^n` of exhaustive multiple-condition coverage ([LDRA](https://ldra.com/capabilities/mc-dc/)). - Network accessline 128
- **What it does NOT measure.** Loop iteration counts, data values, integration paths, assertion strength. - **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/ - Network accessline 129
- **Typical tools.** LDRA TBvision, Rapita RapiCover, VectorCAST, Razorcat TESSY, [Qt Coco](https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc), Parasoft C/C++test. Mostly commercial — open-source MC/ - Network accessline 130
- **When to use vs skip.** When mandated by a standard (DO-178C DAL A, ISO 26262 ASIL D, IEC 62304 Class C high-risk modules, EN 50128 SIL 4, IEC 61508 SIL 4). Outside regulated domains, branch coverage + mutation testing covers the same in - Network accessline 131
- **Targets / thresholds & pitfalls.** 100% by definition in regulated domains. Short-circuit evaluation in C-like languages can make some independence pairs unreachable; compiler optimizations can collapse conditions, so coverage builds mu - Network accessline 153
- **Definition.** Percentage of unique linearly-independent paths through a function. Bounded by cyclomatic complexity `V(G) = decisions + 1` ([Cyclomatic complexity](https://en.wikipedia.org/wiki/Cyclomatic_complexity)). - Network accessline 174
Mutation testing introduces small, syntactic modifications ("mutants") to the source and re-runs the existing test suite against each mutant. If at least one test **fails** for a given mutant, the mutant is **killed** (the suite detected th - Network accessline 186
### Mutant states ([Stryker docs](https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/)) - Network accessline 202
- **Semantic correctness** of assertions — a wrong-but-strict assertion still kills mutants. - **Boundary data values** — operator mutants approximate this but do not replace BVA. - **Equivalent mutants** — variants that produce identical o - Network accessline 204
- **Equivalent mutants** — variants that produce identical observable behavior. Detection is undecidable in general; manual review is the only certain method. Modern tools (Stryker TypeScript Checker, PIT with Major) reduce these heuristica - Network accessline 208
| Ecosystem | Tool | |-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 209
|-----------|------| | JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | | .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documen - Network accessline 210
| JS / TS | [Stryker (StrykerJS)](https://stryker-mutator.io/) — TypeScript checker plugin filters compile-error mutants | - Network accessline 211
| .NET (C#) | [Stryker .NET](https://stryker-mutator.io/docs/stryker-net/introduction/); documented in [Microsoft Learn](https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing) | - Network accessline 212
| Java / JVM | [PIT (Pitest)](https://pitest.org/) — reference standard for JVM; Major Mutator for research | - Network accessline 213
| Python | [mutmut](https://mutmut.readthedocs.io/), [Cosmic Ray](https://cosmic-ray.readthedocs.io/), [MutPy](https://github.com/mutpy/mutpy) | - Network accessline 214
| Go | [go-mutesting](https://github.com/avito-tech/go-mutesting), [ooze](https://github.com/gtramontina/ooze) | - Network accessline 215
| PHP | [Infection](https://infection.github.io/) | - Network accessline 216
| Ruby | [mutant](https://github.com/mbj/mutant) | - Network accessline 217
| Rust | [cargo-mutants](https://mutants.rs/) | - Network accessline 218
| C / C++ | [Mull](https://github.com/mull-project/mull) — LLVM-based | - Network accessline 219
| Scala | [Stryker4s](https://stryker-mutator.io/docs/stryker4s/introduction/) | - Network accessline 239
Stryker defaults ([config](https://stryker-mutator.io/docs/stryker-js/configuration/)): `high: 80`, `low: 60`, `break: null`. Set `break` to fail the build below a floor. Apply with the risk caveat: 60–80% on a mature unit suite over pure-l - Network accessline 243
- **Cost.** CPU-quadratic-ish. A 60-second suite generating 1,000 mutants is up to 1,000 × 60s without optimization. Modern tools mitigate via incremental analysis, per-mutant test selection, and parallel runners. - **Benefit.** Catches *mi - Network accessline 244
- **Benefit.** Catches *missing assertions* and *over-mocked* tests that structural coverage cannot detect. It is the **only practical coverage technique that scores assertion strength** — the chief failure mode of "100% coverage with no as - Network accessline 245
- **CI pattern.** Incremental mutation on PR diff; nightly full run on critical modules ([oneuptime](https://oneuptime.com/blog/post/2026-01-24-mutation-testing/view); see also research roundup at [greg4cr.github.io](https://greg4cr.github. - Network accessline 266
The foundational artifact is the **Requirements Traceability Matrix (RTM)** — a two-dimensional table correlating requirements to test cases ([ISTQB Glossary](https://istqb-glossary.page/traceability-matrix/)). Enables: - Network accessline 288
In BDD ecosystems, Gherkin `Scenario:` blocks are the unit of acceptance coverage; each AC ideally maps to one or more scenarios (the Cardinal Rule of BDD: one scenario, one behavior — [Automation Panda](https://automationpanda.com/bdd/)). - Network accessline 290
Foundational standards: **ISTQB Foundation Level** treats RTM as a foundational artifact for systematic test design. **[ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)** parts 1–5 require traceability at the test-plan, test - Network accessline 320
- **Definition.** `(unique_endpoint_method_pairs_hit) / (total_documented_endpoint_method_pairs)`. Often broken down further by `(endpoint, method, status_code)` triples. - **What it does NOT measure.** Whether responses are *correct* — onl - Network accessline 321
- **What it does NOT measure.** Whether responses are *correct* — only that endpoints were hit. The combinatorial inputs leading to each status code. - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL - Network accessline 322
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (OpenAPI/GraphQL-driven test generator that reports endpoint and status-code coverage), [Dredd](https://dredd.org/) (validates HTTP API against API Blueprint / OpenAP - Network accessline 329
- **Definition.** Percentage of consumer-side **interactions** (request/response examples) that the provider has verified. Consumer generates Pact files (JSON contracts) capturing specific interactions; provider runs verification suites aga - Network accessline 330
- **What it does NOT measure.** Provider behavior on inputs no consumer ever sends (negative space). Performance, security, or schema completeness. - **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow - Network accessline 331
- **Typical tools.** [Pact](https://docs.pact.io/) (multi-language), Pact Broker / [Pactflow](https://pactflow.io/what-is-consumer-driven-contract-testing/) for storage and verification reports. [Spring Cloud Contract](https://spring.io/pro - Network accessline 332
- **When to use vs skip.** Use when there are multiple independent consumers with independent deploy cadences (microservices, mobile + web sharing a backend). Skip for single-consumer APIs that deploy with the provider, or for library APIs. - Network accessline 333
- **Targets / thresholds & pitfalls.** "Schema valid" is weaker than "contract honored" — schema tells you what shapes are *legal*; contract tells you which fields and behaviors a consumer *actually depends on* ([Speakeasy: Pact vs OpenAPI] - Network accessline 338
- **Definition.** Percentage of schema fields, enum values, and `oneOf` / `anyOf` variants exercised across the test suite. - **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - - Network accessline 339
- **What it does NOT measure.** Semantic field correctness (a field can have the wrong value but the right shape). - **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits - Network accessline 340
- **Typical tools.** [Schemathesis](https://schemathesis.readthedocs.io/) (property-based test generation from OpenAPI; emits coverage metrics over schema elements), [Dredd](https://dredd.org/) with hooks for field-level instrumentation, [S - Network accessline 360
- **Definition.** Coverage measured against **input partitions** rather than code. Each Equivalence Partition (EP) and Boundary Value Analysis (BVA) slot from ISTQB Foundation Level black-box techniques becomes a coverage element ([ISTQB BV - Network accessline 369
- **Definition.** **Pairwise (all-pairs)** testing requires that every pair of parameter values appears in at least one test case. Most multi-parameter defects manifest at the 2-way interaction level ([Wikipedia](https://en.wikipedia.org/wi - Network accessline 370
- **What it does NOT measure.** Three-way+ interactions (unless escalated to `t=3`); ordering effects in workflows. - **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports - Network accessline 371
- **Typical tools.** [Microsoft PICT](https://github.com/microsoft/pict) (Pairwise Independent Combinatorial Tool; supports constraints, weighting, seeding), AllPairs (Satisfice), [NIST ACTS](https://csrc.nist.gov/projects/automated-combina - Network accessline 387
- **Definition.** Percentage of declared transitions (and optionally forbidden transitions) in a state machine exercised by tests. - **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecu - Network accessline 388
- **Switch-level coverage:** *0-switch* — every transition exercised once. *1-switch* — every pair of consecutive transitions. *2-switch* — every triple. *Round-trip* — every cycle in the state graph ([Lead With Skills](https://www.leadwith - Network accessline 467
Coverage targets should be **proportional to risk** ([ISO/IEC/IEEE 29119](https://en.wikipedia.org/wiki/ISO/IEC_29119)). The same artifact at different criticalities should not have the same coverage gate. Use the table below as a starting - Network accessline 478
**Delta thresholds** ("must not drop more than X%") are generally safer than absolute floors — they protect against regression in testing discipline without rewarding gaming ([Optivem](https://journal.optivem.com/p/code-coverage-targets-rec - Network accessline 502
| Standard | Domain | Coverage requirement | |----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; St - Network accessline 503
|----------|--------|----------------------| | **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E - Network accessline 504
| **[DO-178C](https://www.consunova.com/do178c-info.html)** §6.4.4.2, Table A-7 | Avionics | MC/DC required for DAL A; Decision coverage for DAL B; Statement coverage for DAL C; none for DAL D/E ([LDRA structural coverage](https://ldra.com/ - Network accessline 505
| **[ISO 26262](https://www.parasoft.com/learning-center/iso-26262/code-coverage/)** Part 6 Table 9 | Automotive | MC/DC highly recommended for ASIL D; branch for ASIL B–C; statement minimum for ASIL A ([Verifysoft](https://www.verifysoft.c - Network accessline 506
| **[IEC 62304](https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide)** | Medical | Coverage scales with safety class A → B → C; auditors expect MC/DC for Class C high-risk modules; MISRA C/C++ coding standards customar - Network accessline 507
| **[MISRA C / MISRA C++](https://www.misra.org.uk/)** | Embedded (cross-industry) | Coding-rule conformance is the primary signal; coverage is complementary; MC/DC expected for safety-critical components | - Network accessline 562
- **Playwright trace coverage** — Playwright records traces (DOM, network, console) per test; the [trace viewer](https://playwright.dev/docs/trace-viewer) makes UI coverage **auditable** in a way DOM-snapshot tests cannot. Trace artifacts g - Network accessline 563
- **Storybook coverage** — [Storybook Test](https://storybook.js.org/docs/writing-tests) reports which stories (component states) have an interaction test (`play` function) vs only a rendered snapshot. - Network accessline 564
- **Visual coverage** — pixel-diff regressions across stories ([Chromatic](https://www.chromatic.com/), Percy, Applitools, Playwright `toHaveScreenshot`). Coverage element = component-state visual baseline. - Network accessline 574
- **DO-178C** — RTCA; overview: <https://www.consunova.com/do178c-info.html>; LDRA structural coverage analysis: <https://ldra.com/ldra-blog/do-178c-structural-coverage-analysis/>. - Network accessline 575
- **ISO 26262** — Road vehicles functional safety; Parasoft summary: <https://www.parasoft.com/learning-center/iso-26262/code-coverage/>; Verifysoft: <https://www.verifysoft.com/en_ISO_26262_Road_Vehicles_Functional_Safety.html>. - Network accessline 576
- **IEC 62304** — Medical device software lifecycle; <https://intuitionlabs.ai/articles/iec-62304-medical-device-software-guide>. - Network accessline 577
- **MISRA C / C++** — <https://www.misra.org.uk/>. - Network accessline 578
- **ISO/IEC/IEEE 29119** — Software testing process; <https://en.wikipedia.org/wiki/ISO/IEC_29119>; ISTQB-to-29119 mapping: <https://www.rcolomo.com/papers/326.pdf>. - Network accessline 579
- **ISTQB Foundation Level** — RTM glossary entry: <https://istqb-glossary.page/traceability-matrix/>; BVA white paper: <https://istqb.org/wp-content/uploads/2025/10/Boundary-Value-Analysis-white-paper.pdf>. - Network accessline 583
- LDRA MC/DC capability: <https://ldra.com/capabilities/mc-dc/>. - Network accessline 584
- Wikipedia MC/DC: <https://en.wikipedia.org/wiki/Modified_condition/decision_coverage>. - Network accessline 585
- Qt Coco MC/DC: <https://www.qt.io/quality-assurance/coco/feature-modified-condition-decision-coverage-mcdc>. - Network accessline 586
- Cyclomatic complexity: <https://en.wikipedia.org/wiki/Cyclomatic_complexity>. - Network accessline 590
- Istanbul: <https://istanbul.js.org/>. - Network accessline 591
- JaCoCo: <https://www.eclemma.org/jacoco/>. - Network accessline 592
- Coverage.py: <https://coverage.readthedocs.io/>. - Network accessline 593
- llvm-cov: <https://llvm.org/docs/CommandGuide/llvm-cov.html>. - Network accessline 594
- Go coverage: <https://go.dev/doc/build-cover>. - Network accessline 595
- Coverlet: <https://github.com/coverlet-coverage/coverlet>; NDepend guide (OpenCover deprecation notice): <https://blog.ndepend.com/guide-code-coverage-tools/>. - Network accessline 596
- SimpleCov: <https://github.com/simplecov-ruby/simplecov>. - Network accessline 600
- Stryker (JS / .NET / Scala): <https://stryker-mutator.io/>; config: <https://stryker-mutator.io/docs/stryker-js/configuration/>; mutant states: <https://stryker-mutator.io/docs/mutation-testing-elements/mutant-states-and-metrics/>; equiva - Network accessline 601
- Microsoft Learn on Stryker .NET: <https://learn.microsoft.com/en-us/dotnet/core/testing/mutation-testing>. - Network accessline 602
- PIT (Pitest): <https://pitest.org/>. - Network accessline 603
- mutmut: <https://mutmut.readthedocs.io/>; Cosmic Ray: <https://cosmic-ray.readthedocs.io/>. - Network accessline 604
- go-mutesting: <https://github.com/avito-tech/go-mutesting>. - Network accessline 605
- Infection (PHP): <https://infection.github.io/>. - Network accessline 606
- Mull (LLVM): <https://github.com/mull-project/mull>. - Network accessline 607
- cargo-mutants (Rust): <https://mutants.rs/>. - Network accessline 608
- Mutant (Ruby): <https://github.com/mbj/mutant>. - Network accessline 609
- Mutation in CI (research): <https://greg4cr.github.io/pdf/23mutationci.pdf>. - Network accessline 613
- Cucumber: <https://cucumber.io/>; behave: <https://behave.readthedocs.io/>; Reqnroll (active SpecFlow fork): <https://reqnroll.net/>. - Network accessline 614
- BDD Cardinal Rule — Automation Panda: <https://automationpanda.com/bdd/>. - Network accessline 618
- Pact: <https://docs.pact.io/>; Pactflow CDC explainer: <https://pactflow.io/what-is-consumer-driven-contract-testing/>; Pact vs OpenAPI: <https://www.speakeasy.com/blog/pact-vs-openapi>; bi-directional contract testing: <https://pactflow. - Network accessline 619
- Spring Cloud Contract: <https://spring.io/projects/spring-cloud-contract/>. - Network accessline 620
- Specmatic: <https://specmatic.io/>. - Network accessline 621
- Schemathesis: <https://schemathesis.readthedocs.io/>. - Network accessline 622
- Dredd: <https://dredd.org/>. - Network accessline 626
- PICT: <https://github.com/microsoft/pict>. - Network accessline 627
- NIST ACTS: <https://csrc.nist.gov/projects/automated-combinatorial-testing-for-software>. - Network accessline 628
- All-pairs testing overview: <https://en.wikipedia.org/wiki/All-pairs_testing>. - Network accessline 629
- State transition testing (ISTQB-aligned): <https://www.leadwithskills.com/blogs/state-transition-testing-behavior-based-systems-istqb>. - Network accessline 630
- Playwright trace viewer: <https://playwright.dev/docs/trace-viewer>. - Network accessline 631
- Storybook Test: <https://storybook.js.org/docs/writing-tests>; Chromatic: <https://www.chromatic.com/>. - Network accessline 635
- "The Fallacy of the 100% Code Coverage" — Thierry de Pauw: <https://thinkinglabs.io/articles/2022/03/19/the-fallacy-of-the-100-code-coverage.html>. - Network accessline 636
- "Code Coverage Targets — Recipe for Disaster" — Optivem Journal: <https://journal.optivem.com/p/code-coverage-targets-recipe-for-disaster>. - Network accessline 637
- "Is 70/80/90/100% coverage good enough?" — Qt: <https://www.qt.io/quality-assurance/blog/is-70-80-90-or-100-code-coverage-good-enough>. - Network accessline 638
- "AI-Generated Tests Give False Confidence" — CodeIntelligently: <https://codeintelligently.com/blog/ai-generated-tests-false-confidence>.
skills/test-prompt/SKILL.md
skills/thought-based-reasoning/SKILL.md
- Network accessline 642
1. Wei, J. et al. (2022). "Chain of Thought Prompting Elicits Reasoning in Large Language Models." [arXiv:2201.11903](https://arxiv.org/abs/2201.11903) - Network accessline 644
2. Kojima, T. et al. (2022). "Large Language Models are Zero-Shot Reasoners." [arXiv:2205.11916](https://arxiv.org/abs/2205.11916) - Network accessline 646
3. Wang, X. et al. (2022). "Self-Consistency Improves Chain of Thought Reasoning in Language Models." [arXiv:2203.11171](https://arxiv.org/abs/2203.11171) - Network accessline 648
4. Yao, S. et al. (2023). "Tree of Thoughts: Deliberate Problem Solving with Large Language Models." [arXiv:2305.10601](https://arxiv.org/abs/2305.10601) - Network accessline 650
5. Zhou, D. et al. (2022). "Least-to-Most Prompting Enables Complex Reasoning in Large Language Models." [arXiv:2205.10625](https://arxiv.org/abs/2205.10625) - Network accessline 652
6. Yao, S. et al. (2022). "ReAct: Synergizing Reasoning and Acting in Language Models." [arXiv:2210.03629](https://arxiv.org/abs/2210.03629) - Network accessline 654
7. Gao, L. et al. (2022). "PAL: Program-aided Language Models." [arXiv:2211.10435](https://arxiv.org/abs/2211.10435) - Network accessline 656
8. Zhang, Z. et al. (2022). "Automatic Chain of Thought Prompting in Large Language Models." [arXiv:2210.03493](https://arxiv.org/abs/2210.03493) - Network accessline 658
9. Shinn, N. et al. (2023). "Reflexion: Language Agents with Verbal Reinforcement Learning." [arXiv:2303.11366](https://arxiv.org/abs/2303.11366)
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.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md antigravity/skills/actualize/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Native | Path .cursor/worktrees.json | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md antigravity/skills/actualize/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md antigravity/skills/actualize/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/neolabhq-context-engineering-kit/)