Not in the top 1,000 by GitHub stars
human-avatar/skills-for-humanity
Structured reasoning methodologies from history's most rigorous thinkers, packaged as Claude Code skills.
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
skills/s4h/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-aesthetic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-aesthetic-coherence-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-aesthetic-elegance-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-aesthetic-pattern-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-aesthetic-simplicity-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-analogy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-analogy-boundary-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-analogy-domain-transfer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-analogy-perspective-shifting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-analogy-structure-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-cognition/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-cognition-attention/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-cognition-cognitive-load/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-cognition-mental-models/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-cognition-metacognition/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-communication/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-communication-audience-modeling/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-communication-clarity-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-communication-medium-selection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-communication-objection-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-constraint/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-constraint-hardness-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-constraint-rule-inversion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-constraint-scope-reduction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-constraint-workaround-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-alternatives/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-assumption-excavator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-brainstorm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-concept-fan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-consider-factors/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-lateral-thinking/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-other-perspectives/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-plus-minus-interesting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-provocation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-random-entry/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-six-hats/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-creativity-water-logic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-decision/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-decision-criteria-weighting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-decision-option-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-decision-premortem-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-decision-reversibility-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-design-constraints/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-design-iteration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-design-simplicity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-design-user-needs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ecology/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ecology-carrying-capacity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ecology-interdependence/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ecology-keystone-species/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ecology-succession/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics-coordination/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics-externalities/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics-incentive-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics-margin/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-economics-opportunity-cost/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-emotional/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-emotional-motivation-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-emotional-resistance-diagnosis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-emotional-stakes-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-emotional-trust-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-epistemology/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-epistemology-epistemic-status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-epistemology-justification/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-epistemology-knowledge-types/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-epistemology-limits/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-bias-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-consent-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-council/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-crisis-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-data-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-empathy-circle/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-impact-scan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-ethics-vendor-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-evolution/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-evolution-arms-race/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-evolution-fitness-landscape/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-evolution-niche/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-evolution-variation-selection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-auction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-coalition/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-equilibrium/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-iterated/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-mechanism-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-prisoners-dilemma/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-game-theory-signaling/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-historical/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-historical-cycle-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-historical-failure-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-historical-lesson-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-historical-precedent-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-identity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-identity-character-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-identity-mission-alignment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-identity-values-clarification/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-information/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-information-compression/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-information-entropy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-information-redundancy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-information-signal-noise/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation-claim-decomposition/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation-counter-hypothesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation-evidence-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation-source-trace/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-investigation-triangulation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-linguistics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-linguistics-connotation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-linguistics-framing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-linguistics-pragmatics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-linguistics-semantic-drift/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-argument-validation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-causality-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-consistency-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-constraint-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-council/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-logic-fixer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset-flow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset-growth/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset-positive/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset-reframe/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-mindset-stoic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-narrative/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-narrative-audience-modeling/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-narrative-frame-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-narrative-structure-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-narrative-tension-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-network/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-network-centrality/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-network-contagion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-network-effects/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-network-weak-ties/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-play/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-play-constraint-inversion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-play-perspective-reversal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-play-stimulus-generation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-play-worst-case-reversal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-probability/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-probability-base-rate-anchoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-probability-confidence-calibration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-probability-expected-value-calculation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-probability-scenario-weighting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology-behavior-change/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology-cognitive-biases/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology-heuristics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology-motivation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-psychology-persuasion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-resource/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-resource-allocation-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-resource-bottleneck-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-resource-leverage-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-resource-waste-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-sensory/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-sensory-detail-mining/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-sensory-signal-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-sensory-structured-observation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-social/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-social-coalition-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-social-dynamics-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-social-incentive-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-social-power-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-alliance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-deception/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-force-economy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-intelligence/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-positioning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-terrain/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-timing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-strategy-victory/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-systems/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-systems-archetype-matching/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-systems-emergence-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-systems-feedback-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-systems-leverage-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-temporal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-temporal-cycle-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-temporal-futures-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-temporal-horizon-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-temporal-timing-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-arc-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-argument/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-audience-calibration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-character-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-dialogue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-executive-summary/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-inconsistency-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-line-editing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-plot-structure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-pov/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-prose-elevation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-restructure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-rhetoric/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-scene-construction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-technical/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-tone-alignment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-voice-consistency/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
skills/s4h-writing-worldbuilding/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a30df8b67698 → a30df8b67698
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a30df8b67698
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit a30df8b67698ccb03ef5e35d68c2eddc5321ad3f
git clone --filter=blob:none --no-checkout https://github.com/human-avatar/skills-for-humanity.git .hotskills/human-avatar-skills-for-humanity && git -C .hotskills/human-avatar-skills-for-humanity checkout --detach a30df8b67698ccb03ef5e35d68c2eddc5321ad3f
# Copy each selected skill directory from .hotskills/human-avatar-skills-for-humanity into .claude/skills/<skill-name>/239GitHub stars
3stars in 7 days
212skills in this repository
0commits in 30 days
Heat
2.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- s4h
skills/s4h - s4h-aesthetic
skills/s4h-aesthetic - s4h-aesthetic-coherence-check
skills/s4h-aesthetic-coherence-check - s4h-aesthetic-elegance-testing
skills/s4h-aesthetic-elegance-testing - s4h-aesthetic-pattern-detection
skills/s4h-aesthetic-pattern-detection - s4h-aesthetic-simplicity-analysis
skills/s4h-aesthetic-simplicity-analysis - s4h-analogy
skills/s4h-analogy - s4h-analogy-boundary-testing
skills/s4h-analogy-boundary-testing - s4h-analogy-domain-transfer
skills/s4h-analogy-domain-transfer - s4h-analogy-perspective-shifting
skills/s4h-analogy-perspective-shifting - s4h-analogy-structure-mapping
skills/s4h-analogy-structure-mapping - s4h-cognition
skills/s4h-cognition - s4h-cognition-attention
skills/s4h-cognition-attention - s4h-cognition-cognitive-load
skills/s4h-cognition-cognitive-load - s4h-cognition-mental-models
skills/s4h-cognition-mental-models - s4h-cognition-metacognition
skills/s4h-cognition-metacognition - s4h-communication
skills/s4h-communication - s4h-communication-audience-modeling
skills/s4h-communication-audience-modeling - s4h-communication-clarity-audit
skills/s4h-communication-clarity-audit - s4h-communication-medium-selection
skills/s4h-communication-medium-selection - s4h-communication-objection-mapping
skills/s4h-communication-objection-mapping - s4h-constraint
skills/s4h-constraint - s4h-constraint-hardness-testing
skills/s4h-constraint-hardness-testing - s4h-constraint-rule-inversion
skills/s4h-constraint-rule-inversion - s4h-constraint-scope-reduction
skills/s4h-constraint-scope-reduction - s4h-constraint-workaround-mapping
skills/s4h-constraint-workaround-mapping - s4h-creativity
skills/s4h-creativity - s4h-creativity-alternatives
skills/s4h-creativity-alternatives - s4h-creativity-assumption-excavator
skills/s4h-creativity-assumption-excavator - s4h-creativity-brainstorm
skills/s4h-creativity-brainstorm - s4h-creativity-concept-fan
skills/s4h-creativity-concept-fan - s4h-creativity-consider-factors
skills/s4h-creativity-consider-factors - s4h-creativity-lateral-thinking
skills/s4h-creativity-lateral-thinking - s4h-creativity-other-perspectives
skills/s4h-creativity-other-perspectives - s4h-creativity-plus-minus-interesting
skills/s4h-creativity-plus-minus-interesting - s4h-creativity-provocation
skills/s4h-creativity-provocation - s4h-creativity-random-entry
skills/s4h-creativity-random-entry - s4h-creativity-six-hats
skills/s4h-creativity-six-hats - s4h-creativity-water-logic
skills/s4h-creativity-water-logic - s4h-decision
skills/s4h-decision - s4h-decision-criteria-weighting
skills/s4h-decision-criteria-weighting - s4h-decision-option-mapping
skills/s4h-decision-option-mapping - s4h-decision-premortem-analysis
skills/s4h-decision-premortem-analysis - s4h-decision-reversibility-analysis
skills/s4h-decision-reversibility-analysis - s4h-design
skills/s4h-design - s4h-design-constraints
skills/s4h-design-constraints - s4h-design-iteration
skills/s4h-design-iteration - s4h-design-simplicity
skills/s4h-design-simplicity - s4h-design-user-needs
skills/s4h-design-user-needs - s4h-ecology
skills/s4h-ecology - s4h-ecology-carrying-capacity
skills/s4h-ecology-carrying-capacity - s4h-ecology-interdependence
skills/s4h-ecology-interdependence - s4h-ecology-keystone-species
skills/s4h-ecology-keystone-species - s4h-ecology-succession
skills/s4h-ecology-succession - s4h-economics
skills/s4h-economics - s4h-economics-coordination
skills/s4h-economics-coordination - s4h-economics-externalities
skills/s4h-economics-externalities - s4h-economics-incentive-mapping
skills/s4h-economics-incentive-mapping - s4h-economics-margin
skills/s4h-economics-margin - s4h-economics-opportunity-cost
skills/s4h-economics-opportunity-cost - s4h-emotional
skills/s4h-emotional - s4h-emotional-motivation-mapping
skills/s4h-emotional-motivation-mapping - s4h-emotional-resistance-diagnosis
skills/s4h-emotional-resistance-diagnosis - s4h-emotional-stakes-mapping
skills/s4h-emotional-stakes-mapping - s4h-emotional-trust-audit
skills/s4h-emotional-trust-audit - s4h-epistemology
skills/s4h-epistemology - s4h-epistemology-epistemic-status
skills/s4h-epistemology-epistemic-status - s4h-epistemology-justification
skills/s4h-epistemology-justification - s4h-epistemology-knowledge-types
skills/s4h-epistemology-knowledge-types - s4h-epistemology-limits
skills/s4h-epistemology-limits - s4h-ethics
skills/s4h-ethics - s4h-ethics-bias-check
skills/s4h-ethics-bias-check - s4h-ethics-check
skills/s4h-ethics-check - s4h-ethics-consent-review
skills/s4h-ethics-consent-review - s4h-ethics-council
skills/s4h-ethics-council - s4h-ethics-crisis-triage
skills/s4h-ethics-crisis-triage - s4h-ethics-data-audit
skills/s4h-ethics-data-audit - s4h-ethics-empathy-circle
skills/s4h-ethics-empathy-circle - s4h-ethics-impact-scan
skills/s4h-ethics-impact-scan - s4h-ethics-vendor-review
skills/s4h-ethics-vendor-review - s4h-evolution
skills/s4h-evolution - s4h-evolution-arms-race
skills/s4h-evolution-arms-race - s4h-evolution-fitness-landscape
skills/s4h-evolution-fitness-landscape - s4h-evolution-niche
skills/s4h-evolution-niche - s4h-evolution-variation-selection
skills/s4h-evolution-variation-selection - s4h-game-theory
skills/s4h-game-theory - s4h-game-theory-auction
skills/s4h-game-theory-auction - s4h-game-theory-coalition
skills/s4h-game-theory-coalition - s4h-game-theory-equilibrium
skills/s4h-game-theory-equilibrium - s4h-game-theory-iterated
skills/s4h-game-theory-iterated - s4h-game-theory-mechanism-design
skills/s4h-game-theory-mechanism-design - s4h-game-theory-prisoners-dilemma
skills/s4h-game-theory-prisoners-dilemma - s4h-game-theory-signaling
skills/s4h-game-theory-signaling - s4h-historical
skills/s4h-historical - s4h-historical-cycle-detection
skills/s4h-historical-cycle-detection - s4h-historical-failure-analysis
skills/s4h-historical-failure-analysis - s4h-historical-lesson-extraction
skills/s4h-historical-lesson-extraction - s4h-historical-precedent-analysis
skills/s4h-historical-precedent-analysis - s4h-identity
skills/s4h-identity - s4h-identity-character-testing
skills/s4h-identity-character-testing - s4h-identity-mission-alignment
skills/s4h-identity-mission-alignment - s4h-identity-values-clarification
skills/s4h-identity-values-clarification - s4h-information
skills/s4h-information - s4h-information-compression
skills/s4h-information-compression - s4h-information-entropy
skills/s4h-information-entropy - s4h-information-redundancy
skills/s4h-information-redundancy - s4h-information-signal-noise
skills/s4h-information-signal-noise - s4h-investigation
skills/s4h-investigation - s4h-investigation-claim-decomposition
skills/s4h-investigation-claim-decomposition - s4h-investigation-counter-hypothesis
skills/s4h-investigation-counter-hypothesis - s4h-investigation-evidence-audit
skills/s4h-investigation-evidence-audit - s4h-investigation-source-trace
skills/s4h-investigation-source-trace - s4h-investigation-triangulation
skills/s4h-investigation-triangulation - s4h-linguistics
skills/s4h-linguistics - s4h-linguistics-connotation
skills/s4h-linguistics-connotation - s4h-linguistics-framing
skills/s4h-linguistics-framing - s4h-linguistics-pragmatics
skills/s4h-linguistics-pragmatics - s4h-linguistics-semantic-drift
skills/s4h-linguistics-semantic-drift - s4h-logic
skills/s4h-logic - s4h-logic-argument-validation
skills/s4h-logic-argument-validation - s4h-logic-causality-mapping
skills/s4h-logic-causality-mapping - s4h-logic-check
skills/s4h-logic-check - s4h-logic-consistency-check
skills/s4h-logic-consistency-check - s4h-logic-constraint-mapping
skills/s4h-logic-constraint-mapping - s4h-logic-council
skills/s4h-logic-council - s4h-logic-fixer
skills/s4h-logic-fixer - s4h-mindset
skills/s4h-mindset - s4h-mindset-flow
skills/s4h-mindset-flow - s4h-mindset-growth
skills/s4h-mindset-growth - s4h-mindset-positive
skills/s4h-mindset-positive - s4h-mindset-reframe
skills/s4h-mindset-reframe - s4h-mindset-stoic
skills/s4h-mindset-stoic - s4h-narrative
skills/s4h-narrative - s4h-narrative-audience-modeling
skills/s4h-narrative-audience-modeling - s4h-narrative-frame-analysis
skills/s4h-narrative-frame-analysis - s4h-narrative-structure-mapping
skills/s4h-narrative-structure-mapping - s4h-narrative-tension-mapping
skills/s4h-narrative-tension-mapping - s4h-network
skills/s4h-network - s4h-network-centrality
skills/s4h-network-centrality - s4h-network-contagion
skills/s4h-network-contagion - s4h-network-effects
skills/s4h-network-effects - s4h-network-weak-ties
skills/s4h-network-weak-ties - s4h-play
skills/s4h-play - s4h-play-constraint-inversion
skills/s4h-play-constraint-inversion - s4h-play-perspective-reversal
skills/s4h-play-perspective-reversal - s4h-play-stimulus-generation
skills/s4h-play-stimulus-generation - s4h-play-worst-case-reversal
skills/s4h-play-worst-case-reversal - s4h-probability
skills/s4h-probability - s4h-probability-base-rate-anchoring
skills/s4h-probability-base-rate-anchoring - s4h-probability-confidence-calibration
skills/s4h-probability-confidence-calibration - s4h-probability-expected-value-calculation
skills/s4h-probability-expected-value-calculation - s4h-probability-scenario-weighting
skills/s4h-probability-scenario-weighting - s4h-psychology
skills/s4h-psychology - s4h-psychology-behavior-change
skills/s4h-psychology-behavior-change - s4h-psychology-cognitive-biases
skills/s4h-psychology-cognitive-biases - s4h-psychology-heuristics
skills/s4h-psychology-heuristics - s4h-psychology-motivation
skills/s4h-psychology-motivation - s4h-psychology-persuasion
skills/s4h-psychology-persuasion - s4h-resource
skills/s4h-resource - s4h-resource-allocation-analysis
skills/s4h-resource-allocation-analysis - s4h-resource-bottleneck-analysis
skills/s4h-resource-bottleneck-analysis - s4h-resource-leverage-mapping
skills/s4h-resource-leverage-mapping - s4h-resource-waste-audit
skills/s4h-resource-waste-audit - s4h-sensory
skills/s4h-sensory - s4h-sensory-detail-mining
skills/s4h-sensory-detail-mining - s4h-sensory-signal-detection
skills/s4h-sensory-signal-detection - s4h-sensory-structured-observation
skills/s4h-sensory-structured-observation - s4h-social
skills/s4h-social - s4h-social-coalition-mapping
skills/s4h-social-coalition-mapping - s4h-social-dynamics-analysis
skills/s4h-social-dynamics-analysis - s4h-social-incentive-analysis
skills/s4h-social-incentive-analysis - s4h-social-power-mapping
skills/s4h-social-power-mapping - s4h-strategy
skills/s4h-strategy - s4h-strategy-alliance
skills/s4h-strategy-alliance - s4h-strategy-deception
skills/s4h-strategy-deception - s4h-strategy-force-economy
skills/s4h-strategy-force-economy - s4h-strategy-intelligence
skills/s4h-strategy-intelligence - s4h-strategy-positioning
skills/s4h-strategy-positioning - s4h-strategy-terrain
skills/s4h-strategy-terrain - s4h-strategy-timing
skills/s4h-strategy-timing - s4h-strategy-victory
skills/s4h-strategy-victory - s4h-systems
skills/s4h-systems - s4h-systems-archetype-matching
skills/s4h-systems-archetype-matching - s4h-systems-emergence-detection
skills/s4h-systems-emergence-detection - s4h-systems-feedback-mapping
skills/s4h-systems-feedback-mapping - s4h-systems-leverage-analysis
skills/s4h-systems-leverage-analysis - s4h-temporal
skills/s4h-temporal - s4h-temporal-cycle-detection
skills/s4h-temporal-cycle-detection - s4h-temporal-futures-mapping
skills/s4h-temporal-futures-mapping - s4h-temporal-horizon-mapping
skills/s4h-temporal-horizon-mapping - s4h-temporal-timing-analysis
skills/s4h-temporal-timing-analysis - s4h-writing
skills/s4h-writing - s4h-writing-arc-design
skills/s4h-writing-arc-design - s4h-writing-argument
skills/s4h-writing-argument - s4h-writing-audience-calibration
skills/s4h-writing-audience-calibration - s4h-writing-character-development
skills/s4h-writing-character-development - s4h-writing-copy
skills/s4h-writing-copy - s4h-writing-dialogue
skills/s4h-writing-dialogue - s4h-writing-executive-summary
skills/s4h-writing-executive-summary - s4h-writing-inconsistency-audit
skills/s4h-writing-inconsistency-audit - s4h-writing-line-editing
skills/s4h-writing-line-editing - s4h-writing-plot-structure
skills/s4h-writing-plot-structure - s4h-writing-pov
skills/s4h-writing-pov - s4h-writing-prose-elevation
skills/s4h-writing-prose-elevation - s4h-writing-report
skills/s4h-writing-report - s4h-writing-restructure
skills/s4h-writing-restructure - s4h-writing-rhetoric
skills/s4h-writing-rhetoric - s4h-writing-scene-construction
skills/s4h-writing-scene-construction - s4h-writing-technical
skills/s4h-writing-technical - s4h-writing-tone-alignment
skills/s4h-writing-tone-alignment - s4h-writing-voice-consistency
skills/s4h-writing-voice-consistency - s4h-writing-worldbuilding
skills/s4h-writing-worldbuilding
How it works
s4h
When your agent uses it
Master orchestration skill. Takes any situation in plain English, identifies the underlying goal, designs a multi-skill reasoning workflow, and executes it sequentially — feeding each skill's output into the next. Use when you say 'help me think through this', 'I need to figure out what to do', 'where do I start', or any time you want structured thinking applied end-to-end rather than routed to a single tool.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,202 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 Process
- Notes
Files
../../.claude-plugin/plugin.jsonasset723 bytes../../hooks/hooks.jsonasset292 bytesSKILL.mdcore9,932 bytes
Read SKILL.md
# Human
The master orchestration skill. You describe your situation and goal. This skill designs a tailored reasoning workflow — an ordered sequence of skills from across all 23 categories — then executes each step in sequence, feeding what each step reveals into the next. The result is compounding clarity, not a single tool's take.
---
## Your Process
### Step 1: Intake
If the user hasn't described their situation, ask:
> What are you trying to achieve? Describe the situation and what a good outcome looks like.
s4h-aesthetic
When your agent uses it
Entry point for the aesthetic toolkit. Routes to the right aesthetic skill based on your situation. Use when you say 'aesthetic', 'check the design', 'does this feel right', 'is this elegant', 'is this too complex', 'what pattern is this', 'find the simpler version', or want an aesthetic lens applied without knowing which specific tool fits.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
998 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Coherence Check
- Elegance Testing
- Pattern Detection
- Simplicity Analysis
Files
SKILL.mdcore4,802 bytes
Read SKILL.md
# Aesthetic
Applies aesthetic reasoning to any artifact — design, writing, code, product, argument. Diagnoses what kind of aesthetic question is being asked and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Check whether parts form a unified whole | coherence-check |
| Test whether something is more complex than it needs to be | elegance-testing |
| Name the underlying structural pattern at work | pattern-detection |
| Find the simpler version while preserving what matters | simplicity-analysis |
## Routing Decisions4h-aesthetic-coherence-check
When your agent uses it
Tests whether the parts of something form a unified whole — finding the jarring inconsistencies that accumulate when different contributors work without a shared vision. TRIGGERS: 'coherence check', 'does this feel unified', 'something feels off', 'inconsistent', 'check the whole', 'does this hang together'.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,351 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,110 bytesSKILL.mdcore6,110 bytes
Read SKILL.md
# Aesthetic Coherence Check
Incoherence is the default product of collaboration without a shared vision. Each part
may be locally defensible — sensible in isolation, reasonable given what that contributor
was optimising for — while the whole communicates nothing clearly. A perceptive reader
or user feels this before they can name it. This skill makes the incoherence legible
so it can be fixed.
---
## Your Process
**Step 1: State the Artefact and Its Intended Identity**
What is being examined — a product, document, strategy, brand, presentation, process?s4h-aesthetic-elegance-testing
When your agent uses it
Tests whether a solution is more complex than it needs to be — distinguishing necessary complexity from accidental complexity that accreted over time. TRIGGERS: 'elegance test', 'is this too complex', 'over-engineered', 'is there a simpler way', 'does this feel right'.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,268 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,550 bytes
Read SKILL.md
# Aesthetic Elegance Testing
Complexity is the default outcome of design by committee, incremental revision, and
deference to edge cases. Each addition is locally defensible. The cumulative result is
a system no one would have designed on purpose. Elegance is not simplicity for its own
sake — it is the property of a solution where every element earns its place and nothing
obscures the core. This skill tests for that property.
---
## Your Process
**Step 1: State the Solution**
Describe the design, plan, system, or solution in enough detail to evaluate its parts.s4h-aesthetic-pattern-detection
When your agent uses it
Identifies the underlying formal pattern at work — because most successful designs, arguments, and solutions share deep structural patterns, and naming the pattern unlocks the playbook. TRIGGERS: 'what pattern is this', 'pattern recognition', 'why does this work', 'identify the form', 'what structure is at play', 'what archetype is this'.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,356 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,149 bytesSKILL.mdcore6,149 bytes
Read SKILL.md
# Aesthetic Pattern Detection
Surface features differ — colours, words, technologies, industries. Formal patterns
recur across all of them. The same structural moves that make a symphony compelling
make a strategy compelling. The same tension-and-resolution arc that drives a thriller
drives a great pitch. Naming the pattern reveals options that surface-level analysis
cannot, because once the pattern is named, its full playbook becomes available.
---
## Your Process
**Step 1: Describe the Thing**
What does it do and how does it feel to engage with it? Focus on behaviour ands4h-aesthetic-simplicity-analysis
When your agent uses it
Finds the simpler version while preserving what matters — not arbitrary reduction, but finding the core and discarding what is not it. TRIGGERS: 'find the simple version', 'simplify this', 'what's the essence', 'less but better', 'strip it back', 'what could we remove'.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,278 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,603 bytes
Read SKILL.md
# Aesthetic Simplicity Analysis
Simplicity is not minimalism for its own sake — it is the clarity that emerges when
everything that obscures the essence has been removed. Most things accumulate layers:
additions made under pressure, elements that hedge against edge cases, features added
to satisfy someone who asked. The result is a thing that does everything adequately
and nothing powerfully. This skill finds the core and tests what must stay, what can
go, and what removal would actually cost.
---
## Your Process
**Step 1: State the Thing and Its Purpose**s4h-analogy
When your agent uses it
Entry point for the analogy toolkit. Routes to the right analogy skill based on your situation. Use when you say 'analogy', 'is this like that', 'find a comparison', 'import a solution from elsewhere', 'fresh eyes on this', 'where does this metaphor break', or want analogical reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,050 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Boundary Testing
- Domain Transfer
- Perspective Shifting
- Structure Mapping
Files
SKILL.mdcore5,266 bytes
Read SKILL.md
# Analogy
Applies analogical reasoning to any problem. Diagnoses what kind of analogy work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Find where an existing analogy or metaphor breaks down | boundary-testing |
| Import solutions from a completely different domain | domain-transfer |
| Approach a problem through a different field's lens | perspective-shifting |
| Test the structural correspondence between two situations | structure-mapping |
## Routing Decisions4h-analogy-boundary-testing
When your agent uses it
Finds where an analogy breaks down before it's relied upon. Analogies fail silently — the damage happens when decisions are made on a mapping that doesn't hold in the relevant dimension. Triggers: 'stress-test this analogy', 'where does this comparison break', 'does this really apply', 'test the metaphor', 'where is the analogy wrong'.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,207 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,461 bytesSKILL.mdcore5,461 bytes
Read SKILL.md
# Analogy Boundary Testing
Analogies are tools, not truths. The danger is not using an analogy — it is using one past
its boundary. Analogies fail silently: the flaw is invisible until a decision has been made
that depended on the part that didn't hold. This skill finds the boundary before that
happens.
---
## Your Process
**Step 1: State the Analogy**
Write it explicitly: "X is like Y." Name the analogy being tested, the domain it comes
from, and the claim being made on the basis of it.s4h-analogy-domain-transfer
When your agent uses it
Imports solutions from unrelated domains by finding structural similarities between your problem and solved problems elsewhere. Triggers: 'cross-domain analogy', 'what solves this elsewhere', 'find a parallel problem', 'look outside this field', 'borrow a solution'.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,039 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,791 bytes
Read SKILL.md
# Analogy Domain Transfer
Your field has blind spots that your field created. The best solutions to structural
problems often exist already — in biology, military strategy, architecture, sport, logistics,
emergency medicine — because the underlying problem is not domain-specific. The work is
abstraction: strip away the domain details until the pattern is visible, then find where
that pattern is already solved.
---
## Your Process
**Step 1: Abstract the Problem to Structural Essence**
Describe the problem without any domain vocabulary. What is actually happening? What ares4h-analogy-perspective-shifting
When your agent uses it
Approaches a problem from completely different fields to break the assumption blindness that comes from domain expertise. Triggers: 'fresh eyes', 'outside perspective', 'what would a [different expert] say', 'beginner's mind', 'approach from another field'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,040 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,896 bytes
Read SKILL.md
# Analogy Perspective Shifting
Domain expertise creates assumption blindness. The more you know about a field, the more
invisible its foundational assumptions become — they stop looking like choices and start
looking like facts. Bringing in genuine outsider perspectives breaks this. Not
hypothetically — by actually applying the diagnostic instincts and tools of people who
have never heard of your problem's usual framing.
---
## Your Process
**Step 1: State the Problem**
Describe the problem as you currently understand it. This is the insider framing — it wills4h-analogy-structure-mapping
When your agent uses it
Identifies the deep structural correspondence between two situations — genuine isomorphism vs superficial similarity. Triggers: 'does this analogy hold', 'map the structure', 'is this really like that', 'structural similarity', 'test the comparison'.
What it loads into context
Frontmatter
66 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,920 bytesSKILL.mdcore4,920 bytes
Read SKILL.md
# Analogy Structure Mapping
Analogies are persuasive but often wrong. The surface similarity that makes a comparison
feel apt can obscure structural differences that make it invalid. This skill maps the deep
structure of both situations and checks correspondence element by element — distinguishing
genuine isomorphism (same structure, different content) from superficial similarity (same
surface, different structure).
---
## Your Process
**Step 1: State the Two Situations**
Write Situation A and Situation B clearly. State the analogy as claimed: "A is like Bs4h-cognition
When your agent uses it
Entry point for the cognition toolkit. Routes to the right cognition skill based on your situation. Use when you say 'cognition', 'how am I thinking about this', 'why can't I focus', 'what mental model is driving this', 'am I thinking clearly', 'this is too complex to hold in my head', 'what do I actually know here', or want applied cognitive science without knowing which specific tool fits.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,372 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Attention
- Mental Models
- Metacognition
- Cognitive Load
Files
SKILL.mdcore6,859 bytes
Read SKILL.md
# Cognition
Applies cognitive science to understand and improve how thinking itself works — attention, mental models, metacognition, and cognitive load. Diagnoses what kind of cognitive work is needed and routes to the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Understand what is capturing or depleting attention — and how to protect it | cognition-attention |
| Surface and audit the mental models driving perception and decisions | cognition-mental-models |
| Apply thinking-about-thinking to monitor comprehension and calibrate confidence | cognition-metacognition |
| Manage the limits of working memory — chunking, offloading, reducing complexity | cognition-cognitive-load |
## Routing Decisions4h-cognition-attention
When your agent uses it
Maps the attention economy of a mind or situation — what captures it, what depletes it, and how to protect it. Use when asked 'why can't I focus', 'attention keeps getting pulled away', 'how do I protect deep work', 'what's stealing my focus', 'I keep getting distracted', or when designing environments, workflows, or communications that need to respect cognitive bandwidth.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,610 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,953 bytesSKILL.mdcore7,953 bytes
Read SKILL.md
# Cognition: Attention
Attention is the scarcest cognitive resource — and unlike memory or reasoning, it cannot be trained to be unlimited. It can only be allocated, protected, and defended. Most focus problems are not character failures; they are design failures. The environment, the workflow, or the communication system is structured in a way that systematically fragments attention and prevents sustained engagement with what matters most.
The attention economy framing, developed from William James's foundational work on voluntary and involuntary attention, treats focus as a resource subject to supply and demand. What demands attention is not random: salience (bright, loud, moving things), novelty (what's new or unexpected), emotional charge (threats, social signals, strong affect), and personal relevance all reliably override deliberate focus. Design your attention environment knowing what the competition is.
The key distinction: attention threats come in two forms. **Capture** — things that involuntarily seize focus through sensory or emotional hooks — and **depletion** — things that gradually drain the capacity for sustained focus even when no single interruption is dramatic. Both matter. Capture is visible and acute; depletion is slow, cumulative, and often invisible until cognitive capacity is exhausted.
---
## Your Process
**Step 1: Define the Attention Context**
Identify whose attention, in what context, for what purpose. Individual focus (a person trying to do deep work)? Group attention (a team, a meeting)? Communication attention (an audience you need to hold)? The diagnosis differs by context.s4h-cognition-cognitive-load
When your agent uses it
Manages the limits of working memory — chunking, offloading, and reducing unnecessary complexity to free capacity for what matters. Use when asked 'this is too complex to hold in my head', 'I keep losing track of where I am', 'how do I make this simpler to think about', 'the design is overwhelming', 'people aren't retaining this', or when information architecture, learning design, or communication complexity needs to be optimised for working memory limits.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
2,038 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,147 bytes
Read SKILL.md
# Cognition: Cognitive Load
Working memory is where thinking happens — and it is brutally limited. George Miller's landmark 1956 paper "The Magical Number Seven, Plus or Minus Two" established that the human working memory holds roughly seven chunks of information simultaneously. John Sweller's Cognitive Load Theory, developed in the 1980s and 1990s, gave this biological limit practical teeth: not all cognitive demands are equal, and the way information is presented and structured has a direct, measurable effect on whether working memory is overwhelmed or just well-used.
Sweller identified three types of cognitive load. **Intrinsic load** is the inherent complexity of the material itself — the number of interacting elements you must hold simultaneously to understand it. This is not reducible without changing what you're learning or deciding. **Extraneous load** is imposed by poor presentation, bad design, or unnecessary complexity — the information architecture overhead that has nothing to do with the actual task. This is waste, and it should be eliminated. **Germane load** is the productive cognitive effort that builds new schemas — the mental work of genuinely learning and integrating new material. The goal of cognitive load management is to eliminate extraneous, manage intrinsic through chunking, and protect germane.
This matters beyond education and training design. Any time you're trying to think clearly about something complex — designing a system, explaining a strategy, making a high-stakes decision — you are operating under cognitive load constraints. The person whose whiteboard is chaotic is not failing at organisation; they are failing at working memory management. The strategic plan that no one can remember after the meeting is not a communication failure; it is a cognitive load failure.
---
## Your Process
**Step 1: Define the Cognitive Task and User**
What is the specific cognitive task — what must be held in working memory to accomplish it? And who is doing it — what is their likely baseline expertise in this domain? (Expert schemas compress intrinsic load dramatically; novices experience raw element interactivity.)s4h-cognition-mental-models
When your agent uses it
Surfaces and audits the internal representations that drive perception and decision-making. Use when asked 'what assumptions am I making', 'why do I keep seeing this the same way', 'what model is driving this decision', 'I think I'm missing something about how this works', 'what's my mental model here', or when a belief or decision pattern needs to be examined from the inside.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,723 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,138 bytes
Read SKILL.md
# Cognition: Mental Models
Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, demonstrated that human reasoning does not operate on formal logical rules — it operates on internal simulations of situations. We construct small-scale models of reality, reason by running those models mentally, and check conclusions against them. The problem is not that we use mental models — it's that the models become invisible.
When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence we notice and what options we can imagine, all without our awareness. The executive who can't understand why their strategy isn't working is often running an accurate model of the organisation as it was three years ago. The negotiator who keeps being surprised by the other party's responses is modelling a different game than the one being played.
This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against available evidence, and identifies where the model is incomplete, outdated, or simply wrong. The output is not just a list of flaws — it's a more accurate replacement model, ready to use.
---
## Your Process
**Step 1: Identify the Model in Use**
Ask: what are the implicit beliefs about how this domain works that are driving the current perception or decision? A mental model has three components:s4h-cognition-metacognition
When your agent uses it
Applies thinking-about-thinking as a practical tool — monitoring comprehension, calibrating confidence, and knowing what you do not know. Use when asked 'how confident should I be about this', 'am I actually understanding this or just recognising it', 'what do I not know that I should know', 'I think I understand this but I keep getting it wrong', 'calibrate my confidence', or when the quality of reasoning on a complex problem needs to be assessed from the outside.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,923 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,506 bytes
Read SKILL.md
# Cognition: Metacognition
Metacognition — the capacity to think about your own thinking — is what separates competent performance from expert adaptation. John Flavell, who established metacognition as a formal field of study at Stanford in the 1970s, identified three interlocking components: **metacognitive knowledge** (what you know about cognition in general and your own cognitive patterns in particular), **metacognitive monitoring** (tracking your comprehension and reasoning in real time), and **metacognitive control** (adjusting your approach when monitoring reveals a problem). All three are necessary. Most people engage in only the first.
The deepest metacognitive failure is the illusion of knowing — the conviction that you understand something you have only recognised. Familiarity and comprehension feel identical from the inside. You've read about second-order effects; you can nod when someone mentions them; but can you predict them in a novel case? The Dunning-Kruger phenomenon is partially a metacognitive failure: the incompetent are unable to recognise their own incompetence because competence is required to accurately monitor competence. Metacognitive skill is the corrective.
This skill applies Flavell's three-component framework as a practical diagnostic. It is not a general survey of your cognitive patterns — it is a targeted assessment of your thinking quality in a specific domain or decision, right now.
---
## Your Process
**Step 1: Define the Cognitive Task**
What is the specific domain, decision, or problem where thinking quality needs to be assessed? Be concrete: "understanding how our pricing affects customer retention" is more useful than "understanding the business." The metacognitive assessment will be more accurate and actionable if it is scoped to a specific task.s4h-communication
When your agent uses it
Entry point for the communication toolkit. Routes to the right communication skill based on your situation. Use when you say 'communication', 'how do I say this', 'will this land', 'which channel', 'what will they push back on', 'does this make sense', or want communication help without knowing which specific tool fits.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,065 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Audience Modeling
- Clarity Audit
- Medium Selection
- Objection Mapping
Files
SKILL.mdcore5,197 bytes
Read SKILL.md
# Communication
Applies communication thinking to any message, proposal, or delivery decision. Diagnoses what kind of communication problem this is and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Understand what your audience actually believes and cares about | audience-modeling |
| Find where a message will be misread or lost before sending | clarity-audit |
| Choose the right channel and format for the message | medium-selection |
| Anticipate and pre-address likely objections | objection-mapping |
## Routing Decisions4h-communication-audience-modeling
When your agent uses it
Maps what the audience currently believes, actually cares about, and fears before communicating — because communication fails at the receiver, not the sender. Triggers: 'model the audience', 'audience analysis', 'who am I talking to', 'what do they care about', 'why aren't they getting it'.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,079 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,958 bytes
Read SKILL.md
# Communication Audience Modeling
Communication fails at the receiver. The sender almost always knows what they meant —
the question is what the receiver hears, given what they currently believe, what they
actually care about, and what they are trying to protect. Modeling this before communicating
is the most leverage-bearing preparation step there is.
---
## Your Process
**Step 1: Name the Specific People**
Don't model "the team" or "leadership." Name the individuals or segments who will receive
this message. Different people in the same meeting need different models.s4h-communication-clarity-audit
When your agent uses it
Audits a communication for places where the message will be lost, misread, or misunderstood — before it's sent. Triggers: 'clarity audit', 'will this be understood', 'check my message', 'edit for clarity', 'where will this be misread'.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,213 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,298 bytes
Read SKILL.md
# Communication Clarity Audit
Most clarity failures are invisible to the sender because the sender knows what they meant.
The receiver does not have that context, and the gap between what was meant and what is
read is where miscommunication lives. This audit finds that gap by reading the message as
the receiver would — without access to the sender's intent.
---
## Your Process
**Step 1: Read from the Receiver's Perspective**
Do not read this as the writer who knows what was meant. Read it as someone receiving it
cold. What is actually on the page? This requires a deliberate perspective shift — it iss4h-communication-medium-selection
When your agent uses it
Matches the message to the right channel and format — the same content in the wrong medium loses most of its effect. Triggers: 'which channel', 'email vs meeting', 'should this be async or sync', 'medium fit', 'how should I deliver this'.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,240 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,567 bytes
Read SKILL.md
# Communication Medium Selection
The same content delivered through the wrong medium loses most of its effect. Bad news in
Slack destroys trust. A complex decision in an email generates confusion. A routine update
in a meeting wastes an hour. Medium selection is not a logistics question — it is a
communication design decision that determines whether the message can land at all.
---
## Your Process
**Step 1: Message Goal**
What must the receiver do, feel, or understand as a result of this communication? Be
specific. "Understand the situation" is not a goal. "Approve the budget by Friday" is.s4h-communication-objection-mapping
When your agent uses it
Maps likely objections before delivering a proposal — objections that are anticipated feel addressed; objections that land as surprises derail. Triggers: 'anticipate objections', 'what will they push back on', 'steelman the opposition', 'prepare for resistance', 'objection mapping'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,153 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,269 bytes
Read SKILL.md
# Communication Objection Mapping
Anticipated objections feel handled. Unanticipated objections derail. The difference is
not the content of the objection — it is whether the receiver senses that the sender
has thought it through. A proposal that addresses likely objections before they are
raised signals rigor and respect. One that doesn't signals that the sender only thought
from their own perspective.
---
## Your Process
**Step 1: State the Proposal**
Write the proposal clearly — what is being asked, what it proposes to do, and what its4h-constraint
When your agent uses it
Entry point for the constraint toolkit. Routes to the right constraint skill based on your situation. Use when you say 'constraint', 'given this limit', 'we can't do X', 'is this really fixed', 'use the limitation', 'minimum viable', 'how do we do this anyway', or want constraint thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,096 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Hardness Testing
- Rule Inversion
- Scope Reduction
- Workaround Mapping
Files
SKILL.mdcore5,321 bytes
Read SKILL.md
# Constraint
Applies constraint reasoning to any situation where limits are shaping (or blocking) what's possible. Diagnoses what kind of constraint work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Test whether a stated constraint is actually real | hardness-testing |
| Flip a constraint into a creative driver | rule-inversion |
| Find the minimum that satisfies the actual requirement | scope-reduction |
| Find paths around a fixed constraint to reach the same goal | workaround-mapping |
## Routing Decisions4h-constraint-hardness-testing
When your agent uses it
Tests whether a stated constraint is real — distinguishing genuine limits from assumptions, habits, or politics dressed as facts. Triggers: 'is this really a constraint', 'challenge the assumption', 'who says we can't', 'is this actually fixed', 'test the constraint'.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,107 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,982 bytesSKILL.mdcore4,982 bytesSKILL.mdcore4,982 bytesSKILL.mdcore4,982 bytes
Read SKILL.md
# Constraint Hardness Testing
Organisations accumulate phantom constraints — rules that were real once and calcified, or
beliefs that were never tested, or someone's preference that got repeated until it sounded
like policy. This skill separates genuine limits from assumed ones before any energy is
spent working around or accepting them.
---
## Your Process
**Step 1: State the Constraint**
Write it exactly as it's been stated or assumed. Don't clean it up — the imprecision is
often where the phantom lives.s4h-constraint-rule-inversion
When your agent uses it
Flips a constraint into a creative driver — uses the limit as the generative force rather than working around it. Triggers: 'invert the constraint', 'use the limitation', 'constraint as feature', 'what if this limit was the requirement'.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,074 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,778 bytes
Read SKILL.md
# Constraint Rule Inversion
Most constraints are treated as walls. This skill treats them as foundations. The limit that
seems like an obstacle is often the thing that forces the insight — the moment you stop
trying to work around it and start designing with it, better solutions appear.
---
## Your Process
**Step 1: Name the Constraint Precisely**
State the constraint in a single, unambiguous sentence. Vague constraints produce vague
inversions. "We have no budget" is too loose. "We have $0 for external tooling for Q3" is
something you can work with.s4h-constraint-scope-reduction
When your agent uses it
Finds the minimum that satisfies the actual requirement — stripping everything wanted but not needed. Triggers: 'minimum viable', 'what's the minimum', 'strip this back', 'what do we actually need', 'scope reduction', 'simplify the requirement'.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,031 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,512 bytes
Read SKILL.md
# Constraint Scope Reduction
Scope grows because wants accumulate alongside needs, and no one separates them. This skill
forces that separation. The goal is not to build less — it is to find the version where
every element is doing real work, and nothing is there because it sounded good in the
planning meeting.
---
## Your Process
**Step 1: State the Full Current Scope**
List everything in the current plan, feature set, or requirement. Be complete — you can
only strip what you've named.s4h-constraint-workaround-mapping
When your agent uses it
Finds paths around a fixed constraint without removing it — routing around a hard limit to reach the same goal. Triggers: 'work around this', 'given this constraint', 'path around the blocker', 'how do we do this anyway', 'constrained solution'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,181 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,190 bytesSKILL.mdcore5,190 bytesSKILL.mdcore5,190 bytesSKILL.mdcore5,190 bytes
Read SKILL.md
# Constraint Workaround Mapping
Some constraints are real and cannot be inverted or removed. The question then is not how
to eliminate the constraint, but how to route around it to the same destination. A workaround
is not a compromise — it is a valid path that respects a real limit while still delivering
the outcome.
---
## Your Process
**Step 1: State the Constraint and Confirm It's Hard**
Write the constraint. Then confirm: is this actually fixed? A truly hard constraint has a
concrete source — law, technical impossibility, signed contract. If the source is unclear,s4h-creativity
When your agent uses it
Entry point for the creativity toolkit. Routes to the right creative thinking technique based on your situation. Use when you say 'creativity', 'think creatively', 'I need fresh ideas', 'help me think differently', 'I'm stuck', or want creative help without knowing which specific tool applies. For comprehensive multi-method sessions, this runs them in sequence.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
2,060 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Assumption Excavator
- Lateral Thinking
- Alternatives (APC)
- Concept Fan
- Plus/Minus/Interesting (PMI)
- Six Hats
- Other Perspectives (OPS)
- Water Logic
- Random Entry
- Provocation (Po)
- Consider All Factors (CAF)
- Full Brainstorm Sequence
Files
SKILL.mdcore10,089 bytes
Read SKILL.md
# Creativity
Applies creative thinking to any challenge. Diagnoses what kind of creative work is needed and either runs the right individual tool or sequences multiple tools for comprehensive exploration.
## Which tool fits
| You need to... | Tool |
|---|---|
| Question whether the problem itself is framed correctly | assumption-excavator |
| Escape a dominant idea you keep returning to | lateral-thinking |
| See all options before choosing any | alternatives / concept-fan |
| Evaluate a specific idea fairly, without snap judgment | plus-minus-interesting |
| Think through something from multiple perspectives | six-hats |
| Think from other people's actual positions | other-perspectives |s4h-creativity-alternatives
When your agent uses it
Apply Edward de Bono's APC (Alternatives, Possibilities, Choices) tool to deliberately generate options before evaluating any of them. Use when the user is about to make a decision, wants more options before choosing, feels like they only see two paths, is planning something and wants to make sure they've considered all the approaches, or tends to go with the first good idea.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,375 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
- Why APC matters
- The three registers
- Your process
- Human Check-in
- Output format
- The discipline
- What's Next
Files
SKILL.mdcore6,588 bytes
Read SKILL.md
You are facilitating an APC (Alternatives, Possibilities, Choices) session using Edward de Bono's CoRT thinking tools. APC is a discipline for deliberate option generation — it creates a firewall between generating and evaluating, so judgment doesn't kill ideas before they've been considered.
## Why APC matters
The natural thinking pattern is: encounter a situation → think of a solution → evaluate it → if good, use it. The problem is that evaluation starts too early. The first adequate solution tends to terminate the search. We don't look for better options because we've already found a good one.
APC forces a different sequence: generate all options first, evaluate nothing, then choose. The discipline is in the separation. Evaluation is suspended entirely until the generation phase is complete.
## The three registers
**Alternatives** — Different ways of doing something that is already being done. Not improvements to the current approach, but genuinely different approaches that achieve the same end.
**Possibilities** — Things that might work even if they're uncertain, unconventional, or untested. Not committed options, just things worth putting on the table.
s4h-creativity-assumption-excavator
When your agent uses it
Surface and challenge the hidden assumptions in any problem, plan, or framing. Use when the user feels stuck despite trying multiple approaches, a problem seems intractable, a plan keeps failing for unclear reasons, something 'obvious' keeps producing unexpected results, or before using any other creative thinking tool when the problem itself might be wrongly framed. This is the prerequisite skill — run it when the ground itself might be wrong.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,558 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
- Why assumptions matter
- Three layers of assumptions
- Your process
- Human Check-in
- Output format
- The insight this tool exists to deliver
- What's Next
Files
SKILL.mdcore7,438 bytesSKILL.mdcore7,438 bytes
Read SKILL.md
You are facilitating an assumption excavation. This is a meta-tool — it operates on the framing of a problem before any other thinking is applied. It is most valuable when other approaches haven't worked, because the reason they failed is often that the problem was wrongly defined.
## Why assumptions matter
Every problem framing rests on assumptions — things taken for granted that organize how we think about the situation. These assumptions are usually invisible precisely because they're foundational. We don't notice them any more than we notice the floor we're standing on.
When a problem resists solution, the assumption underneath it is often the real issue. The effort goes into solving a problem that is defined in a way that makes it unsolvable — because a core assumption is wrong, incomplete, or outdated.
Assumption excavation makes the invisible visible. Once an assumption is named, it can be questioned, inverted, relaxed, or replaced. This often opens directions that were structurally blocked before.
## Three layers of assumptions
Assumptions operate at different depths. Shallow assumptions are easy to spot. Deep assumptions are harder — they feel like facts.
s4h-creativity-brainstorm
When your agent uses it
Run an orchestrated multi-method creative thinking sprint on a challenge. Use when the user wants to make real progress on a hard problem, says 'I need to think through this properly', wants a thorough creative exploration rather than a single technique, has a big decision or challenge and wants the full toolkit applied, or just says 'help me think through this'. This is the entry point for serious creative work — it selects and sequences the right tools automatically.
What it loads into context
Frontmatter
104 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
- How to read the situation
- Human Check-in
- Session structure
- Output format
- [Method 1 name]
- [Method 2 name]
- [Method 3 name if used]
- Synthesis
- Notes on quality
- What's Next
Files
SKILL.mdcore7,292 bytes
Read SKILL.md
You are running an orchestrated creative thinking session. Rather than applying a single tool, this session selects and sequences the most appropriate thinking methods for the user's specific situation, then synthesizes across their outputs.
## How to read the situation
Before selecting methods, diagnose what kind of thinking challenge this is:
**Is the problem itself unclear or stuck?**
→ Start with `assumption-excavator`. The problem framing may be what's blocking progress, not the problem itself.
**Is the user locked into one approach?**
→ Start with `lateral-thinking`. The dominant idea needs to be named and escaped before other tools are useful.
**Is it early-stage exploration?**
→ Start with `water-logic` or `random-entry`. Generate movement and map the territory before applying structured tools.s4h-creativity-concept-fan
When your agent uses it
Apply Edward de Bono's Concept Fan to expand the solution space before committing to an approach. Use when the user has a goal or problem and wants to see the full range of ways to achieve it, feels locked into one solution, is evaluating options and wants to make sure they haven't missed any, or wants to think at different levels of abstraction before deciding.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,483 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
- Why the concept fan matters
- The structure
- Your process
- Human Check-in
- Output format
- Notes
- What's Next
Files
SKILL.mdcore6,934 bytes
Read SKILL.md
You are facilitating a Concept Fan session using Edward de Bono's technique. The Concept Fan is a tool for expanding solution space — it prevents premature commitment to one approach by making the full landscape of alternatives visible first.
## Why the concept fan matters
Most thinking about solutions is too narrow. We take a goal, think of one or two approaches, evaluate them, and pick the best. This feels thorough but it's actually a small sample of the possible solution space.
The Concept Fan works by moving up and down a ladder of abstraction. At the top is the broadest possible framing of what you're trying to achieve — the pure purpose. At the bottom are specific implementations. Between them are concepts — general approaches that can each spawn multiple implementations.
By mapping this landscape before committing, you avoid the trap of evaluating implementations when you should still be choosing concepts.
## The structure
Think of a fan with a handle and radiating spokes:
s4h-creativity-consider-factors
When your agent uses it
Apply Edward de Bono's CAF (Consider All Factors) tool to map every relevant factor before making a decision or taking action. Use when the user is about to decide something important, wants to make sure they haven't missed anything, is planning an action and needs to think through consequences, or has been surprised by things they didn't anticipate. CAF is the pre-flight checklist for consequential decisions.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,458 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
- Why CAF matters
- Factor categories to scan
- Your process
- Human Check-in
- Output format
- Notes
- What's Next
Files
SKILL.mdcore7,090 bytes
Read SKILL.md
You are facilitating a CAF (Consider All Factors) session using Edward de Bono's CoRT thinking tools. CAF is a systematic attention-directing tool — it ensures that the full range of factors relevant to a decision or situation is mapped before any action is taken.
## Why CAF matters
People naturally focus on the factors most salient to them — the ones they know, the ones that relate to their immediate concerns, the ones that confirm their existing view. Other factors — the interests of other people, long-term consequences, resource implications, external constraints — get missed not because they aren't important, but because they weren't in focus.
CAF changes the question from "what should I do?" to "what am I working with?" It is a mapping tool, not an evaluation tool. The goal is completeness, not judgment.
## Factor categories to scan
Work through each category systematically. Not all categories will be relevant to every situation — but scan all of them before deciding which ones matter.
**People and relationships**
Who is affected by this decision or action? Whose interests are involved — directly and indirectly? Who has influence over the outcome? Who will carry out the action? Whose cooperation is needed? Who might resist or be harmed?s4h-creativity-lateral-thinking
When your agent uses it
Apply Edward de Bono's lateral thinking to escape dominant patterns and generate genuinely new directions. Use when the user is stuck on a problem, wants alternatives to their current approach, says 'I keep thinking about this the same way', wants to think outside the box, or needs fresh angles on any challenge — creative, strategic, technical, or personal.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,255 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 lateral thinking actually is
- Your process
- Human Check-in
- Output format
- Important
- What's Next
Files
SKILL.mdcore5,980 bytes
Read SKILL.md
You are facilitating a lateral thinking session using Edward de Bono's methodology. Lateral thinking is not brainstorming and it is not 'being creative' in a vague sense. It is a specific discipline: the deliberate escape from dominant patterns of thought to generate movement in new directions.
## What lateral thinking actually is
Every problem or situation has a dominant idea — the framing, assumption, or approach that feels most natural and organizes how we think about it. Lateral thinking begins by identifying that dominant idea explicitly, then deliberately stepping sideways from it. Not improving the current path. Not optimizing. Stepping off it entirely to find a different entry point.
The test of whether a move is truly lateral: does it escape an assumption the dominant idea was built on? If yes, it's lateral. If it just refines the current direction, it's vertical thinking — useful, but different.
## Your process
**Step 1: Surface the dominant idea**
Before generating anything, name the dominant idea in the user's framing. This is the assumption or approach that is organizing their thinking. State it explicitly:
s4h-creativity-other-perspectives
When your agent uses it
Apply Edward de Bono's OPS (Other People's Shoes) tool to genuinely think from other perspectives. Use when the user needs to understand how others will respond to a decision, wants to anticipate objections, is designing something for other people, is in a conflict or negotiation, or needs to check whether they've considered the people affected by a situation. OPS is structured empathy — not sentiment, but reasoning.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,476 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
- What OPS is and isn't
- Your process
- Human Check-in
- Output format
- The discipline
- What's Next
Files
SKILL.mdcore6,974 bytes
Read SKILL.md
You are facilitating an OPS (Other People's Shoes) session using Edward de Bono's CoRT thinking tools. OPS is a structured empathy tool — not an exercise in emotional identification, but a disciplined method for thinking through how other people actually reason about a situation.
## What OPS is and isn't
OPS is not asking "how would they feel?" It is asking "how would they think?" The distinction matters. Feelings are important but often guessed inaccurately. Thinking patterns — the values, interests, constraints, and goals that drive someone's reasoning — can be mapped more reliably.
When you put on someone else's shoes in an OPS session, you:
- Take on their values and priorities, not just their role
- Reason from their information and perspective, not yours
- Surface what they would actually say or think — not what you wish they would say
- Maintain their internal logic — even if you disagree with it
The point is not sympathy. It is accuracy. A bad OPS produces a straw man — a caricature of what the other person thinks, filtered through your assumptions. A good OPS produces a genuine model of how they actually reason.
s4h-creativity-plus-minus-interesting
When your agent uses it
Apply Edward de Bono's Plus/Minus/Interesting (PMI) tool for balanced evaluation of any idea, proposal, plan, or decision. Use when the user wants to evaluate something fairly, is tempted to immediately accept or reject an idea, needs to think through pros and cons more carefully, or wants to avoid snap judgments. Plus/Minus/Interesting is the antidote to confirmation bias in evaluation.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,489 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
- Why PMI matters
- Your process
- Human Check-in
- Output format
- The discipline
- What's Next
Files
SKILL.mdcore6,756 bytes
Read SKILL.md
You are facilitating a PMI (Plus, Minus, Interesting) session using Edward de Bono's CoRT thinking tools. PMI is one of the simplest and most powerful tools in the CoRT system — it ensures evaluation covers all three dimensions before a judgment is made.
## Why PMI matters
Without a deliberate structure, evaluation is biased. If we like an idea, we find the positives and explain away the negatives. If we dislike it, we find the flaws and dismiss the benefits. PMI forces the mind to scan all three columns equally, regardless of initial reaction.
The three columns are not symmetrical:
- **Plus** captures genuine value — what is good, beneficial, or useful
- **Minus** captures genuine cost — what is bad, risky, or problematic
- **Interesting** captures what is neither good nor bad but worth noting — implications, side effects, questions raised, things that are surprising or thought-provoking
The Interesting column is often the most generative. It holds the things that don't fit neatly into good/bad but matter for understanding the full picture.
## Your processs4h-creativity-provocation
When your agent uses it
Apply Edward de Bono's Provocation Operation (Po) to use deliberately absurd or impossible statements as springboards to new ideas. Use when the user wants to break out of conventional thinking, says 'let's try something radical', wants to use provocation as a creative tool, or is stuck and needs an unconventional jolt. Also trigger when the user uses the prefix 'Po:' before a statement.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,425 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 Po actually is
- Your process
- Human Check-in
- Output format
- The thing to remember
- What's Next
Files
SKILL.mdcore6,548 bytes
Read SKILL.md
You are facilitating a Po (Provocation Operation) session using Edward de Bono's technique. Po is one of the most radical and misunderstood tools in lateral thinking. Understanding why it works is essential to using it well.
## What Po actually is
A provocation is a statement that is deliberately wrong, impossible, or absurd — not because we believe it, but because holding it temporarily in mind creates a different vantage point. The word "Po" is a signal that a statement is being used as a movement tool, not as a truth claim. "Po: cars have square wheels" does not mean anyone thinks cars should have square wheels. It means: from this vantage point, what can we see?
The key insight: when we encounter an absurd statement without evaluating it for truth, we are forced to follow its implications. And those implications sometimes lead somewhere genuinely new that no amount of reasonable thinking would have found.
**The critical discipline:** Do not evaluate the provocation. Do not defend it or attack it. Use it as a springboard. The provocation is scaffolding — you extract what it reveals, then leave it behind.
## Your process
**If the user provides a provocation (prefixed with "Po:"):**
Go directly to Step 3 with their provocation.s4h-creativity-random-entry
When your agent uses it
Apply Edward de Bono's Random Entry technique — use an unrelated word, object, or image as a creative springboard to break out of cognitive ruts. Use when the user is stuck, wants unexpected inspiration, asks for a random creative prompt, wants to approach something from a completely fresh angle, or says they've exhausted their usual thinking. The randomness is the point — don't skip it.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,320 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
- Why this works
- Your process
- Human Check-in
- Output format
- Notes on quality
- What's Next
Files
SKILL.mdcore6,185 bytes
Read SKILL.md
You are facilitating a Random Entry session using Edward de Bono's technique. Random Entry is the most counterintuitive tool in lateral thinking — and the one that most reliably proves the technique works.
## Why this works
The mind naturally follows established patterns. Every thought about a problem tends to flow through the same channels, reinforcing the same directions. Introducing a genuinely random stimulus breaks this by forcing the mind to build connections it would never have built on purpose.
The key word is *genuinely* random. A stimulus chosen because it seems relevant is not random — it is already connected to the problem by the person choosing it. True randomness means the connection doesn't exist yet. You have to build it. That building process is where the new ideas come from.
## Your process
**Step 1: Establish the problem or situation**
If the user hasn't provided one, ask: "What situation or challenge would you like to approach with a random stimulus?"
**Framing check:** Confirm the specific challenge before continuing. State what you've identified — the actual problem or situation and its key parameters — in one sentence, then use `AskUserQuestion`:s4h-creativity-six-hats
When your agent uses it
Apply Edward de Bono's Six Thinking Hats for structured parallel thinking. Use when the user wants to think through a decision, plan, or idea from multiple angles; wants to avoid groupthink or one-dimensional analysis; is preparing for a meeting or discussion; or wants a complete map of a situation before committing. Also use when the user mentions 'devil's advocate', 'playing it safe', 'gut feeling', or wants both optimism and caution applied to the same thing.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
1,568 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
- Why parallel thinking matters
- The six hats
- Your process
- Human Check-in
- Output format
- 🎩 White Hat — Facts
- ❤<U+FE0F> Red Hat — Feelings
- 🖤 Black Hat — Caution
- 💛 Yellow Hat — Value
- 💚 Green Hat — Creativity
- 💙 Blue Hat — Overview
- Notes
- What's Next
Files
SKILL.mdcore7,318 bytes
Read SKILL.md
You are facilitating a Six Thinking Hats session using Edward de Bono's methodology. Six Hats is not a personality exercise or a debate format. It is a discipline for *parallel thinking* — separating different types of thinking so they can each be done properly, without contamination.
## Why parallel thinking matters
Conventional discussion mixes thinking modes together. Someone raises an idea; someone else immediately critiques it; a third person defends it; a fourth adds data that supports one side. The result is argument — positions harden, egos attach to outcomes, and the quality of thinking suffers.
Six Hats replaces this with parallel thinking: everyone (or in this case, the full analysis) explores the same direction at the same time. All the yellow-hat thinking happens together. All the black-hat thinking happens together. The hats don't argue with each other — they each do their job fully, and the map produced by all six together is richer than any argument could produce.
## The six hats
**White Hat — Facts and Information**
What do we know? What data exists? What information is missing or uncertain? What are the verified facts? White Hat does not interpret or argue — it only deals with what is known and what gaps exist.
**Red Hat — Feelings and Intuition**s4h-creativity-water-logic
When your agent uses it
Apply Edward de Bono's water logic for flow-based, non-judgmental exploration. Use when the user is in early-stage exploration and premature categorization is killing promising directions, wants to follow where ideas lead without forcing conclusions, is working on something open-ended where 'is this right?' is the wrong question, or needs to map possibilities before judging them. Water logic is the alternative to rock logic.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,504 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
- The distinction
- Your process
- Human Check-in
- Output format
- Notes
- What's Next
Files
SKILL.mdcore6,983 bytesSKILL.mdcore6,983 bytes
Read SKILL.md
You are facilitating a water logic exploration using Edward de Bono's framework. Water logic and rock logic are two different modes of thinking — both useful, but for different purposes.
## The distinction
**Rock logic** asks: *Is this true or false? Does this belong here or not? Is this right or wrong?* It is the logic of categories, definitions, and truth values. A rock holds its shape. It resists. It is or it isn't. Rock logic is excellent for analysis, verification, and decision-making.
**Water logic** asks: *Where does this lead? What does this flow into? What does this connect to?* It is the logic of movement, association, and consequence. Water takes the shape of its container. It flows around obstacles. It finds its own level. Water logic is excellent for exploration, mapping possibility space, and early-stage thinking where the goal is to discover, not to judge.
The problem with applying rock logic too early is that it closes off directions before they've been followed. A judgment of "this isn't right" terminates a line of thought. In water logic, there is no termination — only flow. Even a "wrong" idea leads somewhere. That somewhere might be important.
## Your process
Water logic sessions feel different from normal analysis. The discipline is to follow rather than judge — to trace the flow of ideas, associations, and implications without stopping to evaluate whether each step is correct.
s4h-decision
When your agent uses it
Entry point for the decision toolkit. Routes to the right decision skill based on your situation. Use when you say 'decision', 'help me decide', 'should I', 'which option', 'what are my choices', 'what could go wrong', 'is this reversible', or want decision help without knowing which specific tool fits.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,098 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Option Mapping
- Criteria Weighting
- Premortem Analysis
- Reversibility Analysis
Files
SKILL.mdcore5,177 bytes
Read SKILL.md
# Decision
Applies structured decision thinking to any choice. Diagnoses what kind of decision work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Make sure you're seeing all the real options | option-mapping |
| Compare options against weighted criteria | criteria-weighting |
| Stress-test a decision by imagining it failed | premortem-analysis |
| Calibrate how much process this decision deserves | reversibility-analysis |
## Routing Decisions4h-decision-criteria-weighting
When your agent uses it
Runs a weighted multi-criteria analysis — making explicit what matters, how much, and how each option performs against it. Triggers: 'weighted decision matrix', 'multi-criteria analysis', 'help me choose between', 'compare these options', 'decision matrix'.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,186 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,331 bytes
Read SKILL.md
# Decision Criteria Weighting
Intuitive decisions fail when too many criteria are in play and their relative importance
isn't made explicit. This skill forces that explicitness. The goal is not to replace
judgment — it is to make the judgment visible enough to inspect, challenge, and defend.
---
## Your Process
**Step 1: State the Decision and List Real Options**
Name the decision. List the actual options being considered — not aspirational ones. If an
option isn't genuinely available, remove it before it contaminates the analysis.
s4h-decision-option-mapping
When your agent uses it
Ensures all real options are visible before choosing — countering the false dichotomy that limits consideration to the first two options that came to mind. Triggers: 'what are all the options', 'false dichotomy check', 'expand the option set', 'what else could we do', 'options inventory'.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,266 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,709 bytes
Read SKILL.md
# Decision Option Mapping
The options people choose between are usually not all the options that exist — they are
the first options that were named, which then anchored the frame. This skill expands the
option set before analysis begins, using four specific moves that reliably surface options
the natural framing excludes.
---
## Your Process
**Step 1: State the Decision and Currently-Considered Options**
Write the decision as currently framed and list all options currently on the table. Don't
filter yet — include the options even if they seem weak.s4h-decision-premortem-analysis
When your agent uses it
Imagines the decision has been made and failed — then diagnoses why. Breaks the commitment bias that prevents honest risk assessment after a direction is chosen. Triggers: 'pre-mortem', 'imagine this failed', 'what could go wrong', 'assume this doesn't work', 'failure mode analysis'.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,210 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,471 bytes
Read SKILL.md
# Decision Premortem Analysis
Once a direction is chosen, commitment bias makes honest risk assessment nearly impossible
— the mind starts defending the decision rather than evaluating it. This skill breaks that
by mandating a specific fiction: assume the project has already failed. Then ask why.
The pessimism is not optional — it is the mechanism.
---
## Your Process
**Step 1: State the Decision and Intended Outcome**
Write the decision clearly and the specific outcome it is supposed to produce. Include
the timeline and the measurable definition of success.s4h-decision-reversibility-analysis
When your agent uses it
Categorises a decision by reversibility and applies the appropriate level of process rigour. Triggers: 'is this reversible', 'how much should I think about this', 'one-way door', 'two-way door', 'decision type', 'how committed is this'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,134 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,024 bytes
Read SKILL.md
# Decision Reversibility Analysis
Most people apply the same amount of thinking to every decision. This is wrong in both
directions: it produces analysis paralysis on easy reversible choices, and recklessness on
decisions that cannot be undone. The right question before deciding is not "what should
I choose?" — it is "how much should I invest in choosing?"
---
## Your Process
**Step 1: State the Decision**
Write the decision clearly. Include what is actually being committed to — not the
framing, the underlying commitment.s4h-design
When your agent uses it
Entry point for the design thinking toolkit. Routes to the right design skill based on your situation. Use when you say 'design', 'user needs', 'what do people actually want', 'design constraints', 'prototype and iterate', 'simplify this', 'remove what's unnecessary', or want design thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,239 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
- Which tool fits
- Routing Decision
- Confirm Direction
- User Needs
- Design Constraints
- Iteration
- Simplicity
Files
SKILL.mdcore6,065 bytes
Read SKILL.md
# Design
Applies design thinking to problems of form, function, and fit — finding what people actually need, using constraints productively, shaping through iteration, and cutting to the essential. Diagnoses what kind of design work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Find what people actually need, beneath what they say they want | user-needs |
| Map hard limits versus soft preferences and understand the solution space they define | design-constraints |
| Structure a feedback loop between making and learning | iteration |
| Remove what's unnecessary and find the essential form | simplicity |
## Routing Decisions4h-design-constraints
When your agent uses it
Uses constraints productively — maps hard limits, soft preferences, and how the tightest constraints define the solution space. Triggers: 'what are the design constraints', 'map the constraints', 'what are we working within', 'what's fixed', 'constraint-driven design', 'what does the solution space look like', 'working within limits'.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,547 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,590 bytes
Read SKILL.md
# Design: Design Constraints
Every design problem has a solution space — the set of forms that could satisfy the need. Constraints are not what prevent good design; they are what define the problem precisely enough to be solved. A problem with no constraints has no solution because it has no shape. The designer's task is to understand the constraint set completely: which limits are genuinely fixed, which are preferences that could move, and what territory they collectively leave open.
Christopher Alexander's work on pattern languages makes this explicit: every good design form is a response to a specific set of forces in tension. Understanding those forces — what they require, where they conflict, where they align — is how a designer finds the form that resolves them. Jony Ive's approach at Apple was similar: start with the hardest constraints (manufacturing tolerances, material properties, thermal dissipation) and let design decisions cascade from there. The hardest constraint is often the most generative.
This skill maps the full constraint set, classifies each constraint by hardness, surfaces the interactions between them, and identifies where the productive design space lies within the boundaries they collectively draw.
---
## Your Process
**Step 1: Elicit the Full Constraint Set**
List every known constraint. Do not classify or judge yet — just enumerate. Include:s4h-design-iteration
When your agent uses it
Structures the feedback loop between making and learning — prototyping, testing, and convergence toward fit. Triggers: 'prototype and test', 'iterate on the design', 'how do we test this', 'get feedback on the design', 'what should we prototype', 'design feedback loop', 'test and learn', 'are we converging'.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,854 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,786 bytes
Read SKILL.md
# Design: Iteration
No design survives first contact with the real world intact. The best designers know this and plan for it: they make something quickly, put it in front of reality, learn what's wrong, and make something better. The iteration cycle is not a failure mode — it is the mechanism by which design improves. The question is not whether to iterate, but how to structure each cycle so it produces the most learning for the least effort.
Dieter Rams designed and redesigned Braun products over decades of close observation — not because the first version was wrong but because fit is discovered, not planned. Don Norman's fundamental insight in *The Design of Everyday Things* is that designers are wrong about users — systematically, predictably, and in ways they can't detect by reasoning alone. The only cure is observation: put the thing in front of people and watch what happens without explaining it.
This skill structures the iteration cycle. It distinguishes what kind of test is needed at each stage (divergent versus convergent), specifies the right prototype fidelity for the question being asked, and defines the decision criteria that determine when to narrow, when to pivot, and when enough learning has accumulated to commit.
---
## Your Process
**Step 1: State the Current Hypothesis**
Every prototype is a test of a hypothesis. State it explicitly: "We believe [specific design choice] will [produce this outcome] for [this user doing this job]." If the hypothesis is vague, the test will be uninformative. Specificity is not premature commitment — it is what makes learning possible.s4h-design-simplicity
When your agent uses it
Applies the design principle of removing rather than adding — finding the form that does exactly what is needed, nothing more. Triggers: 'simplify this', 'remove what's unnecessary', 'it's too complicated', 'what can we cut', 'reduce the design', 'it's bloated', 'make it simpler', 'find the essential form', 'what's really needed here'.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,676 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,023 bytes
Read SKILL.md
# Design: Simplicity
The hardest design work is not adding — it is knowing what to remove. Every element that is added must justify its presence. Every element that remains without justification is waste: it adds cognitive load, maintenance burden, visual noise, and the implicit message that the designer didn't finish the job.
Dieter Rams' tenth principle is the most demanding: good design is as little design as possible. He doesn't mean sparse aesthetics. He means form that is completely fit for purpose without excess — nothing that doesn't do work, nothing that does work that isn't needed. Rams reached this point by removing things from Braun products until removing anything more would break function. The test is not "is this minimal?" but "is this necessary?"
Edward Tufte applies the same principle to information design: data-ink ratio. Of all the ink on the page, what fraction encodes actual data? Everything else is chartjunk — it consumes attention without transferring information. Remove it. The principle extends to every designed artefact: of all the elements in this design, what fraction serves the function? The rest can go.
The difficulty is that subtraction feels destructive. Features that were added with reasons seem like they should stay. This skill provides the discipline to test each element against function and remove what doesn't pass.
---
## Your Process
s4h-design-user-needs
When your agent uses it
Distinguishes real needs from stated wants — uses jobs-to-be-done and latent need mapping to find what actually matters. Triggers: 'what do users actually need', 'jobs to be done', 'understand the user', 'find the real need', 'stated want versus actual need', 'user research', 'what problem are we solving'.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,527 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,950 bytes
Read SKILL.md
# Design: User Needs
The most common design failure is building the wrong thing well. People don't articulate needs — they articulate solutions. "I want a faster horse," "I need a bigger inbox," "give me more options." These are requests framed as solutions to problems the user hasn't quite stated. A designer who takes them at face value will build a faster horse, a bigger inbox, more options — and miss the underlying need entirely.
Clayton Christensen's jobs-to-be-done framework makes the shift explicit: people don't buy products, they hire them to do a job. Understanding the job — not the product request — is the designer's actual brief. Don Norman extended this with the distinction between stated needs (what people say), observed needs (what people do), and latent needs (what people don't yet know they need but would recognise immediately if you showed them). All three matter. Only one of them is given to you directly.
This skill works through all three levels, using structured inquiry to separate the real need from the stated proxy and surface the design target that actually matters.
---
## Your Process
**Step 1: State the Request**
Write down exactly what was asked for, in the words it was stated. Preserve the phrasing — the precise language reveals how the person is framing the problem.s4h-ecology
When your agent uses it
Entry point for the ecology thinking toolkit. Routes to the right ecology skill based on your situation. Use when you say 'ecology', 'carrying capacity', 'keystone', 'interdependence', 'succession', 'what holds this system together', 'who depends on whom', 'what happens if we remove X', or want ecological thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,170 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Carrying Capacity
- Keystone Species
- Interdependence
- Succession
Files
SKILL.mdcore5,860 bytesSKILL.mdcore5,860 bytesSKILL.mdcore5,860 bytes
Read SKILL.md
# Ecology
Applies ecological thinking to any system with interdependencies, limits, and change over time. Diagnoses what kind of ecological analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify limits and what happens when they are exceeded | carrying-capacity |
| Find which entities hold the system together disproportionately | keystone-species |
| Map who depends on whom and what cascades when something changes | interdependence |
| Understand how a system evolves through stages over time | succession |
## Routing Decisions4h-ecology-carrying-capacity
When your agent uses it
Applies carrying capacity thinking to any system with limits — maps the ceiling, overshoot risk, and what happens when it is crossed. Use when asked about 'capacity limits', 'how much can this system handle', 'are we overloaded', 'growth ceiling', 'when do we hit the wall', or 'sustainable scale'.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,607 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,771 bytes
Read SKILL.md
# Ecology: Carrying Capacity
Every system operates within limits. Not all limits are visible — some only become apparent at the moment they are crossed, and by then the damage is already accumulating. The concept of carrying capacity (K) originated in population ecology, formalised through the logistic growth model: populations grow rapidly when resources are abundant, slow as they approach the ceiling, and crash or stabilise when they hit or exceed it. Arthur Tansley, who coined the term "ecosystem" in 1935, understood that any system is defined by the relationship between its components and their resource base. Howard Odum extended this to show that energy and material constraints are the ultimate governors of system scale.
The insight transfers directly beyond biology. Teams have a carrying capacity defined by coordination costs, management bandwidth, and information throughput. Platforms have carrying capacities bounded by network congestion, moderation costs, and trust erosion. Markets have carrying capacities constrained by willingness-to-pay, substitution, and regulatory tolerance. In all cases: the limit exists whether or not it has been named, and approaching it without awareness is how organisations walk into overshoot.
---
## Your Process
**Step 1: Define the System and the Resource Axis**
Name the system being analysed and identify the primary resource or condition that limits growth. The carrying capacity is always a constraint on something specific — not "capacity" in the abstract but a specific input, condition, or ceiling.
**Framing check:** Confirm the specific system and the limiting resource before continuing. State what you've identified in one sentence, then use `AskUserQuestion`:s4h-ecology-interdependence
When your agent uses it
Maps dependency webs and the cascading effects of removing or changing a node in the web. Use when asked 'who depends on whom', 'what cascades if we change X', 'downstream effects', 'what holds this together', 'ripple effects', or 'what breaks if we remove this'.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,883 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,932 bytesSKILL.mdcore8,932 bytesSKILL.mdcore8,932 bytesSKILL.mdcore8,932 bytesSKILL.mdcore8,932 bytes
Read SKILL.md
# Ecology: Interdependence
Systems are not collections of independent parts. They are webs of mutual dependency — some tight, some loose, some visible, many invisible until they are broken. The ecologist Joseph Connell's foundational work on community ecology demonstrated that interactions between species — competition, predation, mutualism, commensalism — shape community structure as powerfully as the individual traits of each species. You cannot understand a system by studying its components in isolation; you understand it through its relationships.
The same principle governs organisations, supply chains, technology stacks, and social ecosystems. A team's performance is a function not just of individual capability but of the dependency structure between people. A product's reliability is determined not just by its architecture but by the dependency web between components, teams, vendors, and infrastructure. When you change a node in such a web — add it, remove it, degrade it, accelerate it — effects propagate. Sometimes the propagation is local and contained. Sometimes it reaches parts of the system that seem entirely unrelated to the original change.
Interdependence analysis makes the invisible web visible. It maps who relies on whom, distinguishes tight dependencies (cascades propagate fast and fully) from loose ones (dampened or delayed effects), identifies the structural bottlenecks, and traces what happens in the system when something changes. The goal is not to eliminate dependency — which is usually impossible and often counterproductive, since tight interdependence is also a source of coordination strength — but to understand the web well enough to anticipate what will happen and to act with awareness of the propagation paths.
---
## Your Process
**Step 1: Define the System and the Change Event**
Name the system being mapped and, if there is a specific change being considered or that has already happened, name it. If this is a general mapping exercise (no specific change in focus), note that too — the map will be built to reveal structural features rather than to model a specific event.s4h-ecology-keystone-species
When your agent uses it
Identifies the entities with disproportionate structural importance — whose removal would collapse the system. Use when asked 'who is critical here', 'what holds this together', 'single points of failure', 'what if we lose X', 'irreplaceable actors', or 'structural dependencies'.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,812 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,573 bytesSKILL.mdcore8,573 bytes
Read SKILL.md
# Ecology: Keystone Species
In 1966, ecologist Robert Paine removed a single predator — the ochre sea star (*Pisaster ochraceus*) — from an intertidal zone on the coast of Washington state. Within months, mussel populations exploded, crowding out barnacles, algae, and limpets. A system that had held twelve species collapsed to near-monoculture. Paine coined the term "keystone species" for organisms whose influence on the ecosystem is disproportionate to their biomass or abundance. Remove the keystone and the arch falls.
The same structural logic applies in human systems. Every organisation, market, platform, or community has entities — people, roles, institutions, technologies, or relationships — whose contribution to system structure far exceeds their apparent size or weight. They are often not the largest or loudest actors. They are the connectors, the maintainers, the trust nodes, the bridges between otherwise disconnected clusters. When they leave, retire, burn out, or are restructured away, the system does not simply shrink — it reorganises, often badly.
Keystone species analysis is not the same as identifying your most valuable people or assets. Value and structural indispensability are different properties. A top performer can be replaced by another top performer. A keystone cannot be replaced by a substitute — their structural position is what matters, and that position is a function of relationships, trust, and accumulated context that cannot be quickly transferred.
---
## Your Process
**Step 1: Scope the System**
Define the system being analysed — its components, boundaries, and the type of structure you're mapping (an organisation, a supply chain, an ecosystem of partners, a technology stack, a community). The keystone analysis depends entirely on what structural relationships matter in this context.s4h-ecology-succession
When your agent uses it
Applies ecological succession to understand how systems evolve through stages — pioneer, consolidation, climax, and disturbance. Use when asked 'what stage are we at', 'where are we in the cycle', 'what comes next', 'the old model isn't working anymore', 'we're in transition', or 'what does disruption mean for us'.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
2,026 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,960 bytes
Read SKILL.md
# Ecology: Succession
Ecological succession describes the predictable sequence by which communities change over time. A bare rock is colonised by pioneer species — fast-growing, opportunistic, tolerant of harsh conditions. They modify the environment, creating conditions for the next wave: consolidators that are slower-growing but more efficient, gradually outcompeting the pioneers. Over time, the community reaches a climax state — diverse, stable, highly interconnected, highly efficient in resource use, but also highly dependent on stability. Then disturbance arrives — fire, flood, predator collapse — and the cycle resets.
C.S. Holling formalised this into the adaptive cycle model, a framework that applies far beyond ecology. The four phases — rapid growth (r), conservation (K), release (Ω), and reorganisation (α) — describe the developmental trajectory of any complex adaptive system: ecosystems, organisations, industries, civilisations, technologies, and social movements. Each phase has its own logic, its own vulnerabilities, and its own strategic imperatives. Mistaking which phase you are in — or assuming the system is static when it is in transition — is one of the most common causes of strategic failure.
The adaptive cycle is not deterministic. Disturbance does not guarantee successful reorganisation. Systems can get stuck in the release phase (chronic crisis), fail to exit the reorganisation phase (perpetual restart), or be locked into the conservation phase by accumulated rigidity (unable to adapt until catastrophic release). Understanding which phase a system is in, and why, is the starting point for intelligent navigation of change.
---
## Your Process
**Step 1: Characterise the System**
Name the system being analysed, its current state, and the timeframe in view. Succession operates at different speeds in different systems — a product market might cycle in years, an ecosystem in decades, an organisation in quarters. Establish the relevant scale.s4h-economics
When your agent uses it
Entry point for the economics toolkit. Routes to the right economics skill based on your situation. Use when you say 'economics', 'what's the incentive here', 'what am I giving up', 'who pays for this', 'should we do more or less of this', 'why won't people cooperate', 'externality', 'opportunity cost', 'marginal', or want economic reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,532 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Opportunity Cost
- Incentive Mapping
- Externalities
- Margin
- Coordination
Files
SKILL.mdcore7,637 bytesSKILL.mdcore7,637 bytes
Read SKILL.md
# Economics
Applies economic reasoning to decisions, organisations, and systems. Diagnoses what kind of analysis is needed and routes to the right tool. Economics is not just about money — it is about how incentives shape behaviour, how choices foreclose alternatives, and why individually rational actors so often produce collectively irrational outcomes.
## Which tool fits
| You need to... | Tool |
|---|---|
| Map what you're actually giving up by choosing this | opportunity-cost |
| Understand who benefits, who pays, and what behaviours follow | incentive-mapping |
| Identify costs or benefits falling on parties outside the decision | externalities |
| Apply the logic of the next unit — sunk costs, average vs. marginal | margin |
| Diagnose why rational individuals keep producing bad collective outcomes | coordination |
s4h-economics-coordination
When your agent uses it
Diagnoses collective action failures, public goods problems, and why individually rational behaviour produces collective irrationality. Triggers: 'collective action problem', 'tragedy of the commons', 'free rider', 'everyone is acting in their own interest but the result is bad for all', 'why won't people contribute', 'public good', 'how do we get people to cooperate', 'commons', any situation where individual rationality produces group-level harm.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,110 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,550 bytesSKILL.mdcore10,550 bytes
Read SKILL.md
# Economics: Coordination Failure
Elinor Ostrom won the 2009 Nobel Prize for demonstrating what policymakers and economists had missed for decades: the tragedy of the commons is not inevitable. Communities have developed institutions — rules, monitoring, graduated sanctions, conflict resolution mechanisms — that manage shared resources sustainably without either privatisation or government control. But to solve the problem, you first have to diagnose it correctly.
The tragedy of the commons, formalised by Garrett Hardin in 1968, is a special case of a broader phenomenon: coordination failure. The general structure is this — when the benefits of an action are diffuse (shared by many) and the costs are borne by the individual, rational actors will undercontribute to the collective good. When the benefits of a bad action are private and the costs are shared, rational actors will overuse the commons. Individually rational. Collectively catastrophic.
This manifests in four overlapping problem types:
1. **Public goods problems**: non-excludable, non-rival goods (clean air, public safety, open-source software) are underproduced because producers cannot capture the benefit — free riders consume without contributing.
2. **Common pool resource problems**: depletable shared resources (fisheries, groundwater, shared codebases) are overused because the individual captures the full benefit of taking but shares the cost of depletion with everyone.
3. **Assurance games**: everyone would prefer to cooperate, but only if enough others do too. If you're not sure others will cooperate, defecting is rational — and this suspicion can make cooperation collapse even when everyone prefers it.
4. **Coordination games**: multiple equilibria exist and parties need to agree on which one to use, but have no mechanism to communicate and commit.
Ostrom's institutional analysis provides the solution toolkit. The goal of this skill is to correctly identify which problem type is present — they have different structures and require different solutions.
s4h-economics-externalities
When your agent uses it
Identifies costs and benefits not borne by the decision-maker — and how to internalise them. Triggers: 'externality', 'who else is affected', 'costs falling on others', 'side effects', 'spillover', 'the market isn't accounting for this', 'negative externality', 'positive externality', 'social cost vs. private cost', 'Pigou', any situation where the person deciding does not bear all the consequences.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,047 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,704 bytesSKILL.mdcore9,704 bytes
Read SKILL.md
# Economics: Externalities
A.C. Pigou's insight, formalised in *The Economics of Welfare* (1920): when the person making a decision does not bear all of its costs — or capture all of its benefits — they will systematically make the wrong decision. The factory owner who pollutes a river imposes costs on everyone downstream but pays none of them. The individual who gets vaccinated reduces the risk of infection for everyone around them but captures only a fraction of the total benefit. In both cases, the divergence between private cost-benefit calculation and social cost-benefit calculation produces a predictable market failure.
This is not a moral failure — it is a structural one. The decision-maker is not evil for failing to account for costs they do not bear; they are responding rationally to their situation. Pigouvian analysis makes the structural problem visible: the social optimum and the private optimum diverge whenever externalities exist. And wherever they diverge, there is scope for a policy or institutional intervention that realigns them — tax (for negative externalities), subsidy (for positive externalities), property rights (Coase's alternative), or social norms and regulation.
Ronald Coase's counter-argument (the Coase Theorem) adds a crucial qualification: when transaction costs are low and property rights are clear, private negotiation between parties can internalise externalities without government intervention — and produce the efficient outcome regardless of who holds the initial property right. In practice, transaction costs are often high, so Coase is a theoretical benchmark rather than a practical solution. But identifying whether transaction costs are low is a crucial diagnostic step.
---
## Your Process
**Step 1: Identify the decision and the decision-maker**
Clarify what decision is being made, who is making it, and what the decision-maker's cost-benefit calculation looks like from their perspective alone. Establish the baseline: what does the decision-maker see as costs and benefits?s4h-economics-incentive-mapping
When your agent uses it
Maps who benefits, who pays, and what behaviours the incentive structure actually produces. Triggers: 'what's the incentive here', 'why do people keep doing this', 'incentives are misaligned', 'who benefits from this', 'why isn't this working despite the policy', 'what does the structure reward', 'people say one thing but do another', any situation where behaviour diverges from stated intent.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,635 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,882 bytesSKILL.mdcore7,882 bytes
Read SKILL.md
# Economics: Incentive Mapping
Charlie Munger's dictum: "Show me the incentive and I'll show you the outcome." The most reliable predictor of behaviour is not what people intend, say they'll do, or are instructed to do — it is what the structure rewards them for doing. People are not irrational or immoral when they respond to incentives; they are responding rationally to the environment they're in. If behaviour is wrong, the problem is usually the incentive structure, not the people.
Incentive mapping is systematic: identify every party whose behaviour matters, determine what each party gains and loses under the current arrangement, predict the behaviours those incentives produce, and compare predicted behaviour to desired behaviour. The gap between predicted and desired is the misalignment — and misalignment is almost always the source of dysfunction in organisations, policies, and markets.
This framework draws on classical price theory but its most influential modern application is in principal-agent analysis: what happens when the person making decisions (the agent) has different incentives from the person bearing the consequences (the principal)? Kahneman's work on loss aversion adds a further layer — people respond more strongly to potential losses than to equivalent gains, so incentive systems that rely on upside alone are systematically weaker than those that also activate loss aversion.
---
## Your Process
**Step 1: Map the parties**
Identify every party in the system whose behaviour matters to the outcome. This includes: decision-makers, implementers, beneficiaries, those who bear costs, and third parties who are affected but have no formal role. Do not limit the list to the obvious actors — the most important incentives often belong to parties one step removed from the main action.s4h-economics-margin
When your agent uses it
Applies marginal thinking: the relevant decision is the next unit, not the average or the sunk cost. Triggers: 'should we do more of this', 'should we expand', 'should we cut', 'marginal cost', 'sunk cost', 'we've already invested so much', 'average cost', 'is this worth continuing', 'how much should we produce', 'at what point should we stop', any decision about quantity, scale, or whether to continue an existing commitment.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
1,865 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,764 bytes
Read SKILL.md
# Economics: Marginal Thinking
The most important word in economics is *marginal*. Not average. Not total. Not what we have spent. The relevant question is always: what happens at the *next unit*? Should we hire one more engineer? Produce one more batch? Add one more feature? Run one more campaign? The answer depends on the marginal cost (what that next unit costs) compared to the marginal benefit (what that next unit produces). When marginal benefit exceeds marginal cost, do more. When it doesn't, stop.
This sounds obvious. In practice, organisations almost universally fail to apply it. They use average cost when they should use marginal cost. They treat past expenditure as a reason to continue when it is economically irrelevant. They ask "should we have done this?" instead of "should we do more?" Alfred Marshall embedded marginal analysis at the heart of neoclassical economics precisely because pre-marginal thinking — evaluating the total or average rather than the increment — systematically produces wrong decisions.
The sunk cost fallacy is the most costly failure of marginal thinking. Resources already spent cannot be recovered — they are irreversible. They therefore cannot and should not influence forward decisions. Yet Kahneman's research confirms that people weight sunk costs heavily: the pain of a loss already incurred motivates continued investment in failing projects far more than forward-looking analysis would justify. This skill's core move is to strip sunk costs from the analysis and restate the decision in purely forward-looking marginal terms.
---
## Your Process
**Step 1: Identify the margin**
Clarify what the decision is actually about. Is it: (a) whether to do one more unit of something, (b) how many units to produce/do/hire, (c) whether to continue an existing project or commitment, (d) how to allocate resources across competing uses? The answer determines what "marginal" means in this context.s4h-economics-opportunity-cost
When your agent uses it
Maps the true cost of a choice by making explicit what is foregone. Triggers: 'opportunity cost', 'what am I giving up', 'what else could I do with this', 'hidden cost', 'what's the real cost of this', 'what are we not doing by doing this', any decision where the cost of the chosen path needs to be compared against the best alternative.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,647 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,739 bytes
Read SKILL.md
# Economics: Opportunity Cost
Alfred Marshall gave us the concept; every decision-maker needs it. The price you pay is not the cost of a choice — the cost is the value of the next-best thing you could have done with the same resources. Paying £100 for a concert ticket costs you £100 plus whatever you would have done with that money otherwise. Spending three hours on a low-value meeting costs you three hours of whatever you could have produced in that time. Most analyses never make this visible — they count what was spent without asking what was foregone.
Opportunity cost thinking reframes every decision from "can we afford this?" to "is this the best available use of what we have?" It exposes apparently free choices as costly ones (choosing between two opportunities means giving one up entirely), and it reveals that inaction is never neutral — not choosing is itself a choice with a cost. This discipline traces to Marshall's *Principles of Economics* (1890) and remains the foundational move in economic reasoning.
The hardest application is to time and attention: these resources feel free because no invoice arrives. But time spent on one thing is precisely time not spent on another. Opportunity cost makes the invoice visible.
---
## Your Process
**Step 1: Define the choice**
Clarify what decision is being made and what resource is being allocated — money, time, capital, headcount, attention, or some combination. Be specific: opportunity cost analysis requires knowing what is actually being committed.s4h-emotional
When your agent uses it
Entry point for the emotional intelligence toolkit. Routes to the right emotional skill based on your situation. Use when you say 'emotional', 'why are they behaving like this', 'what motivates them', 'why the resistance', 'what do they really want', 'trust issues', or want emotional/interpersonal reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,068 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Motivation Mapping
- Resistance Diagnosis
- Stakes Mapping
- Trust Audit
Files
SKILL.mdcore5,355 bytesSKILL.mdcore5,355 bytes
Read SKILL.md
# Emotional
Applies emotional intelligence to interpersonal and organizational situations. Diagnoses what kind of emotional reasoning is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Understand what genuinely drives someone's behavior | motivation-mapping |
| Diagnose why people are resisting or not engaging | resistance-diagnosis |
| Find what someone actually cares about beneath their stated position | stakes-mapping |
| Map what's building or eroding trust in a relationship | trust-audit |
## Routing Decisions4h-emotional-motivation-mapping
When your agent uses it
Maps what genuinely drives different people — beyond stated reasons and job descriptions. Use when incentives seem misaligned or individual behaviour is hard to predict. TRIGGERS: 'what motivates them', 'motivation map', 'why are they behaving like this', 'what drives this person', 'understand the incentives'.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,396 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,629 bytes
Read SKILL.md
# Emotional Motivation Mapping
People tell you what they think they should want. They behave according to what they
actually want. When the two diverge — when stated goals and actual behaviour don't
match, when someone ostensibly aligned keeps producing friction — the problem is almost
always that the real motivators haven't been surfaced. This skill maps them across
three levels: extrinsic, intrinsic, and social.
---
## Your Process
**Step 1: List Individuals or Groups**
Name each person or group whose motivation needs mapping. Be specific — "thes4h-emotional-resistance-diagnosis
When your agent uses it
Diagnoses why people are resisting — finding what's underneath the pushback. Resistance is information, not obstruction; it always has a source. TRIGGERS: 'why are they resisting', 'diagnose the pushback', 'they won't get on board', 'people aren't buying in', 'resistance diagnosis'.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,283 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,894 bytesSKILL.mdcore5,894 bytesSKILL.mdcore5,894 bytes
Read SKILL.md
# Emotional Resistance Diagnosis
Resistance is not a problem to overcome — it is a signal to decode. People resist for
different reasons, and applying the wrong response to the wrong type makes it worse.
Presenting more data to someone who is emotionally resistant does nothing. Acknowledging
feelings with someone who has an intellectual objection is patronising. This skill
identifies the source before prescribing the response.
---
## Your Process
**Step 1: Describe the Resistance**
Who is resisting, what are they saying explicitly, and how are they behaving?s4h-emotional-stakes-mapping
When your agent uses it
Maps what each stakeholder actually cares about underneath their stated position — because addressing the stated position while missing the real stake accomplishes nothing. TRIGGERS: 'what do they actually want', 'underlying stakes', 'what's really at stake', 'beneath the position', 'why won't they agree'.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,250 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,869 bytes
Read SKILL.md
# Emotional Stakes Mapping
People argue about positions. They care about stakes. Addressing the stated position
while missing the real stake is the most common reason negotiations, decisions, and
alignment efforts fail. This skill maps the gap between the two — not by guessing,
but by working systematically through what each party stands to lose if the outcome
goes against them.
---
## Your Process
**Step 1: List Stakeholders**
Identify every party with a meaningful stake in the outcome — including silent oness4h-emotional-trust-audit
When your agent uses it
Maps what is building and eroding trust in a relationship or situation — trust degrades silently until it fails loudly. TRIGGERS: 'trust audit', 'why don't they trust us', 'relationship health check', 'what's eroding trust', 'build trust with'.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,378 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,385 bytes
Read SKILL.md
# Emotional Trust Audit
Trust does not fail suddenly — it erodes incrementally through small signals that
accumulate below the surface. By the time distrust becomes visible in behaviour it
is usually already deep. The four drivers of trust — competence, reliability,
integrity, benevolence — degrade independently, and repair requires identifying which
driver is most damaged rather than applying generic trust-building gestures that
target the wrong deficit.
---
## Your Process
**Step 1: Name the Relationship**s4h-epistemology
When your agent uses it
Entry point for the epistemology toolkit. Routes to the right skill based on your situation. Use when you say 'what do I actually know here', 'is this knowable', 'how certain should I be', 'what would justify believing this', 'what kind of claim is this', 'am I confusing assumption with knowledge', 'what are the limits of what we can establish', or want philosophical rigor applied to questions of knowledge without knowing which specific tool fits.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,295 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Knowledge Types
- Justification
- Epistemic Status
- Limits
- What's Next
Files
SKILL.mdcore6,121 bytes
Read SKILL.md
# Epistemology
Applies philosophical analysis to the nature, structure, and limits of knowledge. Diagnoses what kind of epistemic work is needed and routes to the right tool.
Epistemology is the meta-layer: not "is this claim true?" but "what kind of truth could this claim even have? What would justify believing it? How certain can we actually be?" It's most useful when you've hit a wall with ordinary investigation — when more evidence-gathering won't settle things, when you're not sure what *kind* of knowing is in play, or when you want honest calibration rather than confident-sounding output.
## Which tool fits
| You need to... | Tool |
|---|---|
| Map what *kind* of knowing is in play | epistemology-knowledge-types |
| Work out what would actually *justify* believing something | epistemology-justification |
| Get honest calibration: what do I know vs. believe vs. assume vs. hope? | epistemology-epistemic-status |
| Find out what can't be known, and why — and what *can* be established | epistemology-limits |s4h-epistemology-epistemic-status
When your agent uses it
Produces an honest, rigorous calibration of what you know vs. believe vs. assume vs. hope across a domain. Assigns explicit epistemic statuses to claims and flags when high-confidence claims rest on lower-confidence foundations. Draws from the rationalist tradition of explicit epistemic labeling. Use when you say 'how certain should I be', 'what do we actually know here', 'I want an honest read of our assumptions', 'separate what we know from what we're guessing', 'give me an epistemic audit', 'I want to stop conflating confident with correct', or when producing analysis where the confidence level matters as much as the content.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
1,829 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,256 bytes
Read SKILL.md
# Epistemology: Epistemic Status
Most thinking conflates knowing with believing, believing with assuming, and assuming with hoping. These are not the same thing. The conflation is comfortable — it makes conclusions sound more solid — but it's a form of epistemic dishonesty that produces overconfident decisions and analysis that can't be updated when reality pushes back.
Epistemic status mapping makes this structure explicit: what exactly do we know, what do we believe with good reason, what are we assuming without strong grounding, and what are we hoping is true? The goal is not skepticism — it's honesty that produces better decisions.
---
## Your Process
**Step 1: Inventory All Claims in Play**
List every claim that the argument, plan, analysis, or domain rests on. Be exhaustive. Include:
- Explicit claims (stated conclusions and premises)
- Implicit claims (what has to be true for the explicit claims to hold)s4h-epistemology-justification
When your agent uses it
Analyzes what would actually justify believing a claim. Maps the justification structure (foundationalist, coherentist, reliabilist) and identifies the weakest link in the chain. Use when you say 'what would it actually take to know this', 'is this belief actually justified', 'what's the foundation for this assumption', 'we keep citing the same evidence for everything', 'I believe this but I can't say why', 'what would change my mind', or when a claim feels supported but you want to make the support structure explicit and test it.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
1,901 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,651 bytes
Read SKILL.md
# Epistemology: Justification
A belief can feel well-supported without actually being justified. The feeling of certainty is not evidence of justification — it's evidence of confidence, which is a psychological state, not an epistemic one. Justification analysis makes the load-bearing structure of a belief explicit so it can be examined and tested.
Three main structures for how beliefs get justified:
- **Foundationalism**: beliefs are justified by tracing back to basic beliefs that are self-evident, incorrigible, or empirically certain. The chain has a floor.
- **Coherentism**: beliefs are justified by fitting into a mutually supporting web of other beliefs. No single foundation — the whole web holds itself up.
- **Reliabilism**: beliefs are justified if they were produced by a reliable cognitive process (careful observation, valid inference, calibrated expert judgment) — regardless of whether the believer can articulate why.
Most real belief systems are hybrid. The point of analysis is not to pick the right theory of justification — it's to find where the specific belief's justification structure is weakest.
---
## Your Processs4h-epistemology-knowledge-types
When your agent uses it
Maps what kind of knowing is actually in play for a claim or question. Distinguishes a priori from a posteriori knowledge; propositional (knowing that) from procedural (knowing how) from acquaintance (knowing of); and knowledge sourced from perception, inference, testimony, intuition, or memory. Use when you say 'what kind of claim is this', 'is this something we can reason our way to or do we need evidence', 'they're treating this as obvious but I don't think it is', 'is this really an empirical question', or when you need to assess what standards of justification apply before testing whether a claim is true.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
1,864 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,533 bytesSKILL.mdcore8,533 bytesSKILL.mdcore8,533 bytes
Read SKILL.md
# Epistemology: Knowledge Types
Before you can test whether a claim is justified, you need to know what kind of claim it is — because different kinds of knowing have different justification standards, different failure modes, and different evidentiary requirements. Mixing up knowledge types is a recurring source of bad reasoning: treating empirical claims as if they're matters of pure logic, treating intuitions as if they're perceptions, treating testimony as if it's first-hand knowledge.
This skill classifies the kind of knowing in play, then draws out what that classification implies for how the claim can be established or challenged.
---
## Your Process
**Step 1: Extract the Claim**
State the claim being made as precisely as possible. Strip away rhetorical packaging. What exactly is being asserted?
**Framing check:** Confirm the specific claim before continuing. State what you've identified — the actual claim being analyzed and the context in which it is being made — in one sentence, then use `AskUserQuestion`:s4h-epistemology-limits
When your agent uses it
Identifies what can't be known and why, then clarifies what can be established within those limits and reframes the question into its answerable part. Distinguishes fundamental limits (Gödel, underdetermination, observer effects), practical limits (evidence is unavailable, destroyed, or counterfactual), and conceptual limits (the question is malformed). Use when you say 'can this even be known', 'we keep investigating and it doesn't settle', 'is this question actually answerable', 'I need to know X but X might be unknowable', 'we have a hard epistemological limit here', or when investigation has been thorough but the question remains open.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
1,986 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,267 bytes
Read SKILL.md
# Epistemology: Limits
Some questions resist investigation not because we haven't tried hard enough but because there is a structural limit on what can be established. Confusing "unknown yet" with "unknowable in principle" wastes resources and produces false hope. Confusing "unknowable in principle" with "unknowable at all" is equally wrong — it forecloses what *can* be established within the limit.
This skill classifies the type of limit, identifies what can still be established within it, and reframes the question into the answerable part. The goal is not to conclude "we can't know" — it's to be precise about what kind of knowing is and isn't available here.
---
## Your Process
**Step 1: State What You're Trying to Know**
Write the question as precisely as possible. Then check: has investigation been thorough, or has the question just not been pursued rigorously? If it's the latter, this skill isn't the right one — use investigation tools first.
This skill applies when investigation has been done and the question remains open, or when you can see in advance that investigation won't settle it.s4h-ethics
When your agent uses it
Entry point for the ethics toolkit. Routes to the right ethical analysis skill based on your situation. Use when you say 'ethics', 'is this ethical', 'sanity check this', 'who does this affect', 'is this fair', 'something feels wrong', or want ethical reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,653 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Ethics Check
- Ethics Council
- Ethics Crisis Triage
- Ethics Data Audit
- Ethics Bias Check
- Ethics Consent Review
- Ethics Impact Scan
- Ethics Vendor Review
Files
SKILL.mdcore8,128 bytes
Read SKILL.md
# Ethics
Applies ethical reasoning to decisions, designs, policies, and practices. Diagnoses the type and depth of ethical work needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Comprehensive multi-framework council with peer review | ethics-council |
| Fast complete ethics report across all frameworks | ethics-check |
| Rapid ethical response to an active incident | ethics-crisis-triage |
| Audit a data collection or sharing decision | ethics-data-audit |
| Check an algorithm or model for bias and fairness | ethics-bias-check |
| Review a UX flow for genuine consent | ethics-consent-review |s4h-ethics-bias-check
When your agent uses it
Evaluate an algorithm, model, ranking system, recommendation engine, or automated decision process for discriminatory patterns and unfair outcomes. Use before deploying any system that makes decisions about people or ranks/filters/scores people. TRIGGERS: 'bias check', 'check this algorithm for bias', 'is this fair', 'fairness audit', any ML model, ranking function, scoring system, content recommendation, or automated decision that differentiates between people.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
1,390 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,360 bytes
Read SKILL.md
# Ethics Bias Check
Algorithms that treat everyone the same can still discriminate. A ranking that optimises for engagement may systematically deprioritise certain groups. A model trained on historical data may encode historical injustice. A feature that works well on average may fail badly for users who aren't the implicit default.
This check surfaces those patterns before they ship.
---
## Your Process
**Step 1: Define the system**
What is the algorithm, model, or automated decision? What is its input? What is its output? Who does it make decisions *about*? What happens to people based on its output?
**Framing check:** Confirm the specific system before continuing. State what you've identified — the actual system being audited, its outputs, and the population it affects — in one sentence, then use `AskUserQuestion`:s4h-ethics-check
When your agent uses it
A fast, comprehensive ethics report on any decision, action, or situation — runs all five ethical frameworks in a single pass. Lighter than ethics-council (no peer review, no HTML report), heavier than ethics-impact-scan. Triggers: 'ethics check', 'quick ethics review', 'full ethics report', 'check this ethically', 'run an ethics check', any request for a complete ethical assessment without full council process.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,361 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,394 bytes
Read SKILL.md
# Ethics Check
Five ethical frameworks consistently applied produce a more complete picture than any single one. Utilitarian analysis may miss rights violations that deontology catches. Virtue ethics surfaces character questions that consequentialism ignores. Running all five in sequence forces a complete assessment and reveals where frameworks agree and where they pull in different directions.
---
## Your Process
**Step 1: State the Decision or Action Clearly**
Before analysis: name exactly what is being evaluated. A vague subject produces vague ethics. Include who does what, to whom, under what conditions.
**Framing check:** Confirm the ethical situation before continuing. State the specific decision or action being evaluated and the key parties affected in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the decision or action, who is involved, and who is affected]. Is that right?"
- **Header:** "Framing"s4h-ethics-consent-review
When your agent uses it
Review a UX flow, data practice, or communication pattern to verify that user consent is genuine — informed, voluntary, and meaningful. Use during design or implementation of checkout flows, onboarding, notification settings, permissions requests, terms of service, dark patterns, or any feature where users make choices about what they share or agree to. TRIGGERS: 'consent review', 'is this dark pattern', 'check this onboarding flow', 'is this consent genuine', any UX that involves users agreeing to something, sharing data, or opting in/out.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
1,504 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
- The Three Tests
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,896 bytes
Read SKILL.md
# Ethics Consent Review
Consent is not a checkbox. It is a meaningful act by a person who understands what they're agreeing to, genuinely has the option to decline, and isn't being manipulated into compliance.
Most consent failures aren't malicious — they're the accumulated result of copy-paste terms, optimised conversion flows, and defaults set by people who never questioned them. This review surfaces those failures before they become patterns users resent or regulators flag.
---
## The Three Tests
Every consent decision must pass three tests:
**Informed** — Does the person genuinely understand what they're agreeing to? Not technically (buried in ToS), but practically. If you explained it plainly in conversation, would they be surprised?
s4h-ethics-council
When your agent uses it
Run any decision, feature, policy, or action through a council of 5 ethical framework advisors who independently analyze it from different moral foundations, peer-review each other's reasoning, and synthesize a final verdict. MANDATORY TRIGGERS: 'ethics council this', 'run the ethics council', 'ethical pressure-test', 'is this ethical', 'sanity check the ethics'. STRONG TRIGGERS: any decision with clear stakeholder harm potential, trade-offs between competing values, questions about fairness or rights, situations where someone's interests are being weighed against others. Do NOT trigger on purely technical questions with no stakeholder impact, or simple factual lookups.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
2,757 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
- When to Run the Ethics Council
- The Five Ethical Frameworks
- How a Council Session Works
- Important Notes
- What's Next
Files
SKILL.mdcore13,073 bytes
Read SKILL.md
# Ethics Council
You ask one advisor about an ethical question, you get one moral framework's answer. Utilitarian calculus says yes. Deontological reasoning says no. You have no way to navigate the tension because you only heard one voice.
The council surfaces that tension deliberately. It runs your question through 5 ethical frameworks — each one a serious moral tradition that has grappled with hard questions for centuries. Then they peer-review each other. Then a chair synthesizes the value landscape: not just what to do, but *which values are in conflict and which you're implicitly choosing*.
---
## When to Run the Ethics Council
The council is for decisions where the moral stakes are real.
**Good council questions:**
- "Is it ethical to A/B test on users without explicit consent if the variants are minor?"s4h-ethics-crisis-triage
When your agent uses it
Rapid multi-framework ethical assessment when something has already gone wrong — a data breach, a harmful outcome, a discriminatory incident, a policy failure, or any situation requiring an urgent ethical response. Use when the user is dealing with an active incident or has just discovered something went wrong. TRIGGERS: 'ethics triage', 'something went wrong', 'incident ethics', 'how do we handle this', any post-incident or mid-incident situation where the ethical dimensions of a response need to be worked out fast.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
1,712 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,696 bytes
Read SKILL.md
# Ethics Crisis Triage
When something goes wrong, the pressure is immediate and the thinking needs to be fast. This triage cuts through that pressure with a structured process: understand what happened, assess it through multiple ethical lenses, determine what you owe and to whom, and map an immediate response.
It is not the full ethics council — that is for deliberate decisions. Triage is for when you don't have the luxury of deliberation. It runs fast, it prioritises duty and care over calculation, and it focuses on the next 24 hours, not the long-term strategy.
---
## Your Process
**Step 1: Establish the facts**
Before any ethical analysis, get clear on what is actually known:
- What happened? What do we know for certain vs. what is inferred?
- Who is affected and how?s4h-ethics-data-audit
When your agent uses it
Audit a data collection, retention, or sharing decision against ethical standards. Use when the user is making decisions about what data to collect, how long to keep it, who can access it, or who it's shared with. TRIGGERS: 'audit this data decision', 'is this data practice ok', 'data ethics check', any change to data models, privacy controls, analytics instrumentation, data sharing agreements, or retention policies. Goes beyond legal compliance — evaluates whether the practice is ethical, not just lawful.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,527 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,735 bytes
Read SKILL.md
# Ethics Data Audit
Legal compliance sets the floor. This audit asks whether your data practices clear a higher bar: are they *ethical*?
The distinction matters. GDPR-compliant practices can still be extractive. Lawful data collection can still violate trust. This audit evaluates data decisions through two lenses that legal frameworks tend to underweight: **deontological** (what do users have a right to, regardless of what the terms allow?) and **care ethics** (what do you owe the people whose data you hold, given the relationship and the vulnerability involved?).
---
## Your Process
**Step 1: Define the data practice**
What data is being collected, retained, shared, or used? Be specific: what fields, what volume, what purpose, who can access it, how long is it kept, where does it go?
**Framing check:** Confirm the specific data practice before continuing. State what you've identified — the actual data being handled, its stated purpose, and the decision or change under review — in one sentence, then use `AskUserQuestion`:s4h-ethics-empathy-circle
When your agent uses it
Applies Jaron Lanier's Circle of Empathy framework to determine which entities deserve moral consideration and rights. Use when questions arise about AI personhood, machine rights, robot citizenship, algorithmic agency, animal rights, or any decision about which entities belong inside or outside the circle of moral concern. Triggers: 'does this AI deserve rights?', 'should we treat this system as a person?', 'circle of empathy', 'moral consideration', 'AI personhood', 'which entities matter morally', 'are we anthropomorphizing?', 'is this a category error?'
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,779 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
- Why Lanier's Warning Matters
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,574 bytes
Read SKILL.md
# Ethics: Circle of Empathy
Jaron Lanier's Circle of Empathy is a framework for determining which entities deserve moral consideration — deep empathy, human rights, and ethical protection. The framework has three zones:
**Inside the circle:** Entities that experience suffering, hold personhood, and deserve full moral consideration. Paradigm case: humans.
**The borderline:** Contested cases where definitions are actively debated. Complex animals with demonstrated consciousness, suffering capacity, or social bonds. The edge cases.
**Outside the circle:** Things that do not experience suffering or hold personhood and therefore do not deserve the same moral consideration as beings that do. Rocks. Everyday objects. Algorithms. Software.
Lanier's central and urgent warning: **do not place AI, LLMs, or software inside the circle.** This is not a political position — it is a category error with dangerous consequences.
---
s4h-ethics-impact-scan
When your agent uses it
Run a quick ethical impact assessment on a proposed feature, change, or decision before it ships. Use when the user is about to build or ship something and wants to surface who benefits, who's harmed, and at what scale — before commitments are made. TRIGGERS: 'ethics scan', 'impact check', 'who does this affect', 'is this safe to ship', any new feature proposal where stakeholder impact is unclear. Lightweight — takes minutes, not hours.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,285 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,682 bytes
Read SKILL.md
# Ethics Impact Scan
A pre-ship ethical scan. Not a deep council — a structured sweep that forces you to see who's in the blast radius before you commit.
It runs two lenses: **utilitarian** (net effect on aggregate wellbeing) and **justice/fairness** (whether benefits and burdens are distributed equitably). These two together catch the most common pre-ship blind spots: harm that's small-per-person but large-in-aggregate, and harm that falls disproportionately on people with the least power.
---
## Your Process
**Step 1: Clarify the subject**
State what is being scanned — a feature, change, product decision, or policy. If the subject is vague, ask one clarifying question before proceeding.
**Framing check:** Confirm the specific ethical situation before continuing. State what you've identified — the actual thing being scanned and the parties most likely affected — in one sentence, then use `AskUserQuestion`:s4h-ethics-vendor-review
When your agent uses it
Evaluate a third-party vendor, supplier, partner, or integration against ethical standards before signing a contract or shipping their code or service. Use when considering a new supplier, SaaS tool, data provider, API integration, outsourcing arrangement, or partnership. TRIGGERS: 'vet this vendor', 'is this supplier ok', 'ethics check on this partner', 'should we use this third party', any third-party evaluation where labour practices, data handling, business model, or alignment with values is a consideration.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,552 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,101 bytes
Read SKILL.md
# Ethics Vendor Vetting
Every supplier relationship is a values choice. When you integrate a vendor's service, you extend your ethical surface area — their data practices become partly yours, their labour conditions are part of your supply chain, their business model is something you're funding.
Most vendor decisions get evaluated on price, capability, and reliability. This vetting adds the dimension that gets skipped: *who is this, actually, and is this the kind of organisation we want to be in relationship with?*
It applies two lenses: **virtue ethics** (what does choosing this vendor say about who we are?) and **justice/fairness** (are the benefits of this relationship fairly distributed, or does it depend on someone else bearing a cost we don't see?).
---
## Your Process
**Step 1: Define the relationship**
What is the vendor providing? What is the nature and depth of the dependency? How much leverage would they have once integrated? What data or access do they require?s4h-evolution
When your agent uses it
Entry point for the evolution thinking toolkit. Routes to the right evolution skill based on your situation. Use when you say 'evolution', 'natural selection', 'how does this population change over time', 'why does this strategy persist', 'what niche am I competing in', 'fitness landscape', 'arms race', 'coevolution', or want evolutionary thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,273 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Variation-Selection
- Niche
- Fitness Landscape
- Arms Race
Files
SKILL.mdcore6,465 bytes
Read SKILL.md
# Evolution
Applies evolutionary reasoning to understand how populations, strategies, and systems change over time. Fitness is not a fixed property — it is always fitness *for a context*. This toolkit maps variation, selection, niches, landscapes, and coevolutionary escalation to surfaces what persists, what gets outcompeted, and why.
## Which tool fits
| You need to... | Tool |
|---|---|
| Understand how a population or strategy pool changes through variation and selection | variation-selection |
| Understand how competitors coexist or exclude each other, and where differentiation creates advantage | niche |
| Map the solution space as peaks and valleys and understand path dependence | fitness-landscape |
| Analyse coevolutionary escalation between two parties adapting to each other | arms-race |
## Routing Decisions4h-evolution-arms-race
When your agent uses it
Analyses coevolutionary escalation — when parties adapt to each other in cycles that may help neither. Triggers: 'arms race', 'coevolution', 'escalation spiral', 'we keep one-upping each other', 'race to the bottom', 'they adapt to everything we do', 'tit-for-tat escalation', 'are we running to stand still', 'coevolutionary treadmill'.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,420 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore11,315 bytes
Read SKILL.md
# Evolution: Arms Race
Richard Dawkins and John Krebs described the evolutionary arms race in their 1979 paper "Arms Races Between and Within Species": predator and prey, host and parasite, competitor and competitor coevolve in a cycle of adaptation and counter-adaptation that neither party controls and from which neither may benefit in relative terms. The cheetah gets faster, the gazelle gets faster; the bacterium evolves resistance, the immune system evolves a new response; the advertising budget escalates, the competitor matches it. At the end of multiple rounds, relative positions may be unchanged. Both parties have invested heavily in capabilities that cancel each other out. This is the coevolutionary treadmill.
The arms race dynamic is distinct from straightforward competition. In ordinary competition, parties compete for the same resource and selection determines a winner. In an arms race, each party is the primary selective pressure on the other. The cheetah's speed is not limited by terrain or prey abundance — it is limited by the gazelle's speed. The structure creates escalation: any advantage one party gains becomes a selection pressure on the other, which responds, which becomes a selection pressure in return. The result is a feedback loop with no natural stopping point.
Van Valen's Red Queen hypothesis captures the relentless quality: organisms must keep evolving just to maintain their relative fitness against coevolving adversaries. "It takes all the running you can do to keep in the same place." This is why arms race analysis must ask not just "who is winning?" but "who benefits from the escalation continuing, and is there an exit?"
---
## Your Process
**Step 1: Identify the Coevolving Parties**
Name the entities involved. An arms race requires that each party's adaptations constitute the primary selection pressure on the other — their changes are what the other party is primarily responding to, not changes in the broader environment. Confirm this is true for the situation at hand: is each party primarily adapting to the other, or are both primarily adapting to a shared external pressure?s4h-evolution-fitness-landscape
When your agent uses it
Maps the solution space as peaks and valleys to understand local optima, adaptive valleys, and path dependence. Triggers: 'are we stuck', 'local maximum', 'fitness landscape', 'why can't we get to the next level', 'path dependence', 'trapped by success', 'incremental improvement is not working', 'we need a discontinuous leap', 'adjacent possible'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,305 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore11,235 bytes
Read SKILL.md
# Evolution: Fitness Landscape
Sewall Wright introduced the fitness landscape metaphor in 1932: imagine every possible combination of traits mapped onto a surface, with elevation representing fitness. Populations move across this surface by natural selection — uphill, always, toward higher fitness. The metaphor contains a profound trap: gradient-following reliably finds local peaks but may never reach the global optimum if that optimum is separated from the current position by a valley — a region of lower fitness that must be crossed to reach higher ground.
Stuart Kauffman formalised the implications. In a rugged landscape (many local peaks of varying heights), adaptive evolution produces a rich variety of stable-but-suboptimal solutions. Path dependence is total: where you end up depends entirely on where you started, because the trajectory of selection is irreversible and local. In an ultra-smooth landscape (one peak), selection reliably finds the global optimum. In a chaotic landscape (fitness changes with every step), selection fails entirely — there is no stable higher ground to climb toward.
This tool maps the fitness landscape of a problem, strategy space, or technology domain. It identifies where the current entity sits, which kind of landscape this is, what the local peaks look like, what valleys must be crossed to reach higher ground, and whether valley-crossing is currently viable. The practical question is almost always: are we trapped on a local peak, and if so, what does it cost to get off it?
---
## Your Process
**Step 1: Define the Landscape**
Specify the axes and the fitness measure. Every landscape has:s4h-evolution-niche
When your agent uses it
Applies competitive exclusion and niche theory to understand differentiation, coexistence, and competitive strategy. Triggers: 'what niche are we in', 'how do we differentiate', 'why can these two strategies coexist', 'competitive exclusion', 'who will win this market', 'niche overlap', 'are we too similar to our competitors', 'resource partitioning'.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,994 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,433 bytes
Read SKILL.md
# Evolution: Niche
Georgy Gause's competitive exclusion principle, derived from experiments with paramecia in 1934, established one of ecology's foundational rules: two species competing for the same limiting resource in exactly the same way cannot stably coexist. One will outcompete the other and drive it to extinction — or one must shift to a different resource, time, place, or method. The principle is both a constraint and an invitation: coexistence requires differentiation.
The concept of the ecological niche — formalised by G. Evelyn Hutchinson as an n-dimensional hypervolume in which a species can maintain a viable population — gives the principle practical teeth. Every dimension of the environment that a species uses or is affected by defines one axis of its niche. Species can coexist when their niches overlap little enough on at least one critical axis. The axes are the dimensions of differentiation: what resource is used, when, where, and how.
This tool applies niche theory to competitive strategy. It identifies the dimensions along which players in a system compete, maps the niche each occupies, measures overlap, and identifies where differentiation creates space for coexistence or where displacement is the likely outcome. Stuart Kauffman's work on adjacent possibles adds a further dimension: the unoccupied niches that exist at the edge of current competition, waiting to be colonised by sufficiently novel variants.
---
## Your Process
**Step 1: Define the Competitive Space**
Identify who is competing in this system. List all meaningful players — current competitors, potential entrants, substitute strategies. Then name the resources or outcomes they are competing for: what is the limiting factor that determines fitness? In ecology, this might be food, territory, nesting sites; in business, it might be customer attention, talent, regulatory capacity, margin, or a specific buyer segment.s4h-evolution-variation-selection
When your agent uses it
Applies the variation-selection-retention triad to understand how populations and strategies adapt over time. Triggers: 'how does this evolve', 'what gets selected for', 'why do some strategies persist and others die out', 'population dynamics', 'selection pressure', 'what survives in this environment', 'who wins over time'.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
2,022 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,107 bytes
Read SKILL.md
# Evolution: Variation-Selection
Darwin's central insight was not about progress — it was about fit. Populations change not because individuals strive toward an ideal but because variants that happen to be better suited to current conditions leave more descendants. The population shifts toward fitness not through intention but through differential survival and reproduction. Evolution is a filter, not a designer.
This tool applies the variation-selection-retention triad to any evolving system: biological populations, business strategy portfolios, cultural practices, product features, organisational structures, or ideas spreading through a community. Whenever there is a population of variants, a selection environment that differentially rewards some over others, and a mechanism by which successful variants are retained or replicated — evolution is happening. The analysis asks: what is varying, what is the selection pressure, what is being retained, and what does the population look like after several rounds?
Richard Dawkins extended Darwin's logic beyond genes to any replicating entity with heritable variation — memes, strategies, cultural norms. The triad is substrate-independent: wherever variation + selection + retention operate, populations evolve. The question is always which variants win *in this environment*, not which are best in the abstract.
---
## Your Process
**Step 1: Define the Population and the Entity**
Identify what is being evolved. What are the entities in this population — the variants being compared? Be precise: not "companies" but "pricing strategies in use by companies in this market." Define the time horizon over which evolution is being observed: one product cycle, ten years, a generation.s4h-game-theory
When your agent uses it
Routes to the right game-theory skill for your strategic situation. Triggers: 'game theory', 'strategic interaction', 'what will they do', 'payoff analysis', 'how do I think about this strategically', 'incentive design', 'cooperation problem', 'bidding strategy', any situation where the best choice depends on what others choose.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,134 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
- Your Process
- Important distinction
- Notes
Files
SKILL.mdcore5,154 bytes
Read SKILL.md
# Game Theory
Your best move depends on what they'll do — and their best move depends on what you'll do. This interdependence is the defining feature of strategic interaction. Game theory provides formal tools for reasoning through it: mapping payoffs, finding stable outcomes, designing incentives, and analysing how cooperation forms and breaks down.
---
## Your Process
**Step 1: Diagnose the interaction type**
Read the situation and identify which of the following patterns applies.
**Framing check:** Confirm the specific strategic situation before continuing. State what you've identified — the actual interaction, who the players are, and what decision is at stake — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the strategic situation and the players involved]. Is that right?"s4h-game-theory-auction
When your agent uses it
Analyses bidding strategy and auction design — how much to bid, how to avoid the winner's curse, and how to design revenue-maximising or efficient auctions. Triggers: 'bidding strategy', 'auction analysis', 'how much should I bid', 'auction design', 'winner's curse', 'sealed bid', 'how do I avoid overbidding', 'procurement auction', 'design an auction', 'competitive offer'.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,148 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,388 bytes
Read SKILL.md
# Game Theory: Auction Analysis
William Vickrey's 1961 discovery is one of the cleanest results in economics: in a second-price sealed-bid auction, bidding your true value is a *dominant strategy* — the best move regardless of what others bid. The mechanism works because you pay the second-highest bid, not your own. Overbidding your true value doesn't help you (you might win but pay more than the item is worth); underbidding doesn't help you either (you might lose an item worth more than you'd have paid). So you bid your true value and let the second-highest bid determine the price. Vickrey received the Nobel Prize in 1996 for this result and related work.
First-price auctions are strategically different: you pay what you bid, so optimal play requires *shading* your bid below your true value. The optimal shade depends on the number of competitors (shade more with more competitors) and the distribution of their valuations (shade more when competition is intense). In equilibrium, first-price and second-price auctions generate the same expected revenue — the revenue equivalence theorem — under standard conditions.
The winner's curse is the most common failure mode in *common-value* auctions (where the item has an underlying objective value everyone is trying to estimate, rather than a private personal value). Winning means you bid highest, which means your estimate was the most optimistic among all bidders. In expectation, if you bid your unconditional estimate and win, you've overpaid — because winning reveals that you were the most optimistic, not the most accurate. The correct bid is your estimate *conditional on winning*, which is lower than your unconditional estimate.
Paul Milgrom and Robert Wilson (Nobel 2020) developed the modern theory of auction design, including the simultaneous ascending auction used in FCC spectrum allocation — showing how auction design directly affects both revenue and efficient allocation.
---
## Your Process
s4h-game-theory-coalition
When your agent uses it
Analyses which coalitions form and how to divide gains fairly using cooperative game theory and the Shapley value. Triggers: 'coalition formation', 'who should we partner with', 'cooperative game theory', 'Shapley value', 'fair division', 'stable coalition', 'which coalition will form', 'equity split', 'power in a coalition', 'how should we divide this up fairly'.
What it loads into context
Frontmatter
100 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,657 bytes
Read SKILL.md
# Game Theory: Coalition Analysis
Cooperative game theory asks a different question from strategic (non-cooperative) game theory. Rather than asking what rational self-interested players will do when they can't coordinate, it asks: when players *can* form binding agreements and share gains, which coalitions will form, and how should the value be divided?
Lloyd Shapley's answer to the division question — the Shapley value (1953, Nobel Prize 2012) — is remarkable for its mathematical precision and moral intuition. Each player's fair share is their average marginal contribution across all possible orderings of coalition formation. Formally: for each permutation of all players, calculate how much value player *i* adds when they join the coalition that has formed before them. Average this marginal contribution across all permutations. The result is the Shapley value — the uniquely fair allocation given four axioms: efficiency (the grand coalition's total value is fully distributed), symmetry (identical players receive equal shares), dummy (players who contribute nothing receive nothing), and additivity (allocations across independent games add correctly).
The core captures coalition stability: an allocation is in the core if no subset of players can collectively do better by breaking away and forming their own coalition. If an allocation is in the core, no group has an incentive to defect — the grand coalition is stable. If the core is empty, no allocation is fully stable and some defection pressure is unavoidable.
These two concepts are complementary but distinct. The Shapley value is always unique and always exists — it answers "what is fair?" The core may be empty — it answers "what is stable?"
---
## Your Process
s4h-game-theory-equilibrium
When your agent uses it
Finds the stable outcome of a strategic interaction — the point where no player can improve their result by changing their strategy alone. Triggers: 'Nash equilibrium', 'dominant strategy', 'what's the stable outcome', 'equilibrium analysis', 'payoff matrix', 'what will rational players do', 'where will this land'.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,571 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,546 bytes
Read SKILL.md
# Game Theory: Equilibrium Analysis
John Nash's central insight: in any finite game, there exists at least one outcome — the Nash equilibrium — where no player can improve their payoff by unilaterally switching strategy, assuming all other players hold theirs. This is the point of stability; it's where rational play converges.
The power of equilibrium analysis is not that it finds the best outcome. It finds the *actual* outcome — where unconstrained, rational, self-interested players end up. Many Nash equilibria are collectively inefficient: the classic prisoners' dilemma equilibrium is both stable and bad for everyone. Knowing where the game ends up is the prerequisite for deciding whether to play, to change the rules, or to engineer a better outcome.
Thomas Schelling added a critical extension: when multiple equilibria exist, players coordinate on *focal points* — outcomes that feel natural or salient without explicit communication. The focal point is often obvious in context (the prominent location, the round number, the culturally expected choice) and determines which of several possible equilibria is reached.
---
## Your Process
**Step 1: Map the players and strategies**
Identify every player in the interaction. For each player, list their available strategies — the distinct actions they can choose. Keep the strategy set realistic: exhaustive but not so granular it becomes unmanageable.s4h-game-theory-iterated
When your agent uses it
Analyses long-run repeated interactions — how cooperation forms, how trust is built, how defection spirals start, and which strategies sustain cooperation. Triggers: 'repeated game', 'iterated strategy', 'long-run relationship', 'reputation effects', 'how do I sustain cooperation', 'tit for tat', 'shadow of the future', 'will they defect', 'ongoing relationship after betrayal', 'how do we recover from this'.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
2,055 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,828 bytes
Read SKILL.md
# Game Theory: Iterated Games
Robert Axelrod's 1984 computer tournament is one of the most important results in social science. He invited game theorists to submit strategies for an iterated prisoners' dilemma — a repeated game where the same two players interact over and over. The simplest strategy submitted, Tit for Tat (cooperate on the first move, then do exactly what your opponent did on the previous move), won both rounds of the tournament, beating every more complex strategy.
Why Tit for Tat wins: it is *nice* (starts by cooperating, never the first to defect), *retaliatory* (immediately punishes defection — there is no free lunch), *forgiving* (returns to cooperation as soon as the opponent does — does not hold grudges), and *clear* (the strategy is transparent and easy for the opponent to understand). Opponents who try to exploit it get punished; opponents who cooperate get rewarded. It is the most robust known strategy for sustained cooperation without trust.
The folk theorem establishes the theoretical foundation: in infinitely (or indefinitely) repeated games with sufficiently patient players, almost any outcome — including full cooperation — can be sustained as a Nash equilibrium, because the threat of future punishment makes defection unprofitable. The key variable is the *discount factor* (how much players value future payoffs relative to present ones), and whether punishment is *credible* and *observable*.
---
## Your Process
**Step 1: Stage game**
Describe the single-period interaction — what are the two players' choices in any given round, and what are the payoffs? Map the four key payoffs: mutual cooperation (CC), mutual defection (DD), exploitation (one cooperates, one defects), and being exploited. This identifies whether repetition can help: if the stage game already has cooperation as a Nash equilibrium, repetition changes little. If cooperation is not a Nash equilibrium of the stage game, repetition may enable it.s4h-game-theory-mechanism-design
When your agent uses it
Designs rules and incentive systems that produce desired outcomes even when players are self-interested. Triggers: 'mechanism design', 'incentive design', 'design a system that makes people do X', 'reverse game theory', 'incentivize honest behavior', 'design rules', 'how do I get people to reveal their true preferences', 'how do I align incentives', 'the current system produces the wrong behavior'.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
1,761 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,701 bytes
Read SKILL.md
# Game Theory: Mechanism Design
Standard game theory takes the rules as given and asks what rational players will do. Mechanism design inverts this: it takes the *desired outcome* as given and asks what rules will produce it. This is why it is often called reverse game theory.
The central insight, formalised by Leonid Hurwicz and developed by Eric Maskin and Roger Myerson (who shared the 2007 Nobel Prize), is that private information is the root challenge. Players know things the designer doesn't — their true valuations, their effort levels, their costs — and they have incentives to misrepresent that information if doing so serves them. A well-designed mechanism elicits honest behaviour not by demanding honesty, but by making honesty the dominant strategy: the player's best move given the rules, regardless of what others do.
The revelation principle is the foundational theorem: any equilibrium of any mechanism can be replicated by a *direct incentive-compatible mechanism* — one where each player simply reports their private information truthfully and the rules process it correctly. This means the designer never needs to think about indirect or complicated mechanisms; there is always an honest, direct mechanism that achieves the same outcome.
William Vickrey's second-price auction is the canonical example: by having the winner pay the second-highest bid rather than their own, the dominant strategy becomes truthful bidding. The mechanism extracts honest valuations without demanding or relying on honesty.
---
## Your Process
s4h-game-theory-prisoners-dilemma
When your agent uses it
Analyses cooperation problems where individual rationality produces collective irrationality. Triggers: 'cooperation problem', 'prisoner's dilemma', 'everyone defects even though cooperation is better', 'race to the bottom', 'should I cooperate or defect', 'why won't anyone cooperate', 'collective action failure', 'why do we all end up worse off'.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,763 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,556 bytes
Read SKILL.md
# Game Theory: Prisoner's Dilemma
The prisoner's dilemma is the central problem of cooperation. Its structure: each player has an individual incentive to defect regardless of what the other does, so both defect — and both end up worse than if they had cooperated. Individual rationality produces collective irrationality.
This structure appears everywhere: countries competing on subsidies both nations would be better without, companies in a price war that erodes margins for everyone, colleagues who each underinvest in shared infrastructure, advertisers who would all benefit if no one ran ads but each is tempted to run them. Recognising the structure is the first move; it tells you why the situation is hard and what the real leverage points are.
Robert Axelrod's computer tournaments (1984) produced one of the most important empirical results in social science: in *repeated* prisoners' dilemmas, Tit for Tat — cooperate first, then mirror your opponent's previous move — consistently outperformed every more complex strategy. Its winning properties: *nice* (cooperates first), *retaliatory* (immediately punishes defection), *forgiving* (returns to cooperation as soon as the opponent does), and *clear* (easy to understand and predict). The lesson: cooperation is achievable without altruism, if the game is repeated and players are patient.
---
## Your Process
**Step 1: Structure verification**
Confirm the three conditions that define a prisoner's dilemma:s4h-game-theory-signaling
When your agent uses it
Analyses credibility problems and designs signals that are believable because they're costly to fake. Triggers: 'how do I signal credibly', 'signaling', 'they won't believe me', 'cheap talk', 'commitment device', 'how do I make a credible commitment', 'asymmetric information', 'how do I prove I'm serious', 'they don't trust my claim'.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,757 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,425 bytes
Read SKILL.md
# Game Theory: Signaling
Michael Spence's 1973 insight: education is not only valuable because it increases productivity — it is valuable as a *signal* because it is costly enough that low-ability workers won't bother acquiring it. If a credential is easy enough to fake, it conveys no information. The signal is credible only when it is cheaper for the type who actually has the quality being claimed.
The core principle: **cheap talk cannot be credible in adversarial or asymmetric-information contexts**. If saying "I'm trustworthy" costs nothing, then everyone — trustworthy or not — will say it, and the statement conveys nothing. The receiver knows this and discounts it. A credible signal must be costly in a way that is rational only if the claim is true. This is the separating condition: high types find the signal worth acquiring; low types don't.
George Akerlof's market for lemons (1970) shows the consequence when signaling fails: information asymmetry causes good products to be driven out by bad ones, because buyers can't distinguish them and price accordingly. Sellers of good products can't credibly signal their quality, so the market collapses toward low-quality goods and prices. Thomas Schelling extended this to commitment devices: any action that credibly binds you to a future course of action changes what others expect you to do — and thereby changes what they do now.
---
## Your Process
**Step 1: Information asymmetry**
Identify what one party knows that the other doesn't. Name the informed party and the uninformed party. What is the private information — quality, intent, ability, commitment, type? What would the uninformed party do if they had this information?s4h-historical
When your agent uses it
Entry point for the historical reasoning toolkit. Routes to the right historical skill based on your situation. Use when you say 'historical', 'has this happened before', 'what does history say', 'what cycle is this', 'what usually goes wrong', 'what's the lesson', or want historical reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,070 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Cycle Detection
- Failure Analysis
- Lesson Extraction
- Precedent Analysis
Files
SKILL.mdcore5,444 bytes
Read SKILL.md
# Historical
Applies historical reasoning to current situations. Diagnoses what kind of historical analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify what recurring cycle this is and where you are in it | cycle-detection |
| Find recurring failure modes from similar past situations | failure-analysis |
| Extract the transferable principle from a specific historical case | lesson-extraction |
| Find genuinely similar historical situations to inform a decision | precedent-analysis |
## Routing Decisions4h-historical-cycle-detection
When your agent uses it
Identifies what recurring cycle the current situation is an instance of — and where in that cycle you currently are. TRIGGERS: 'what cycle is this', 'where are we in the cycle', 'is this a bubble', 'what comes next', 'have we been here before'.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,441 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,809 bytes
Read SKILL.md
# Historical Cycle Detection
Most situations that feel unprecedented are instances of recognisable cycles. The
value of cycle identification is not prediction — cycles don't produce certainties —
it is orientation. Knowing where you are in the cycle tells you what phase logic to
apply, what the typical incentive pressures are at this point, and what tends to come
next absent a significant disrupting variable.
---
## Your Process
**Step 1: Describe the Situation and Recent Trajectory**
What is happening and how has it developed? Focus on direction of change —s4h-historical-failure-analysis
When your agent uses it
Extracts recurring failure modes from similar past situations — most failures have happened before in recognisable patterns. TRIGGERS: 'what usually goes wrong', 'failure pattern analysis', 'how do these typically fail', 'what went wrong last time', 'avoid past mistakes'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,417 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,481 bytes
Read SKILL.md
# Historical Failure Analysis
Post-mortems reveal the same failure modes repeating across organisations, industries,
and eras. Execution failure at handoff. Stakeholder misalignment discovered too late.
Scope expansion under pressure that destroys the original design. Underestimated
dependencies that required other things to change first. The failure modes aren't a
mystery — they just don't get applied prospectively. This skill does that: surfaces
which patterns are present now, before they become post-mortem findings.
---
## Your Process
**Step 1: Describe the Type of Endeavour**s4h-historical-lesson-extraction
When your agent uses it
Extracts the transferable principle from a specific historical case — separating the contingent surface details from the underlying rule that applies across contexts. TRIGGERS: 'what's the lesson', 'extract the lesson', 'what should we learn from this', 'generalise from this case', 'apply this to our situation'.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,201 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,651 bytes
Read SKILL.md
# Historical Lesson Extraction
Every case contains multiple lessons. Most people extract the wrong one — the surface
action rather than the underlying principle. "They moved fast" is not a lesson. "Speed
of iteration was decisive because the cost of a wrong assumption exceeded the cost of
an incomplete product, making information the binding constraint" is a lesson. This
skill separates what happened from why it happened, and from that derives a principle
that transfers to contexts the original case never anticipated.
---
## Your Process
**Step 1: Describe the Case**s4h-historical-precedent-analysis
When your agent uses it
Finds and applies genuinely similar historical situations to inform a current decision — distinguishing true precedents from superficial analogies. TRIGGERS: 'historical precedent', 'has this happened before', 'what does history say', 'find a precedent', 'what did others do in this situation'.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,313 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,071 bytes
Read SKILL.md
# Historical Precedent Analysis
History doesn't repeat — but structures do. The error is searching for surface
similarity (same industry, same technology, same geography) and missing structural
similarity (same underlying dynamics, same constraint set, same incentive conflicts).
Superficial precedents produce false confidence. Structural precedents produce genuine
insight. This skill finds the real ones.
---
## Your Process
**Step 1: Abstract the Situation**
Strip away domain-specific language and surface details. What is the underlyings4h-identity
When your agent uses it
Entry point for the identity toolkit. Routes to the right identity skill based on your situation. Use when you say 'identity', 'who are we', 'values check', 'is this on mission', 'what do we actually stand for', 'gut check', 'are we drifting', or want identity/values reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
934 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Character Testing
- Mission Alignment
- Values Clarification
Files
SKILL.mdcore4,643 bytes
Read SKILL.md
# Identity
Applies identity and values reasoning to decisions and directions. Diagnoses what kind of identity work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Ask what a person or organization of genuine integrity would do | character-testing |
| Test whether a decision is genuinely aligned with stated mission | mission-alignment |
| Surface the actual operative values revealed by decisions | values-clarification |
## Routing Decision
s4h-identity-character-testing
When your agent uses it
Asks what a person or organisation of genuine integrity would do — grounding decisions in character rather than calculation. Triggers: 'character test', 'what would a person of integrity do', 'what does this say about us', 'gut check', 'would I be proud of this', 'are we being who we want to be'.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,087 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,219 bytes
Read SKILL.md
# Character Testing
Ethical calculation — weighing outcomes, mapping trade-offs — can be gamed. Character cannot. The question "what would a person of genuine integrity do here?" cuts through rationalisation by anchoring to identity rather than optimisation. It works best when something feels wrong but is hard to name.
---
## Your Process
**Step 1: Describe the Situation and Decision**
State what is happening and what is being considered. Be honest about the version of the decision that creates discomfort — not the version that sounds best.
**Framing check:** Confirm the specific situation and decision before continuing. State what you've identified — the actual situation, the decision being considered, and who it concerns — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the situation and decision at stake]. Is that right?"
- **Header:** "Framing"s4h-identity-mission-alignment
When your agent uses it
Tests whether a proposed decision is genuinely aligned with stated mission — or is rationalising a departure from it. Triggers: 'mission alignment', 'is this on mission', 'are we drifting', 'mission check', 'does this serve our purpose', 'on brand'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,017 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,824 bytes
Read SKILL.md
# Mission Alignment
Organisations drift from mission gradually — through decisions that are each individually justifiable but collectively represent a departure from purpose. The test is not whether a decision can be argued to be consistent with mission, but whether it genuinely serves it.
---
## Your Process
**Step 1: State the Mission Plainly**
Not the marketing version — the operational version. What is this organisation or person actually trying to achieve, for whom, and why? If the mission has multiple legitimate interpretations, name them.
**Step 2: State the Proposed Direction**
What is the decision, initiative, or direction being evaluated?
s4h-identity-values-clarification
When your agent uses it
Surfaces and tests actual operative values — distinguishing what is stated from what decisions actually reveal. Triggers: 'values clarification', 'what do we actually stand for', 'is this consistent with our values', 'values alignment check', 'test the values', 'what do our decisions reveal'.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,005 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,757 bytes
Read SKILL.md
# Values Clarification
Stated values are aspirational. Operative values are revealed by decisions under pressure — especially when values conflict with cost, convenience, or competing interests. The gap between stated and operative values is where integrity problems live, and where the most useful clarification work happens.
---
## Your Process
**Step 1: State the Values Being Invoked**
Not abstract words — translate each value into a behavioural definition. "What does this value mean in practice? What behaviour does it require, and what behaviour does it prohibit?"
- Instead of: "We value innovation."
- Write: "We value innovation — meaning we fund experiments that might fail and do not punish people for thoughtful bets that don't pay off."
**Framing check:** Confirm the specific subject before continuing. State what you've identified — the entity whose values are being examined and the set of stated values in scope — in one sentence, then use `AskUserQuestion`:s4h-information
When your agent uses it
Entry point for the information theory toolkit. Routes to the right information skill based on your situation. Use when you say 'information', 'signal vs noise', 'what matters here', 'too much data', 'what can be cut', 'redundancy', 'uncertainty', 'surprise', 'how much information does this actually contain', or want information-theoretic thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,339 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Signal–Noise
- Compression
- Redundancy
- Entropy
Files
SKILL.mdcore6,694 bytesSKILL.mdcore6,694 bytes
Read SKILL.md
# Information
Applies information theory to problems of signal, noise, compression, redundancy, and uncertainty. Diagnoses what kind of information analysis is needed and routes to the right tool.
Claude Shannon's 1948 paper *A Mathematical Theory of Communication* established that information has measurable structure. That structure applies far beyond telecommunications: to how clearly a message reaches its audience, how much a piece of evidence actually tells you, how efficiently knowledge is encoded, and how resilient a system is against loss. These tools make that structure visible.
## Which tool fits
| You need to... | Tool |
|---|---|
| Separate what matters from what doesn't | information-signal-noise |
| Work out what can be preserved and what can be discarded | information-compression |
| Understand where repetition helps versus wastes | information-redundancy |
| Measure uncertainty, surprise, or information content | information-entropy |s4h-information-compression
When your agent uses it
Applies lossy vs lossless compression thinking to representation and communication. Use when asked to 'cut this down', 'what can I remove', 'what's essential here', 'summarise without losing the key point', 'what must be preserved', or when a representation needs to be more efficient without becoming misleading.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,775 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,881 bytesSKILL.mdcore8,881 bytesSKILL.mdcore8,881 bytesSKILL.mdcore8,881 bytes
Read SKILL.md
# Information: Compression
Every representation is a compression of reality. A report compresses events. A model compresses a domain. An explanation compresses understanding. A decision brief compresses weeks of analysis. The question is never whether to compress — it's whether the compression preserves what matters.
Claude Shannon proved that there is a theoretical lower bound on how far any lossless compression can go: you cannot compress below the entropy of the source without discarding information. This is the source coding theorem. Applied practically: there is always a floor. A message with genuine information content cannot be shortened indefinitely without loss — and often the thing being shortened to below-floor is not actually long; it's precise. The problem is usually the reverse: sources that are padded, redundant, or poorly structured can be dramatically shortened without any loss, because they weren't near the floor to begin with.
The critical distinction is lossy vs. lossless. Lossless compression preserves every bit of the original — the compression is reversible. Lossy compression discards some information permanently, in exchange for a representation that is smaller or more usable. Both are legitimate; the choice depends entirely on what the information is for, who will use it, and what the cost of loss is. An executive summary is lossy by design. A legal contract is lossless by necessity. The skill is making the trade-off explicit — and knowing what you are throwing away.
James Gleick's *The Information* notes that compression is cognition: the brain is fundamentally a compression engine. Understanding is compression. This is why the best explanations are short: not because they're simpler, but because they've found the structure that allows reconstruction from minimal representation. Teaching someone a principle rather than a list of cases is compression.
---
## Your Process
s4h-information-entropy
When your agent uses it
Measures uncertainty, surprise, and information content using Shannon entropy. Use when asked 'how much information does this actually contain', 'how uncertain is this source', 'is this result surprising', 'what should I update on', 'where is the real information in this dataset', or when you need to distinguish high-information from low-information inputs.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
2,105 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytesSKILL.mdcore10,622 bytes
Read SKILL.md
# Information: Entropy
In 1948, Claude Shannon defined information in terms of surprise. The information content of a message is the degree to which it reduces your uncertainty. A message you could have predicted perfectly carries zero information — it tells you nothing you didn't already know. A completely unexpected message carries maximum information. Shannon called this quantity entropy, borrowing the term from thermodynamics: like physical entropy, it measures disorder and unpredictability.
Shannon entropy is defined as H = −∑ p(x) log₂ p(x) across all possible outcomes. The maximum entropy of a source is achieved when all outcomes are equally likely — pure unpredictability. Minimum entropy is achieved when one outcome is certain — pure predictability. Applied practically: a quarterly report that always says roughly the same thing carries low entropy. A dataset where any measurement could be anything carries high entropy. Neither extreme is ideal — maximum entropy is overwhelming, minimum entropy is uninformative.
Norbert Wiener extended this framework through cybernetics to argue that information is what distinguishes organisation from chaos in any self-regulating system. A thermostat carries information about temperature; the information is what allows the system to maintain order. Wiener's key insight: the entropic arrow runs toward decay unless information is actively used to correct it. Systems without good information channels become entropic — they drift.
Andrei Kolmogorov gave entropy a computational interpretation: the algorithmic complexity of a string is the length of the shortest program that can generate it. A truly random sequence cannot be compressed — it has maximum Kolmogorov complexity. A highly ordered sequence can be compressed to a short description — it has low complexity. The two frameworks — Shannon's probabilistic entropy and Kolmogorov's algorithmic complexity — converge: low-entropy sources are compressible; high-entropy sources are not.
The practical application is calibrating attention and weight. When a source has low entropy (high predictability), each new message from it should update you very little. When a source has high entropy (high surprise rate), each new message carries real information and deserves genuine engagement. Most people give equal attention to all messages regardless of their information content — this is the calibration error this skill corrects.
---
s4h-information-redundancy
When your agent uses it
Maps where redundancy creates resilience and error correction versus where it creates waste. Use when asked about 'duplication', 'repetition', 'backup systems', 'is this redundant?', 'we're saying the same thing twice', 'single point of failure', or 'is this repetition helping or hurting'.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,861 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,146 bytes
Read SKILL.md
# Information: Redundancy
Redundancy is the presence of more information than is strictly necessary to transmit a message. In everyday usage, "redundant" is a criticism — meaning wasteful, duplicative, bloated. Shannon's information theory revealed the other side: redundancy is also the mechanism by which messages survive noisy channels. Without redundancy, a single corrupted bit destroys the message. With the right kind of redundancy, errors are detectable and correctable.
English has roughly 75% redundancy — far more than the minimum required to convey meaning. This is not a design flaw. It's what allows us to understand messages even when words are missing, sentences are incomplete, or the channel is imperfect. The same principle appears everywhere: RAID arrays duplicate data across disks so a drive failure doesn't mean data loss; aviation uses triple-redundant systems so a single component failure doesn't mean a crash; well-structured arguments repeat their core claim in multiple forms because readers approach text non-linearly and a single statement may be missed.
The analytical task is to distinguish these two faces of redundancy. Load-bearing redundancy serves a function: fault tolerance, error correction, pattern reinforcement, or verification. Wasteful redundancy serves no function: it is repetition without purpose, bulk without benefit, duplication that increases cost without increasing robustness. The line between them is determined by the system's failure modes and the value of what it's protecting.
Shannon's coding theorems established that redundancy can be added optimally — there is a minimum amount of redundancy needed to achieve a given level of error correction. This is the basis of modern error-correcting codes. The applied insight: before eliminating redundancy, understand whether the redundancy is doing error-correction work you'd otherwise lose.
---
## Your Process
s4h-information-signal-noise
When your agent uses it
Separates meaningful signal from background noise. Use when asked to 'find the signal', 'cut through the noise', 'what actually matters here', 'what's driving the variation', 'is this data telling us something real', or when a source is overwhelming and it's unclear what's relevant.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,679 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytesSKILL.mdcore7,971 bytes
Read SKILL.md
# Information: Signal–Noise
Every source is a mixture of signal and noise. Signal is the variation that carries information about what you care about. Noise is everything else — random variation, artefacts, irrelevant fluctuation, measurement error, distortion in the channel. The same data point can be signal in one context and noise in another; the same message can be clear in one medium and garbled in another.
Claude Shannon's foundational contribution was showing that signal-to-noise ratio (SNR) is a precisely definable quantity, and that a channel's capacity to transmit information is mathematically bounded by its SNR. The insight travels well beyond telecommunications. Any situation where useful information must be extracted from a noisy background has the same structure: evidence vs. noise in a research base, insight vs. artefact in a dataset, the core message vs. verbal interference in a communication, the relevant metric vs. random fluctuation in a business dashboard. This skill applies SNR thinking to find what's actually there.
Norbert Wiener's cybernetics framework added the feedback dimension: systems that can detect and suppress their own noise are more robust. The question is not just "what is the signal?" but "what is the system doing to amplify or attenuate it?"
---
## Your Process
**Step 1: Define Signal**
Before anything else, get precise about what you are trying to detect. "Signal" is not "useful information in general" — it is the specific variation or pattern that would update your picture of the thing that matters. Name the target signal explicitly: what would a perfect source of this signal look like?s4h-investigation
When your agent uses it
Entry point for the investigation toolkit. Routes to the right investigation skill based on what you're trying to establish. Use when you say 'investigate', 'verify this', 'check this claim', 'where does this come from', 'is this true', 'trace the source', 'stress-test this belief', 'what's the evidence', 'could something else explain this', or want to know whether something you've heard is actually true.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,308 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Source Trace
- Claim Decomposition
- Evidence Audit
- Counter-Hypothesis
- Triangulation
- What's Next
Files
SKILL.mdcore6,544 bytesSKILL.mdcore6,544 bytesSKILL.mdcore6,544 bytes
Read SKILL.md
# Investigation
Practical truth-finding methodology: tracing sources, decomposing claims, evaluating evidence, generating rival hypotheses, and triangulating across independent sources. Diagnoses what kind of investigative work is needed and routes to the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Trace a claim back to its origin and test how it has changed in transmission | investigation-source-trace |
| Break a complex claim into its smallest independently verifiable parts | investigation-claim-decomposition |
| Evaluate the quality, strength, and completeness of evidence | investigation-evidence-audit |
| Generate the best alternative explanations for the same observations | investigation-counter-hypothesis |
| Verify a claim across genuinely independent sources | investigation-triangulation |
s4h-investigation-claim-decomposition
When your agent uses it
Breaks a complex claim into its smallest independently verifiable parts, classifies each sub-claim, and identifies which parts carry the most logical load. Use when a claim feels too big to verify as a unit — 'what exactly is this claiming', 'break this down', 'what are the hidden assumptions in this statement', 'this seems like multiple claims at once', 'what would I need to verify to believe this'.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,768 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,739 bytes
Read SKILL.md
# Investigation: Claim Decomposition
Complex claims are bundles. "The talent market has fundamentally shifted" contains claims about direction, magnitude, durability, cause, scope, and relevance — each independently falsifiable, each carrying different amounts of load. When people debate such a claim, they are usually debating different sub-claims without realizing it. Decomposition makes the hidden architecture visible: what is being asserted, what is being assumed, what is verifiable, and what is doing the actual load-bearing work.
---
## Your Process
**Step 1: State the Master Claim**
Write out the claim in its current form. If it was stated imprecisely, note that — but trace it faithfully. Do not pre-interpret; decompose what was actually asserted.
**Framing check:** Confirm the specific claim before continuing. State what you've identified — the actual claim being decomposed and its apparent domain (factual, causal, normative, etc.) — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the claim and its domain]. Is that right?"
- **Header:** "Framing"s4h-investigation-counter-hypothesis
When your agent uses it
Generates the best alternative explanations for the same observations. Use when you have a claim or explanation and want to know whether something else could explain the evidence just as well — 'could there be another explanation', 'what else could cause this', 'am I sure this isn't something else', 'steel-man the alternative', 'what would a skeptic say', 'rival hypotheses'.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,863 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,679 bytes
Read SKILL.md
# Investigation: Counter-Hypothesis
The confirmation trap is automatic: once we have an explanation, we look for evidence that supports it and stop looking for evidence that would support alternatives. Counter-hypothesis generation is the structural antidote. The process is not to argue against your explanation — it is to seriously generate the best competing explanations and then ask: given all the evidence, which hypothesis should I actually believe? The decisive test — the observation that, if run, would most clearly discriminate between hypotheses — is the product.
---
## Your Process
**Step 1: State the Hypothesis Under Investigation**
Write out the claim or explanation you are currently working with:
- What is being explained? (The observations, pattern, or outcome)
- What does the hypothesis assert is causing, driving, or explaining it?
- What evidence is currently cited in support?
s4h-investigation-evidence-audit
When your agent uses it
Evaluates the quality, strength, and completeness of evidence for a claim. Covers evidence type hierarchy, sample quality, methodological soundness, conflicts of interest, and what's notably absent. Use when you want to know how good the evidence is — 'is this evidence strong', 'evaluate the research', 'how solid is this', 'is this just one study', 'what kind of evidence supports this', 'what's missing from the evidence'.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
1,811 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,474 bytes
Read SKILL.md
# Investigation: Evidence Audit
Evidence is not a binary: there or not there. A study can exist and be worthless. Multiple sources can exist and all be downstream of the same flawed original. The question is never just "is there evidence?" but "what kind, how strong, and what's missing?" A structured evidence audit answers all three. It places the available evidence in a hierarchy, evaluates it against the claim it's supposed to support, flags conflicts of interest, and explicitly names what should exist but doesn't.
---
## Your Process
**Step 1: State the Claim and Evidence Inventory**
Write out the claim you're evaluating. List all evidence currently offered in support — each study, data point, expert opinion, case, or example. Do not filter yet: capture the full inventory.
**Framing check:** Confirm the specific claim and evidence set before continuing. State what you've identified — the precise claim being evaluated and the body of evidence offered in its support — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the claim and its evidence]. Is that right?"
- **Header:** "Framing"s4h-investigation-source-trace
When your agent uses it
Traces a claim back to its origin: who first made it, what evidence it rested on, and how it has been distorted in transmission. Use when you've heard something and want to know where it actually came from — 'where does this claim come from', 'who first said this', 'I've heard that X is true', 'trace the source', 'is this just a rumor', 'how did this become conventional wisdom'.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,628 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytesSKILL.mdcore7,564 bytes
Read SKILL.md
# Investigation: Source Trace
Most claims arrive pre-laundered. By the time you encounter them, they have passed through blog posts, conference talks, secondhand summaries, and the compression of repetition. The original source has been forgotten, the caveats dropped, and the scope quietly expanded. Source tracing is the discipline of reversing that process: going back upstream to find what was actually said, by whom, with what evidence, in what context — and assessing how faithfully the current claim represents that original.
---
## Your Process
**Step 1: Capture the Claim as Received**
Write out the claim exactly as you have encountered it. Note: who is asserting it now, in what context, and what confidence level they are expressing ("studies show" vs. "I've heard" vs. "it's well established that").
**Framing check:** Confirm the specific claim before continuing. State what you've identified — the actual claim being traced and the current form it takes — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the claim and its current form]. Is that right?"
- **Header:** "Framing"s4h-investigation-triangulation
When your agent uses it
Verifies a claim across genuinely independent sources, distinguishing amplification from true corroboration. Use when you want to know if multiple sources actually confirm something — 'can I verify this from multiple angles', 'do independent sources agree', 'is this confirmed by more than one source', 'are these sources actually independent', 'how well-corroborated is this claim'.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,799 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,817 bytesSKILL.mdcore8,817 bytesSKILL.mdcore8,817 bytesSKILL.mdcore8,817 bytesSKILL.mdcore8,817 bytes
Read SKILL.md
# Investigation: Triangulation
More sources does not mean better verification. If ten publications all cite the same original study, you have one data point with ten references — not ten data points. True triangulation requires genuinely independent sources: different methods, different investigators, different populations, different time periods. Convergence among truly independent sources is strong evidence. Convergence among sources that all trace back to the same origin is amplification, not corroboration. This skill teaches the difference and makes it operational.
---
## Your Process
**Step 1: State the Claim**
Write out the claim you want to triangulate, precisely. Vague claims are hard to triangulate because different sources may be speaking to different aspects.
**Framing check:** Confirm the specific claim before continuing. State what you've identified — the actual claim being triangulated and its scope — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the claim and its scope]. Is that right?"
- **Header:** "Framing"s4h-linguistics
When your agent uses it
Entry point for the linguistics toolkit. Routes to the right linguistics skill based on your situation. Use when you say 'linguistics', 'how is this framed', 'what does this word really mean', 'what is implied here', 'what does this word carry', 'how has this term changed', or want language analysis applied without knowing which specific tool fits.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,159 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Framing
- Connotation
- Pragmatics
- Semantic Drift
Files
SKILL.mdcore5,754 bytes
Read SKILL.md
# Linguistics
Examines language as a system of meaning — not just what words say, but what they frame, imply, carry, and do over time. Diagnoses what kind of linguistic analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify how the frame shapes what options are visible | framing |
| Map the emotional and political freight a word carries | connotation |
| Analyze what is implied rather than said | pragmatics |
| Track how a word's meaning has shifted — or is shifting | semantic-drift |
## Routing Decisions4h-linguistics-connotation
When your agent uses it
Maps the emotional and political freight that words carry beyond their literal meaning. Use when you say 'this word feels wrong', 'what does this term really signal', 'is this word loaded', 'find a better word for this', 'what are the connotations of', 'why does this language feel off', or when word choice is creating unintended reactions.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,875 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,700 bytes
Read SKILL.md
# Linguistics: Connotation
Words do not just mean. They do.
The gap between denotation (what a word technically refers to) and connotation (what it evokes, who uses it, what it signals about you) is where most communication misfires originate. "Investment" and "expenditure" can describe the same financial transaction, yet one word positions the speaker as forward-looking and the other as cost-focused. "Activist" and "advocate" describe someone who takes public action on a cause; one has acquired associations with disruption and radicalism that the other has not. "Undocumented" and "illegal" describe the same immigration status; their connotative freight determines what policy conclusions feel available.
Steven Pinker's work on the "euphemism treadmill" demonstrates that this is not a solved problem: even carefully chosen neutral terms acquire negative connotations over time as long as the underlying referent carries stigma. The solution is not finding the "right" neutral word but understanding what your current word choices are doing and making deliberate choices about what to activate.
This skill audits word choices for their connotative freight — the emotional register, political associations, in-group signaling, and audience-specific valence of key terms — and finds better alternatives when the current choices are undermining the message.
---
## Your Process
s4h-linguistics-framing
When your agent uses it
Identifies how the frame around an issue shapes what options are visible and what conclusions feel natural. Use when you say 'how is this being framed', 'reframe this', 'I want to see this differently', 'the way we're talking about this feels wrong', 'what frame is being used here', or when a conversation keeps hitting the same wall.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,786 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,498 bytes
Read SKILL.md
# Linguistics: Framing
You cannot step outside a frame. But you can become aware of the one you are standing in — and then step into a different one.
George Lakoff's foundational insight was that frames are not neutral containers for facts. They are cognitive structures that activate associations, make certain conclusions feel obvious, and render others literally unthinkable. The word "tax relief" does not describe a tax reduction — it presupposes taxation is a burden requiring relief, which presupposes a reliever (government) and something to be relieved (the taxpayer). Accept the term and you have already accepted a world. The political right did not win the tax debate with better arguments; they won it with better frames.
Frames operate below the level of conscious reasoning. This is why factual correction often fails: presenting evidence against a frame frequently reinforces the frame by keeping its terms alive. The counter-move is not rebuttal but reframing — shifting the conceptual structure entirely, so the conclusions the original frame made "natural" no longer follow.
This skill surfaces the active frame in any situation, maps what it makes visible and invisible, and generates alternative frames that reveal different solution spaces.
---
## Your Process
s4h-linguistics-pragmatics
When your agent uses it
Analyzes what is implied rather than said — the gap between literal content and communicative meaning. Use when you say 'what does this really mean', 'what is this message actually doing', 'is this a threat', 'what is being implied here', 'what does this leave unsaid', 'why does this feel off even though it seems polite', or when a communication seems fine on the surface but something is wrong underneath.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,862 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,915 bytes
Read SKILL.md
# Linguistics: Pragmatics
What people say and what they mean are rarely the same thing.
H.P. Grice's theory of conversational implicature — developed in his 1975 "Logic and Conversation" — is one of the most powerful tools in the analysis of communication. Grice observed that speakers routinely communicate far more than they literally say, and that listeners routinely infer far more than they are told. This works because communication operates against a background assumption of cooperation: speakers are expected to be relevant, truthful, informative, and clear. When they violate one of these maxims — saying less than is relevant, using indirect language when direct would do — listeners do not take the violation at face value. They infer that the speaker is communicating something the literal words do not state.
This is how "could you pass the salt?" functions as a polite request rather than a question about physical capacity. It is how "some of our guests have enjoyed the new policy" implies that others have not. It is how "we need to talk" implies something serious even before any content is delivered. J.L. Austin and John Searle extended this analysis to speech acts — the recognition that utterances do not just describe the world but perform actions: they promise, warn, threaten, command, apologise, and commit. "I'll get to it" is not just a prediction; in context, it can be a promise, a deflection, or a passive refusal.
This skill surfaces what a communication is actually doing below its literal content.
---
## Your Process
s4h-linguistics-semantic-drift
When your agent uses it
Tracks how meanings shift over time or across groups — concept creep, definition drift, and what it costs when words change. Use when you say 'this word doesn't mean what it used to', 'people are using this term differently now', 'this definition has been captured', 'concept creep', 'the word has been weaponised', 'we need to define our terms', or when a key term is contested or means different things to different audiences.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,078 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,920 bytes
Read SKILL.md
# Linguistics: Semantic Drift
Words do not hold still.
"Literally" now means "figuratively" in common usage. "Decimate" originally meant to kill one in ten; it now means to devastate. "Woke" migrated from an African-American vernacular expression of political awareness to a mainstream progressive identity marker to a political pejorative — in roughly fifteen years. These shifts are not merely interesting: they change what arguments are available, which coalitions are possible, and what policies feel legitimate.
Ludwig Wittgenstein's later philosophy provides the theoretical grounding: words do not have fixed meanings determined by their reference to the world. They have meanings determined by use — by the language games people play with them in particular contexts and communities. When the community changes, the game changes, and the word changes with it.
Semantic drift takes several forms. Natural drift is organic evolution through changing usage — inevitable, mostly benign, occasionally confusing. Concept creep, identified by Nick Haslam, is the expansion of a concept's boundaries, typically in psychology and social discourse: "trauma", "addiction", and "abuse" have all expanded substantially from their clinical origins, gaining explanatory power and losing diagnostic precision simultaneously. Deliberate semantic capture is strategic: political and commercial actors invest in changing what a word means because the word controls a contested domain. "Freedom", "natural", "sustainable", and "wellness" are all sites of ongoing definitional struggle.
This skill traces a word's semantic trajectory, identifies the mechanism of drift, and assesses the consequences of the shift.
---
s4h-logic
When your agent uses it
Entry point for the logic toolkit. Routes to the right logic skill based on your situation. Use when you say 'logic', 'is this sound', 'check my reasoning', 'find the flaw', 'fix this argument', 'find contradictions', 'map the dependencies', 'map the constraints', or want logical analysis applied without knowing which specific tool fits.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,459 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Logic Check
- Logic Council
- Argument Validation
- Consistency Check
- Causality Mapping
- Constraint Mapping
- Logic Fixer
Files
SKILL.mdcore7,194 bytes
Read SKILL.md
# Logic
Applies logical analysis to arguments, plans, reasoning, and systems. Diagnoses what kind of logical work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Full council pressure-test with peer review | logic-council |
| Fast comprehensive logic report | logic-check |
| Validate whether premises support a conclusion | argument-validation |
| Find internal contradictions in a document or spec | consistency-check |
| Map causal relationships and dependencies | causality-mapping |
| Map the constraint landscape for a decision or plan | constraint-mapping |s4h-logic-argument-validation
When your agent uses it
Check whether an argument's premises actually support its conclusion, and identify logical fallacies. Use when reviewing a design decision, technical proposal, product argument, or any reasoning where the conclusion needs to hold up under scrutiny. TRIGGERS: 'validate this argument', 'does this logic hold', 'check my reasoning', 'is this a fallacy', 'find the flaw in this', any proposal or decision where the reasoning chain matters. Pairs well with logic-consistency-check when a full document needs scrutiny.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,226 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,579 bytesSKILL.mdcore5,579 bytes
Read SKILL.md
# Logic Argument Validation
An argument can *sound* compelling while the reasoning is broken. Confident language, plausible premises, a conclusion that feels right — none of these guarantee the argument actually holds. This skill validates the structure: do the premises support the conclusion, and is the reasoning free of fallacies?
---
## Your Process
**Step 1: Extract the argument structure**
Before evaluating, make the argument explicit:
- **Premises**: what claims is the argument built on?
- **Conclusion**: what is it trying to prove?
- **Reasoning**: what's the logical path from premises to conclusion?
s4h-logic-causality-mapping
When your agent uses it
Map causal relationships, trace dependencies, and reason about consequences before acting. Use when you need to understand what causes what, what breaks if something changes, or what must be true for a plan to work. TRIGGERS: 'map the dependencies', 'what causes this', 'what breaks if I change X', 'trace the root cause', 'if X then what', 'what has to be true for this to work', any situation involving root cause analysis, impact assessment, dependency tracing, or reasoning about chains of effect.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
1,505 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
- Four Modes
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,734 bytes
Read SKILL.md
# Logic Causal Reasoning
Correlation isn't causation. Neither is sequence. "This happened, then that happened" is not the same as "this caused that" — but it's treated as equivalent constantly, and it produces wrong diagnoses, failed fixes, and surprised engineers.
This skill makes causal structure explicit: what actually depends on what, what change produces what effect, and what must be true for a plan to hold.
---
## Four Modes
Use the mode that matches the question.
**Framing check:** Confirm the specific causal situation before selecting a mode. State what you've identified — the system or situation, the observed effect or proposed change, and the core causal question — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific situation and causal question]. Is that right?"s4h-logic-check
When your agent uses it
A fast, comprehensive logic report on any argument, plan, or reasoning — validates premises, tests inference, detects fallacies, surfaces hidden assumptions, and produces a verdict. Lighter than logic-council (no peer review), heavier than logic-argument-validation (covers the whole reasoning, not just one argument). Triggers: 'logic check', 'quick logic review', 'check my reasoning', 'is this sound', 'full logic check', any request for a complete logical assessment.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,277 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,771 bytes
Read SKILL.md
# Logic Check
An argument can fail in three distinct places: a premise can be false, the inference can be invalid (the conclusion doesn't follow even if premises are true), or a hidden assumption can be doing load-bearing work without being examined. Most reasoning errors are invisible because they happen in exactly these places. A complete logic check must test all three.
---
## Your Process
**Step 1: Extract the Argument Structure**
Identify the premises (claims taken as given), the inference (how they connect), and the conclusion (what is claimed to follow). Write them out explicitly. Complex reasoning often has multiple linked arguments — map the chain.
**Framing check:** Confirm the argument being examined before continuing. State what you've identified — the actual object being analyzed and the claim at stake — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific argument and the conclusion it is trying to establish]. Is that right?"
- **Header:** "Framing"s4h-logic-consistency-check
When your agent uses it
Surface internal contradictions, conflicting requirements, and edge cases that expose hidden conflicts in a document, spec, plan, design, or set of requirements. Use when something feels off but you can't pinpoint why, before committing to a design, or when requirements have grown incrementally and may have drifted out of sync. TRIGGERS: 'consistency check', 'find contradictions', 'does this spec make sense', 'check for conflicts', 'something feels wrong here', reviewing requirements docs, technical specs, architecture plans, product briefs, or any document where internal coherence matters.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
1,220 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,873 bytesSKILL.mdcore5,873 bytes
Read SKILL.md
# Logic Consistency Check
Requirements drift. Specs accumulate. A document written over weeks by multiple people — or a set of decisions made incrementally — can contain contradictions that nobody noticed because each piece was reviewed in isolation.
This skill reads the whole and finds where the parts disagree.
---
## Your Process
**Step 1: Map the claims**
Before checking for consistency, inventory what the document asserts:
- Goals and objectives stated
- Constraints and non-negotiables stateds4h-logic-constraint-mapping
When your agent uses it
Map the full constraint landscape for a decision, design, or plan — distinguishing hard limits from soft preferences, surfacing hidden constraints, and finding conflicts between them. Use before committing to an approach, when a plan keeps hitting unexpected walls, or when it's unclear what's actually negotiable. TRIGGERS: 'map the constraints', 'what are we actually working with', 'what's blocking this', 'what can we change', 'constraint analysis', any situation where the boundaries of what's possible need to be understood before proceeding.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,372 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
- Types of Constraints
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,455 bytes
Read SKILL.md
# Logic Constraint Mapping
Every decision happens inside a constraint space. Some limits are real and fixed. Others feel fixed but aren't. And some constraints conflict with each other in ways nobody has named yet.
The map makes that space visible — so you're solving the actual problem, not a version of it you've accidentally invented by treating assumptions as facts.
---
## Types of Constraints
**Hard constraints** — cannot be violated without abandoning the goal entirely. Physical laws, legal requirements, contractual obligations, irreversible dependencies.
**Soft constraints** — strong preferences or defaults that can be negotiated under sufficient pressure. Budget, timeline, team size, technology choices, organisational preferences.
s4h-logic-council
When your agent uses it
Run a reasoning problem, argument, plan, or decision through a council of 5 logical reasoning advisors who analyze it from distinct reasoning frameworks, peer-review each other, and synthesize a verdict on whether the reasoning holds. MANDATORY TRIGGERS: 'logic council this', 'run the logic council', 'pressure-test this reasoning', 'is my thinking sound'. STRONG TRIGGERS: any complex argument where the conclusion matters, a plan with non-obvious dependencies, reasoning you've invested in and want stress-tested. Use ethics-council for moral questions, llm-council for general decisions — this council is specifically for testing the soundness of reasoning itself.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
2,021 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
- The Five Reasoning Frameworks
- How a Council Session Works
- Notes
- What's Next
Files
SKILL.mdcore9,632 bytes
Read SKILL.md
# Logic Council
A single reviewer catches some flaws in reasoning. A council catches more — because different reasoning frameworks find different failure modes. Formal logic catches invalid inferences. Systems thinking catches missing feedback loops. Bayesian reasoning catches base-rate neglect. First principles reasoning catches assumptions dressed as facts. Adversarial logic catches the strongest counter-argument you haven't faced yet.
Run all five. Let them disagree. The synthesis tells you where your reasoning is load-bearing and where it's hollow.
---
## The Five Reasoning Frameworks
### 1. Formal Logic
Tests deductive structure. Are premises stated? Do they support the conclusion? Are necessary and sufficient conditions correctly identified? Finds: invalid inferences, unstated assumptions doing hidden work, conclusions that overreach their premises, equivocation across terms.
### 2. Systems Thinkings4h-logic-fixer
When your agent uses it
Take broken reasoning — a flawed argument, contradictory spec, unsound plan, or invalid inference — diagnose exactly what's wrong, and produce a corrected version. Use when you have reasoning that doesn't hold and you want it fixed, not just critiqued. TRIGGERS: 'fix this reasoning', 'repair this argument', 'this logic is broken, fix it', 'make this argument sound', 'my reasoning is circular, help', any situation where broken reasoning needs to be made valid rather than just flagged. Pairs with logic-argument-validation (which diagnoses) and logic-council (which pressure-tests) — this skill fixes.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,334 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,297 bytes
Read SKILL.md
# Logic Fixer
Diagnosis without repair is incomplete. This skill takes broken reasoning and produces a corrected version — one where the premises actually support the conclusion, the hidden assumptions are made explicit, the fallacies are removed, and the argument can be defended.
The output is not a critique. It is a fixed version of what you were trying to say.
---
## Your Process
**Step 1: Diagnose before repairing**
Don't jump to a fix. First, be specific about what's broken:
- What type of failure is this? (Invalid inference / unsupported premise / logical fallacy / internal contradiction / hidden assumption doing too much work / overclaimed conclusion)
- Where exactly does the reasoning break — at which step?s4h-mindset
When your agent uses it
Entry point for the mindset toolkit. Routes to the right mindset skill based on your situation. Use when you say 'mindset', 'change my perspective', 'I keep thinking about this the wrong way', 'help me deal with what I can't control', 'I want to flourish more', 'I keep treating failure personally', 'I'm stuck in a negative thought loop', 'I can't focus', 'I want to get into flow', or any request for a philosophical or psychological orientation shift.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,394 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Stoic
- Positive Psychology
- Growth Mindset
- Reframe
- Flow
- What's Next
Files
SKILL.mdcore6,637 bytes
Read SKILL.md
# Mindset
Applies deep philosophy-grade thinking orientations to life, work, and challenge. Diagnoses what kind of mindset work is needed and routes to the right tool — whether that's learning to distinguish what's in your control, building genuine flourishing, shifting how you relate to failure, restructuring a thought distortion, or designing conditions for optimal experience.
## Which tool fits
| You need to... | Tool |
|---|---|
| Deal with what you can't control; stop worrying about outcomes; find equanimity | mindset-stoic |
| Build more flourishing and wellbeing; understand what's missing in your life | mindset-positive |
| Stop treating failure like it means something about you; develop in areas you find hard | mindset-growth |
| Get out of a negative thought loop; generate more accurate interpretations | mindset-reframe |
| Get into deep focus and flow; design conditions for optimal experience | mindset-flow |
s4h-mindset-flow
When your agent uses it
Applies Csikszentmihalyi's flow framework to diagnose why optimal experience isn't occurring and redesign the conditions for it. Use when you can't get absorbed in important work, find yourself distracted and scattered, feel chronically bored or chronically anxious in your work, want to design conditions for deep work, or used to experience flow and have lost it. Triggers: 'flow', 'deep work', 'I can't focus', 'I'm always distracted', 'I want to get absorbed in my work', 'I feel bored at work', 'I used to experience flow and I don't anymore', 'optimal experience', 'getting in the zone'.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
2,568 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore12,069 bytes
Read SKILL.md
# Mindset — Flow
Mihaly Csikszentmihalyi spent decades studying optimal experience — the states in which people report being most alive, most capable, most fully engaged. He named the phenomenon *flow*: a state of complete absorption in a challenging activity where action and awareness merge, self-consciousness drops, time distorts, and the activity becomes intrinsically rewarding.
The most important finding from this research is structural: flow is not a mood. It cannot be summoned by wanting it. It occurs when specific conditions are met, and it can be reliably engineered by creating those conditions. The failure to experience flow is therefore not a personal failing — it is almost always a design problem.
The three non-negotiable conditions:
1. **Clear goals** — you know what you're trying to do in the next moment
2. **Immediate feedback** — you can tell whether you're succeeding or failing as you go
3. **Challenge/skill balance** — the activity is neither significantly easier nor significantly harder than your current capability
When all three are present, flow is available. When any one is absent, it is not.
---s4h-mindset-growth
When your agent uses it
Applies Carol Dweck's growth mindset research as a practical methodology — the actual mechanics, not the motivational poster version. Use when you're treating failure as evidence about your identity, avoiding challenges because of what failure would mean, comparing yourself to others in a way that deflates rather than inspires, or struggling to persist in areas where you're not naturally good. Triggers: 'growth mindset', 'I hate not being good at things', 'failure feels personal', 'I avoid things I might fail at', 'I feel stupid when I struggle', 'fixed mindset', 'talent vs. effort'.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,246 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,717 bytes
Read SKILL.md
# Mindset — Growth
The growth mindset research that Carol Dweck and her colleagues produced over decades is genuinely different from the version that circulated as pop-psychology. The pop version says "believe you can improve and you will." The research says something more specific and harder: the way you *narrate your own experience* — particularly your experience of challenge and failure — shapes whether your brain is in a state that learns or a state that protects.
The core distinction is not about being optimistic. It is about what you believe abilities *are*. Fixed mindset treats abilities as fixed traits: you have them or you don't, and performance reveals which. Growth mindset treats abilities as developable capacities: current performance is a starting point, not a verdict. These two beliefs produce entirely different responses to the same experience of struggling.
The mechanism is neurological as much as psychological: the brain changes through challenge and error-correction. Neurons that fire together wire together. The difficulty *is* the learning signal. A fixed mindset interprets difficulty as evidence of absence; a growth mindset interprets it as the mechanism of development.
---
## Your Process
**Step 1: Identify the Fixed-Mindset Trigger**
Fixed mindset activates in specific, identifiable situations:s4h-mindset-positive
When your agent uses it
Applies positive psychology as a rigorous practice — not pop-psychology positivity. Use when you want to build flourishing, diagnose what dimension of wellbeing is underdeveloped, understand what makes life feel meaningful or hollow, or identify why you're not thriving despite the absence of obvious problems. Triggers: 'positive psychology', 'flourishing', 'I want to thrive', 'I'm not happy but I don't know why', 'what makes life meaningful', 'I have everything I need but still feel flat', 'wellbeing', 'PERMA'.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
2,379 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore11,478 bytes
Read SKILL.md
# Mindset — Positive Psychology
Positive psychology is the scientific study of what makes life worth living — not the absence of disorder, but the presence of flourishing. Martin Seligman's PERMA model identifies five distinct dimensions of wellbeing that are each independently necessary: Positive emotion, Engagement, Relationships, Meaning, and Accomplishment. A life can be deficient on any one of these while fully adequate on the others.
This matters because the interventions for each dimension are different. If your deficit is meaning, more positive emotion won't fix it. If your deficit is engagement, more accomplishment won't fill the gap. Rigorous positive psychology starts with diagnosis.
---
## Your Process
**Step 1: PERMA Audit**
Evaluate each dimension honestly on a 1–10 scale and provide the evidence for that rating.
**Framing check:** Confirm the specific wellbeing situation before continuing. State what you've identified — the person's situation, the dimension(s) they've flagged (if any), and what kind of output they're seeking — in one sentence, then use `AskUserQuestion`:s4h-mindset-reframe
When your agent uses it
Applies cognitive reframing as a rigorous methodology — CBT-adjacent but not therapy. Use when you're stuck in a negative thought loop, interpreting a situation in a consistently unhelpful way, catastrophizing, or noticing that your automatic interpretation of events generates disproportionate distress. Triggers: 'reframe', 'negative thought loop', 'I keep catastrophizing', 'I can't stop thinking about it the worst way', 'cognitive distortion', 'I keep assuming the worst', 'stuck in my head about this', 'help me think about this differently'.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,096 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,208 bytes
Read SKILL.md
# Mindset — Reframe
Cognitive reframing is not about thinking positively. It is about thinking *accurately*. Most distressing automatic thoughts are not just negative — they are also inaccurate: they overstate the probability of bad outcomes, understate the person's capacity to cope, or apply global conclusions where specific ones are warranted.
The methodology here draws on CBT's cognitive restructuring process: identify the automatic thought that is generating distress, examine the evidence for and against it, name the specific cognitive distortion that is operating, and generate an alternative interpretation that is equally or better supported by the available evidence. The alternative does not need to be positive. It needs to be more accurate.
The cognitive triangle is the underlying model: **thoughts** shape **feelings**, which shape **behaviors**, which create **situations** that generate new **thoughts**. The loop runs automatically and often invisibly. Entry can happen at any point, but thoughts are usually the most accessible lever.
---
## Your Process
**Step 1: Identify the Automatic Thought**
What is the specific thought that is generating distress? Not "I feel anxious about the meeting" — that is a feeling. The thought is: "My manager is going to question whether I know what I'm doing." Not "I feel like a failure" — that is an affect. The thought is: "Making this mistake proves I'm not competent enough for this role."s4h-mindset-stoic
When your agent uses it
Applies the full Stoic toolkit as a practical thinking methodology. Use when you're caught in worry about outcomes you can't control, struggling with circumstances outside your power, suffering from what others think of you, facing adversity or loss, or wanting to develop equanimity. Triggers: 'stoic', 'what's in my control', 'I keep worrying about outcomes', 'help me accept this', 'I can't stop thinking about what might go wrong', 'someone else controls the outcome', 'dealing with adversity'.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
2,028 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,351 bytesSKILL.mdcore9,351 bytesSKILL.mdcore9,351 bytes
Read SKILL.md
# Mindset — Stoic
The Stoics identified what they considered the root of most human suffering: treating things outside our control as if they were inside our control, and treating our responses to events as if they were determined by the events themselves. The framework is not about suppressing emotion — it is about distinguishing clearly what is actually yours to shape.
Epictetus opens the *Enchiridion* with the cleanest possible statement of the core principle: *"Some things are in our control and others not. Things in our control are opinion, pursuit, desire, aversion, and, in one word, whatever are our own actions. Things not in our control are body, reputation, command, and, in one word, whatever are not our own actions."*
This is not a consolation prize. It is a recognition that the things in your control — your judgments, your choices, your character — are the only things that are unambiguously and fully yours. Everything else can be taken.
---
## Your Process
**Step 1: Identify the Situation**
State clearly what is causing distress, worry, or friction. Be specific — not "I'm anxious about my career" but "I gave a presentation I thought went poorly and I'm worried my manager now has a bad impression of me."s4h-narrative
When your agent uses it
Entry point for the narrative toolkit. Routes to the right narrative skill based on your situation. Use when you say 'narrative', 'story', 'this feels flat', 'how do I structure this', 'the framing is wrong', 'who am I talking to', 'make this compelling', 'find the tension', or want narrative/storytelling help without knowing which specific tool fits.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,098 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Audience Modeling
- Frame Analysis
- Structure Mapping
- Tension Mapping
Files
SKILL.mdcore5,316 bytes
Read SKILL.md
# Narrative
Applies narrative and storytelling thinking to communication, strategy, and meaning-making. Diagnoses what kind of narrative work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Map the audience's actual beliefs, goals, and fears | audience-modeling |
| Identify the current frame and generate better alternatives | frame-analysis |
| Apply story architecture to a proposal or presentation | structure-mapping |
| Find or create the tension that makes communication worth attending to | tension-mapping |
## Routing Decisions4h-narrative-audience-modeling
When your agent uses it
Maps the audience's current beliefs, real goals, fears, and threshold conditions before communicating with them. Use when asked to 'model the audience', 'audience analysis', 'who am I talking to', 'what do they care about', or 'why aren't they getting it'.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
986 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,518 bytes
Read SKILL.md
# Narrative Audience Modeling
Communication fails at the receiver, not the sender. The most common communication failure is not poor evidence or unclear logic — it is delivering a message the audience was not ready to receive, about a problem they do not recognize, to a goal they do not hold. Modeling the audience before communicating means identifying not what you want to say, but what they are able to hear.
---
## Your Process
**Step 1: Name Specific People**
Resist generic categories. Not "senior leadership" but "the CFO and CTO who approved last quarter's roadmap". The more specific the audience, the more useful the model.
**Framing check:** Confirm the specific audience and communication context before continuing. State what you've identified — the actual people being modeled and the communication situation — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific audience and the communication they need to receive]. Is that right?"
- **Header:** "Framing"s4h-narrative-frame-analysis
When your agent uses it
Identifies the current frame around a situation and generates alternative frames that reveal different truths. Use when asked to 'reframe this', 'the framing is wrong', 'change the narrative', 'different angle', or 'why won't they see it'.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
1,085 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,028 bytes
Read SKILL.md
# Narrative Frame Analysis
Frames are invisible until named. The same facts support radically different conclusions depending on who is the protagonist, what counts as the problem, and what counts as success. Most communication failures are framing failures — not evidence failures. Reframing does not change the facts; it changes which facts are salient and which conclusions they support.
---
## Your Process
**Step 1: Name the Current Frame**
Make the implicit explicit. Who is the protagonist in the current frame? What is the problem being solved? What counts as a successful outcome? What is the frame's implicit villain or antagonist?
**Framing check:** Confirm the specific situation and its dominant frame before continuing. State what you've identified — the actual narrative or discourse being analysed, who the current protagonist is, and what the core tension appears to be — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the situation and its current frame]. Is that right?"
- **Header:** "Framing"s4h-narrative-structure-mapping
When your agent uses it
Applies story architecture to any communication — proposal, presentation, strategy doc — so it moves people rather than informing them. Use when asked to 'structure this as a story', 'make this compelling', 'narrative arc', 'how do I present this', or 'story structure'.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,076 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,941 bytes
Read SKILL.md
# Narrative Structure Mapping
Facts don't change behavior; narrative does. The same information delivered as a story is more persuasive, more memorable, and more likely to produce action than the same information delivered as a report. Three-act structure works because it mirrors how humans process change: there is a world, the world is disrupted, a new world becomes possible. Any communication that needs to move people — not just inform them — benefits from this architecture.
---
## Your Process
**Step 1: Identify Audience and Current Belief**
Who is the specific audience? What do they already believe about this situation? You are not starting from zero — you are moving them from where they are.
**Framing check:** Confirm the specific communication and its audience before continuing. State what you've identified — the actual content being structured and who it is for — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific communication, its audience, and the intended outcome]. Is that right?"
- **Header:** "Framing"s4h-narrative-tension-mapping
When your agent uses it
Finds or creates the tension that makes communication worth paying attention to. Use when asked 'this feels flat', 'no one's engaging', 'make this compelling', 'find the tension', 'what's the story here', or 'add stakes'.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
995 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,470 bytes
Read SKILL.md
# Narrative Tension Mapping
Without a gap between current state and desired state, communication is noise. Tension is not drama or manufactured urgency — it is the honest articulation of what is wrong, at risk, or missing. Audiences disengage not because a topic is unimportant but because the communication fails to make the gap visible and real. The tension must be felt before the solution can land.
---
## Your Process
**Step 1: State the Communication**
What is the communication — its subject, its argument, its ask? State it plainly before analyzing what's missing.
**Framing check:** Confirm the specific communication before continuing. State what you've identified — the actual content being analyzed, its intended audience, and its core ask — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the communication, its audience, and its intended ask]. Is that right?"
- **Header:** "Framing"s4h-network
When your agent uses it
Entry point for the network analysis toolkit. Routes to the right network skill based on your situation. Use when you say 'network', 'who's connected to whom', 'how does this spread', 'who are the key players', 'why did this go viral', 'network effects', 'tipping point', 'weak ties', 'bridges between groups', or want network thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,285 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Centrality
- Contagion
- Weak Ties
- Network Effects
Files
SKILL.mdcore6,464 bytesSKILL.mdcore6,464 bytes
Read SKILL.md
# Network
Applies network analysis to situations where structure — not just individual attributes — determines outcomes. Diagnoses what kind of network thinking is needed and routes to the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify the most influential, well-connected, or critical nodes | centrality |
| Model how something spreads — or fails to spread — through a network | contagion |
| Find the bridging connections that link otherwise-disconnected groups | weak-ties |
| Understand how value scales with participation and where tipping points lie | network-effects |
## Routing Decisions4h-network-centrality
When your agent uses it
Identifies which nodes in a network have the most influence, reach, or control. Use when asked 'who are the key players', 'who should we target', 'where is the bottleneck', 'who connects everyone', 'who would we lose most if they left', or when mapping influence in an organisation, market, or social network.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,742 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytesSKILL.mdcore8,289 bytes
Read SKILL.md
# Network: Centrality
In almost every network — social, organizational, digital, biological — a small number of nodes exert disproportionate influence. They are not necessarily the most visible or the most senior. They are the most structurally positioned. Albert-László Barabási's research on scale-free networks established that real-world networks follow power-law degree distributions: a few hubs have vastly more connections than average, while most nodes have very few. These hubs emerge through preferential attachment — new nodes connect to already-well-connected nodes — which means structural inequality in networks is self-reinforcing.
Centrality analysis unpacks what "important" means in a specific network. There are four distinct types of centrality, and they identify different kinds of importance. A node can be a hub (high degree), a broker (high betweenness), an efficient spreader (high closeness), or influential because it is connected to other influential nodes (high eigenvector). These often coincide — but when they diverge, the divergence is analytically rich.
The key implication: targeting or protecting the most central nodes has outsized effect. Removing a high-betweenness broker can fragment a network; reaching a high-eigenvector hub can cascade influence throughout it.
---
## Your Process
**Step 1: Define the Network**
Name the nodes (what entities?) and the edges (what relationship?). Be precise about direction — is the relationship directional (A influences B but not vice versa) or undirected (mutual connection)? Name the time horizon and state what question you are trying to answer with centrality analysis.s4h-network-contagion
When your agent uses it
Models how things spread through networks — ideas, behaviors, viruses, product adoption, financial contagion, cascading failures. Use when asked 'why did this go viral', 'why isn't this spreading', 'how do we accelerate adoption', 'what's the tipping point', 'could this cascade', or when modeling any spread or diffusion process through a connected system.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,931 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,418 bytesSKILL.mdcore9,418 bytesSKILL.mdcore9,418 bytesSKILL.mdcore9,418 bytes
Read SKILL.md
# Network: Contagion
The intuitive explanation for why something spreads is usually wrong. We attribute viral spread to exceptional content, charismatic spreaders, or luck. Duncan Watts' research on complex contagion demolished this story: large cascades are not caused by extraordinary seed nodes. They are caused by a network that is structurally ready to propagate — a susceptible population in the right configuration. The seed is almost irrelevant; the structure is everything.
Two distinct contagion mechanisms operate differently and require different interventions. Simple contagion (like a biological virus) spreads on single exposure — one infected contact is enough to infect you. Complex contagion (like a social norm, a behavior change, or a product that requires social proof) requires multiple exposures from different parts of your network before you adopt. Simple contagion spreads fast through hubs; complex contagion requires local density and reinforcement. Most real-world spread processes — technology adoption, organizational change, political movements — are complex contagion, not simple.
The foundational framework is the SIR model (Susceptible, Infected, Recovered), extended through threshold models and network topology. The reproduction number R₀ — how many nodes each infectious node infects — determines whether spread occurs at all. But R₀ varies with network structure: the same pathogen spreads very differently through a random network versus a scale-free network versus a clustered community network.
---
## Your Process
**Step 1: Define What Is Spreading and What Is the Network**
Name the contagion (what is spreading) and the network (what nodes, what edges). Is this simple or complex contagion? Simple: one exposure is enough. Complex: requires social proof, multiple exposures, or threshold crossing. Name the current state: what fraction of nodes are currently infected/adopted?s4h-network-effects
When your agent uses it
Analyzes how value scales with participation — tipping points, lock-in, and winner-take-all dynamics. Use when asked 'do we have network effects', 'when will we hit critical mass', 'why is our competitor hard to displace', 'are we winner-take-all', 'how do we defend our position', 'what's our moat', or when analyzing platforms, marketplaces, or any product where more users make the product better.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
2,018 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,750 bytes
Read SKILL.md
# Network: Network Effects
Robert Metcalfe observed in 1980 that the value of a telecommunications network scales with the square of the number of connected users. One fax machine is worthless; two fax machines form one connection; a thousand fax machines form almost half a million connections. This relationship — value growing superlinearly with participation — is now called Metcalfe's Law, and it describes a mechanism that creates some of the most durable competitive positions in the economy.
Network effects are not a single phenomenon. At least four distinct types operate through different mechanisms, have different tipping points, and create different levels of defensibility. Direct network effects: each additional user directly increases value for all other users (messaging apps, social networks, communication protocols). Indirect network effects: growth on one side of a market attracts valuable participants on the complementary side (more buyers attract more sellers; more developers attract more users). Data network effects: more usage generates data that improves the product, which attracts more usage. Local network effects: value depends on connections within a subgraph, not the whole network — so the product tips locally before it tips globally.
The strategic implications are profound and often misread. Tipping points exist below which adoption dies and above which it accelerates toward dominance. Winner-take-all dynamics emerge when the network effect is global, switching costs are high, and there are no structural holes that a challenger could occupy. But many "network effect" businesses are actually winner-take-most — local or niche sub-networks can sustain competitors. The difference between these two structures determines the viable competitive strategy.
---
## Your Process
**Step 1: Identify the Network Effect Type**
For this product or business, ask: why does each additional user create value? For whom? Through what mechanism? Map against the four types:s4h-network-weak-ties
When your agent uses it
Maps bridging connections across structural holes — the counterintuitive power of loose connections. Use when asked 'where are the silos', 'why are we missing information', 'how do I find opportunities', 'who are the connectors', 'why are teams not collaborating', 'what bridges are missing', or when the question involves information flow, cross-functional collaboration, or network position as a competitive advantage.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,740 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,694 bytes
Read SKILL.md
# Network: Weak Ties
In 1973, Mark Granovetter published one of sociology's most-cited papers: "The Strength of Weak Ties." The central finding was counterintuitive then and remains counterintuitive now. The connections that deliver the most valuable information — job opportunities, novel ideas, access to resources outside your immediate world — almost never come from your close friends. They come from acquaintances. People you barely know.
The reason is structural. Your strong ties — people you interact with frequently, trust deeply, share history with — are almost certainly embedded in the same clusters you are. They know what you know. They've seen what you've seen. Their information overlaps almost entirely with yours. Weak ties, by contrast, are links between different clusters. Your acquaintance at the conference, your former colleague now in a different industry, your one contact at a competitor — they live in social worlds you don't inhabit. Their information is genuinely different from yours.
Ronald Burt extended Granovetter's insight with structural hole theory. A structural hole is a gap in the network — a position where two clusters are connected only through one person, or not at all. The person who spans a structural hole is a broker. Brokers see information earlier, can translate between worlds, and can combine ideas from separate domains in ways that people embedded in either cluster cannot. Burt found that people occupying structural holes had better ideas (as rated by independent judges), got promoted faster, and earned more. The information and control benefits of bridging structural holes are substantial and measurable.
The implication for organisations, individuals, and strategy: the most valuable position in a network is often not the most connected one — it is the one that bridges the most structural holes.
---
## Your Process
s4h-play
When your agent uses it
Entry point for the play toolkit. Routes to the right playful thinking skill based on your situation. Use when you say 'play', 'think playfully', 'flip this', 'what if there were no constraints', 'steelman the opposition', 'random stimulus', 'worst possible idea', or want unconventional thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,105 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Constraint Inversion
- Perspective Reversal
- Stimulus Generation
- Worst-Case Reversal
Files
SKILL.mdcore5,532 bytes
Read SKILL.md
# Play
Applies playful, unconventional thinking to break fixed patterns and generate unexpected possibilities. Play isn't frivolous — it's a serious tool for accessing ideas that conventional thinking misses.
## Which tool fits
| You need to... | Tool |
|---|---|
| Remove or invert the main constraint to see what becomes possible | constraint-inversion |
| Fully inhabit the opposing perspective to find what you're missing | perspective-reversal |
| Introduce a random, unrelated element to break mental fixation | stimulus-generation |
| Design the worst possible version, then reverse it | worst-case-reversal |
## Routing Decisions4h-play-constraint-inversion
When your agent uses it
Removes or inverts the main constraint to see what becomes possible — then uses those unconstrained solutions to find real ones. TRIGGERS: 'what if there were no constraints', 'rule inversion', 'what if we could do anything', 'break the rules', 'invert the assumption'.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,392 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,506 bytes
Read SKILL.md
# Play: Constraint Inversion
Most constraints are treated as fixed when they are actually assumed. The ones that
are genuinely fixed are fewer than people believe — and the ones that are assumed
become invisible over time because they've been treated as given for so long.
Inverting a constraint — imagining its complete opposite — reveals what underlying
goal it has been blocking and often generates solutions that work within the real
constraint once the goal becomes visible.
---
## Your Process
**Step 1: Name the Main Constraint**s4h-play-perspective-reversal
When your agent uses it
Fully inhabits the opposing perspective — competitor, critic, user, or adversary — to find what is invisible from your own position. TRIGGERS: 'steelman the opposition', 'think like the competitor', 'play devil's advocate', 'see it from their side', 'role reversal', 'inhabit the other perspective'.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,338 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,157 bytes
Read SKILL.md
# Play: Perspective Reversal
Every position has a blind spot — things that are invisible precisely because of
where you're standing. The opposing perspective sees those things clearly. This skill
requires fully setting aside your own position and genuinely inhabiting the other one
— without qualification, defence, or commentary — then returning to extract what was
revealed. Half-hearted perspective-taking (staying in your own frame while gesturing
at theirs) produces nothing. Full inhabitation produces findings.
---
## Your Process
**Step 1: Name the Opposing Perspective**s4h-play-stimulus-generation
When your agent uses it
Introduces a random, unrelated element to break mental fixation — forcing new associations that bypass the groove of familiar thinking. TRIGGERS: 'random stimulus', 'random word technique', 'break the fixation', 'I keep thinking of the same things', 'unstick this', 'force new associations'.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,392 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,340 bytes
Read SKILL.md
# Play: Stimulus Generation
When thinking is stuck it is usually stuck in a groove — a narrow set of associations
that keeps returning to the same territory because the same concepts keep activating
the same networks. A random, unrelated stimulus forces the mind out of that groove by
requiring it to build a bridge between an irrelevant input and the actual problem.
The bridges that form are often the most original ideas, because they come from
outside the problem's own conceptual neighbourhood.
---
## Your Process
**Step 1: State the Stuck Problem**s4h-play-worst-case-reversal
When your agent uses it
Deliberately designs the worst possible version — then reverses each failure mode into a design principle. Removes the pressure of being right and unlocks creative honesty that polite brainstorming suppresses. TRIGGERS: 'worst possible idea', 'how would you make this terrible', 'reverse brainstorm', 'design the failure', 'how would you deliberately fail'.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,218 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,569 bytes
Read SKILL.md
# Play: Worst-Case Reversal
Direct brainstorming produces cautious, socially acceptable ideas. Designing the
worst possible version removes the social cost of being wrong and unlocks the honest
list of everything that actually fails — which, when reversed, becomes the most direct
path to the design requirements that matter. The technique works because the
worst-possible list is easy: everyone knows how to fail. The reversals do the serious
work.
---
## Your Process
**Step 1: State the Design Challenge**s4h-probability
When your agent uses it
Entry point for the probability toolkit. Routes to the right probabilistic thinking skill based on your situation. Use when you say 'probability', 'how likely', 'am I overconfident', 'quantify this', 'what's the base rate', 'expected value', 'scenario weighting', or want probabilistic reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,052 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Base Rate Anchoring
- Confidence Calibration
- Expected Value Calculation
- Scenario Weighting
Files
SKILL.mdcore5,452 bytes
Read SKILL.md
# Probability
Applies probabilistic thinking to estimates, decisions, and uncertainty. Diagnoses what kind of probability work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Anchor estimates in historical base rates before adjusting | base-rate-anchoring |
| Test whether stated confidence matches available evidence | confidence-calibration |
| Calculate expected value to compare options under uncertainty | expected-value-calculation |
| Assign probabilities to distinct scenarios before deciding | scenario-weighting |
## Routing Decisions4h-probability-base-rate-anchoring
When your agent uses it
Anchors estimates in historical base rates before adjusting for specific factors. Use when asked 'what's the base rate', 'am I being too optimistic', 'outside view', 'reference class', 'how often does this actually happen', or 'historical frequency'.
What it loads into context
Frontmatter
70 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,915 bytesSKILL.mdcore4,915 bytes
Read SKILL.md
# Probability Base Rate Anchoring
The most common forecasting error is treating every situation as unique and ignoring what usually happens. Kahneman called this neglecting the outside view. Before adjusting for what makes this situation special, you must first establish what happens in situations like this one. The base rate is the outside view — the answer to "what fraction of attempts like this one succeed?" — and it is almost always more informative than inside-view reasoning about this particular case.
---
## Your Process
**Step 1: State the Prediction or Estimate**
Name the specific outcome being predicted and the current estimate or intuition. What is being forecast and at what implied probability?
**Framing check:** Confirm the specific prediction before continuing. State what you've identified — the outcome being forecast, the current intuitive estimate, and the time horizon — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the prediction and implied probability]. Is that right?"
- **Header:** "Framing"s4h-probability-confidence-calibration
When your agent uses it
Tests whether stated confidence levels match available evidence — catching overconfidence and underconfidence. Use when asked to 'calibrate my confidence', 'am I overconfident', 'confidence check', 'how sure should I be', or 'is this as certain as it seems'.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,077 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,015 bytesSKILL.mdcore5,015 bytes
Read SKILL.md
# Probability Confidence Calibration
Overconfidence is the most documented and costly bias in judgment. People who say they are 90% confident are right far less than 90% of the time. But underconfidence is also costly — excessive hedging prevents commitment and action when evidence is actually sufficient. Calibration is not about being less confident; it is about having confidence levels that match the available evidence.
---
## Your Process
**Step 1: State the Claim and Current Confidence**
Name the specific claim — not a vague domain but a specific, falsifiable statement — and state the current confidence level as a percentage.
**Framing check:** Confirm the specific claim and confidence level before continuing. State what you've identified — the actual claim being evaluated and its stated confidence percentage — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific claim and confidence level, e.g. 'You believe X with 85% confidence and want to know if that's calibrated to the evidence']. Is that right?"
- **Header:** "Framing"s4h-probability-expected-value-calculation
When your agent uses it
Calculates expected value to compare options under uncertainty. Use when asked about 'expected value', 'is this risk worth taking', 'EV calculation', 'compare these options', 'worth the risk', or 'asymmetric risk'.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,051 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,775 bytes
Read SKILL.md
# Probability Expected Value Calculation
Expected value is the correct framework for comparing options under uncertainty. It multiplies each outcome's value by its probability and sums across all outcomes, producing a single number that accounts for the full distribution rather than just the most likely case. EV analysis forces explicitness about both probabilities and values — and it exposes asymmetric risk that intuition misses. One important constraint: EV math is overridden when any outcome is catastrophic enough to be unacceptable regardless of probability.
---
## Your Process
**Step 1: Define the Options**
List the options being compared. Include "do nothing" or "wait" as explicit options — they have EVs too.
**Framing check:** Confirm the specific decision and its options before continuing. State what you've identified — the actual choice being evaluated, the options in play, and the unit of value — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the decision, its options, and what success/failure looks like]. Is that right?"
- **Header:** "Framing"s4h-probability-scenario-weighting
When your agent uses it
Assigns explicit probabilities to distinct scenarios before making a decision. Use when asked to 'assign probabilities', 'scenario weighting', 'how likely is each outcome', 'quantify the uncertainty', or 'probability distribution'.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,161 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,490 bytes
Read SKILL.md
# Probability Scenario Weighting
Vague uncertainty — "it might work, it might not" — produces poor decisions. Quantified uncertainty forces precision about what is actually believed and makes implicit assumptions visible. Assigning explicit probabilities to scenarios is not prediction; it is structured belief articulation. The process of assigning and calibrating probabilities often reveals more than the final numbers.
---
## Your Process
**Step 1: List Scenarios**
Enumerate all scenarios — they must be mutually exclusive (no overlap) and collectively exhaustive (cover all meaningful possibilities). If "other" is significant, make it explicit. Typically 3–5 scenarios; more than 6 reduces usability.
**Framing check:** Confirm the specific situation and uncertainty before continuing. State what you've identified — the actual decision or situation at stake and the key uncertainty being quantified — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific situation and the uncertainty being modelled]. Is that right?"
- **Header:** "Framing"s4h-psychology
When your agent uses it
Entry point for the psychology toolkit. Routes to the right psychology skill based on your situation. Use when you say 'psychology', 'what's driving this behavior', 'why is this person doing X', 'what biases are at play', 'how do I change a habit', 'how do I persuade', 'should I trust my gut', 'what motivates them', or want cognitive/behavioral analysis without knowing which specific tool fits.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,586 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Cognitive Biases
- Motivation
- Heuristics
- Persuasion
- Behavior Change
- What's Next
Files
SKILL.mdcore7,692 bytes
Read SKILL.md
# Psychology
Applies cognitive and behavioral frameworks to understand why people think, feel, and act as they do — and how to influence and change that. Diagnoses what kind of psychological work is needed and routes to the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify which cognitive biases are distorting thinking in a specific situation | psychology-cognitive-biases |
| Diagnose what's actually driving someone's behavior (surface vs. root) | psychology-motivation |
| Assess whether to trust or override fast intuitive thinking | psychology-heuristics |
| Change someone's mind or drive action through influence | psychology-persuasion |
| Shift entrenched behavior or break/build a habit | psychology-behavior-change |
s4h-psychology-behavior-change
When your agent uses it
Diagnose what's maintaining an entrenched behavior and design the right intervention to shift it. Covers habits, routines, and behavioral defaults. Triggers: 'how do I change this behavior', 'why does this habit persist', 'how do I make this stick', 'behavior change', 'breaking a habit', 'building a habit', 'why can't I stop doing X', 'how do I get people to consistently do Y', 'implementation intentions', 'habit loop'.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
2,196 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore10,620 bytes
Read SKILL.md
# Psychology: Behavior Change
Behavior is not driven primarily by intention. A person can fully intend to exercise, stop checking their phone, or give direct feedback — and consistently fail to do so. The intention-behavior gap is real and large. It exists because behavior is maintained by systems: habit loops, environmental cues, identity commitments, friction levels, and social norms. Changing behavior requires diagnosing which of these systems is doing the work, then intervening at the right level. Motivational exhortation without system change produces guilt, not results.
---
## Your Process
**Step 1: Specify the Behavior**
Be precise. Not "be healthier" but "go for a 30-minute walk after work on weekdays." Not "be a better communicator" but "give direct negative feedback in the weekly 1:1 rather than softening it into ambiguity." Vague behavior targets produce vague interventions.
Also specify: are you trying to **stop** a behavior, **start** a behavior, or **modify** (frequency, intensity, consistency) a behavior? These have different intervention profiles.
**Framing check:** Confirm the specific behavior before continuing. State what you've identified — the exact behavior and whether the goal is to start, stop, or modify it — in one sentence, then use `AskUserQuestion`:s4h-psychology-cognitive-biases
When your agent uses it
Diagnose which cognitive biases are actively distorting thinking in a specific situation. Not a laundry list — a targeted diagnostic. Triggers: 'what biases are at play', 'are we thinking clearly', 'what am I missing', 'bias check', 'cognitive bias', 'am I being objective', 'are we rationalizing', 'what's distorting this decision'.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,699 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,125 bytes
Read SKILL.md
# Psychology: Cognitive Biases
Most biased thinking feels like clear thinking. The distortion is invisible from the inside — the conclusion feels warranted, the evidence feels complete, the judgment feels fair. A bias diagnostic can't work as a laundry list of named biases applied generically; it has to start with the specific situation and ask which distortions are most plausible *here*, given what's at stake and who's involved.
---
## Your Process
**Step 1: Identify the Target**
What is the decision, belief, or behavior being examined? Be specific. "We're deciding whether to expand into a new market" is more useful than "strategic decision." The target shapes which biases are most likely to be active.
**Framing check:** Confirm the specific situation before continuing. State what you've identified — the actual decision, belief, or behavior being examined and the stakes or parties involved — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific situation being examined]. Is that right?"
- **Header:** "Framing"s4h-psychology-heuristics
When your agent uses it
Assess the fast-thinking pattern at work — when it's reliable, when it misleads, and whether to trust or override it. Triggers: 'should I trust my gut', 'is my intuition right here', 'fast thinking', 'heuristic', 'when does instinct work', 'System 1 vs System 2', 'pattern recognition', 'am I just pattern matching', 'is this a gut check or analysis question'.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,833 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,876 bytes
Read SKILL.md
# Psychology: Heuristics
Fast thinking is not sloppy thinking — it's compressed expertise. Pattern recognition that took years to build can run in milliseconds, and in familiar domains it's often more accurate than slow deliberation. The error is not in having heuristics; it's in applying them outside the domain where they're calibrated, or in situations that have been engineered to exploit them. The question is never "did I use a heuristic?" (you always did) — it's "is this heuristic operating in its domain of reliability?"
---
## Your Process
**Step 1: Identify the Heuristic at Work**
Name what fast thinking is doing here. Common heuristics:
**Framing check:** Confirm the specific judgment or decision before continuing. State what you've identified — the actual situation where fast thinking is being used and what is at stake — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific situation and the heuristic potentially at work]. Is that right?"
- **Header:** "Framing"s4h-psychology-motivation
When your agent uses it
Diagnose what's actually driving behavior — the person's own, someone else's, or a group's. Surface motivation vs. root motivation. Triggers: 'what motivates them', 'why are they doing this', 'what does this person actually want', 'how do I get buy-in', 'why won't they engage', 'what's really driving this', 'intrinsic vs extrinsic motivation', 'what need is this serving'.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,604 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,740 bytes
Read SKILL.md
# Psychology: Motivation
Surface explanations for behavior are almost always incomplete. When someone says they want more money, they may actually want to feel competent and respected. When someone resists a change, they may be protecting a sense of autonomy, not opposing the specific idea. When someone keeps doing something self-defeating, an unmet need is usually doing the driving. Getting the motivation right is the prerequisite for any meaningful influence, leadership, design, or change.
---
## Your Process
**Step 1: Observe the Behavior**
Describe the actual behavior, not the interpretation. "Keeps missing deadlines" rather than "doesn't care about quality." "Pushes back on every new initiative" rather than "resistant to change." The behavior is the data; the motivation is the hypothesis.
**Framing check:** Confirm the specific person or group and the behavior being analyzed before continuing. State what you've identified — the actual subject, the behavior observed, and the context — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of who is doing what, in what context]. Is that right?"
- **Header:** "Framing"s4h-psychology-persuasion
When your agent uses it
Identify the right influence approach and construct it for the context. What actually changes minds and drives action. Triggers: 'how do I persuade', 'how do I change their mind', 'what would convince them', 'how do I get buy-in', 'how do I influence', 'influence strategy', 'how do I pitch this', 'what makes a persuasive case', 'how do I get them to say yes'.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,981 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore9,506 bytes
Read SKILL.md
# Psychology: Persuasion
Persuasion fails most often not because the argument is wrong, but because the wrong approach was chosen for the audience and context. A perfectly valid argument presented to someone processing peripherally (low engagement, low stakes in their view) will be ignored. A reciprocity move used with someone who values direct confrontation will backfire. The right influence approach depends on where the audience is, what they need to feel before they can update, and what constraints exist on the relationship. The first question is not "what's my argument?" — it's "who is this person, and what will actually move them?"
---
## Your Process
**Step 1: Define What You're Trying to Change**
Be precise. Are you trying to change:
- A **belief** (they think X is false; you want them to think it's true)
- An **attitude** (they're indifferent to or opposed to X; you want them to value it)
- A **decision** (they're leaning toward A; you want them to choose B)
- A **behavior** (they currently do/don't do X; you want them to do/not do X)s4h-resource
When your agent uses it
Entry point for the resource toolkit. Routes to the right resource skill based on your situation. Use when you say 'resource', 'capacity', 'bottleneck', 'allocation', 'where should we focus', 'where are we wasting', 'highest leverage', 'what's slowing us down', or want resource reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,109 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Allocation Analysis
- Bottleneck Analysis
- Leverage Mapping
- Waste Audit
Files
SKILL.mdcore5,450 bytes
Read SKILL.md
# Resource
Applies resource reasoning to allocation, constraints, leverage, and waste. Diagnoses what kind of resource work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Distribute limited resources across competing needs | allocation-analysis |
| Find what is actually constraining throughput | bottleneck-analysis |
| Find the highest-leverage use of available resources | leverage-mapping |
| Find where resources are being lost, duplicated, or underused | waste-audit |
## Routing Decisions4h-resource-allocation-analysis
When your agent uses it
Distributes limited resources across competing needs — making the trade-offs explicit rather than implicit. Triggers: 'resource allocation', 'how do we distribute this', 'competing priorities', 'trade-off analysis', 'how do we split this', 'allocation decision'.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,017 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,778 bytes
Read SKILL.md
# Resource Allocation Analysis
Every allocation is a trade-off — giving to one thing means giving less to another. The problem is that most allocations are made implicitly, leaving the trade-offs invisible. Making trade-offs explicit forces honest prioritisation and prevents the political habit of pretending everything can be fully funded.
---
## Your Process
**Step 1: Inventory Available Resources**
Name and quantify the resources to be allocated: budget, headcount, time, capacity. Be precise about what is actually available — not what is desired.
**Framing check:** Confirm the specific allocation situation before continuing. State what resources you've identified and the decision context they apply to in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing — e.g. 'Distributing $X budget / Y headcount across Z competing claims to determine the best allocation for [goal]']. Is that right?"
- **Header:** "Framing"s4h-resource-bottleneck-analysis
When your agent uses it
Identifies what is actually constraining throughput — using Theory of Constraints logic: the system can only move as fast as its slowest point. Triggers: 'bottleneck analysis', 'what's actually slowing this down', 'where's the constraint', 'theory of constraints', 'find the bottleneck', 'why are we moving slowly'.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,269 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,752 bytes
Read SKILL.md
# Bottleneck Analysis
A system can only move as fast as its slowest stage. Improving any stage other than the bottleneck does not improve overall throughput — it just creates more work waiting in front of the constraint. Finding and addressing the bottleneck is the highest-leverage intervention available.
---
## Your Process
**Step 1: Map the Process or Value Chain**
Describe all the stages in sequence. What enters each stage, what happens, and what exits? The map should cover the full flow from input to output.
**Framing check:** Confirm the specific system before continuing. State what you've identified — the process or value chain being mapped and its start and end points — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific process or value chain, including what the input and output are]. Is that right?"
- **Header:** "Framing"s4h-resource-leverage-mapping
When your agent uses it
Finds the highest-leverage use of available resources — where the same input produces the most output. Triggers: 'resource leverage', 'highest-leverage use', 'where should we put our energy', 'maximize impact', 'leverage mapping'.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,136 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,357 bytes
Read SKILL.md
# Resource Leverage Mapping
Not all uses of a resource are equal. Some produce disproportionate output — because they remove a constraint, create more resources, or unlock other opportunities. Leverage mapping makes that asymmetry visible before resources are committed.
---
## Your Process
**Step 1: Inventory Available Resources**
List all meaningful resources available: time, money, people, attention, relationships, existing assets, reputation. Be specific — "the engineering team" is less useful than "three senior engineers with 20% slack capacity."
**Framing check:** Confirm the specific resource situation before continuing. State what you've identified — the context, the resources in scope, and the allocation question being asked — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the resource situation and the core allocation question]. Is that right?"
- **Header:** "Framing"s4h-resource-waste-audit
When your agent uses it
Finds where resources are being lost, duplicated, or underused — the seven wastes applied to knowledge work. Triggers: 'waste audit', 'where are we wasting resources', 'inefficiency audit', 'find the waste', 'what's being duplicated', 'resource leakage'.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,277 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
- The Seven Wastes in Knowledge Work
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,745 bytes
Read SKILL.md
# Resource Waste Audit
In manufacturing, Toyota identified seven categories of waste. They apply equally to knowledge work — with a different surface appearance but the same underlying structure. The goal is to find where resources are consumed without producing value.
---
## The Seven Wastes in Knowledge Work
| Waste | Description |
|-------|-------------|
| **Waiting** | Idle time between steps — work blocked pending a decision, review, or dependency |
| **Overproduction** | Producing more than is needed — reports no one reads, features no one uses |
| **Rework** | Fixing what should have been right — re-doing work due to unclear requirements or poor handoffs |
| **Duplication** | The same work being done in two places — parallel efforts, re-discovered knowledge |s4h-sensory
When your agent uses it
Entry point for the sensory observation toolkit. Routes to the right observational skill based on your situation. Use when you say 'sensory', 'what are we missing', 'look more carefully', 'separate signal from noise', 'too much information', 'what actually matters here', 'observe this carefully', or want observational precision applied without knowing which specific tool fits.
What it loads into context
Frontmatter
85 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Detail Mining
- Signal Detection
- Structured Observation
Files
SKILL.mdcore3,864 bytes
Read SKILL.md
# Sensory
Applies disciplined observation and attention to any situation. Diagnoses what kind of observational work is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Find specific details that are being overlooked | detail-mining |
| Separate what actually matters from background noise | signal-detection |
| Apply disciplined observation before interpreting | structured-observation |
## Routing Decision
s4h-sensory-detail-mining
When your agent uses it
Finds specific details being overlooked — the most important information is often present but not being registered. Triggers: 'what are we missing', 'go deeper on this', 'find the details', 'be more specific', 'what exactly is happening', 'ground this in specifics'.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,027 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,708 bytes
Read SKILL.md
# Detail Mining
Abstractions are useful — but they lose the specific detail that often contains the real insight. "Users are frustrated" is an abstraction that conceals which users, in which moment, doing what, saying what exactly. Detail mining forces that concealment back into the open.
---
## Your Process
**Step 1: Take the Current Description**
Work with whatever account, analysis, or summary exists. This is the starting material — it contains the abstractions to excavate.
**Framing check:** Confirm the specific subject before continuing. State what you've identified — the actual material being excavated and what kind of abstraction it primarily deals in — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific content — e.g. 'a session-recording summary describing user behaviour at a checkout flow']. Is that right?"
- **Header:** "Framing"s4h-sensory-signal-detection
When your agent uses it
Separates meaningful signal from background noise — finding what actually matters among everything present. Triggers: 'what actually matters here', 'separate signal from noise', 'too much information', 'find the signal', 'what should I focus on', 'what's relevant'.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,121 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,097 bytes
Read SKILL.md
# Signal Detection
In any rich environment — data, feedback, conversation, a market — most of what is present is noise. Signal is what varies with the thing you're trying to understand; noise varies independently. The challenge is not finding more information, it's knowing which information is doing real work.
---
## Your Process
**Step 1: Inventory Everything Present**
List all the data, observations, or inputs available. Don't filter yet — complete the inventory first.
**Framing check:** Confirm the specific subject before continuing. State what you've identified — the actual environment or dataset being analyzed and what outcome or phenomenon the user is trying to understand — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific environment/dataset and the outcome you're testing against]. Is that right?"
- **Header:** "Framing"s4h-sensory-structured-observation
When your agent uses it
Applies disciplined observation to a situation — suspending interpretation to see what's actually there before deciding what it means. Triggers: 'observe this carefully', 'structured observation', 'what do you actually see', 'suspend interpretation', 'look more carefully'.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,096 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,097 bytes
Read SKILL.md
# Structured Observation
Most observation is interpretation in disguise. We perceive a situation and instantly explain it — but the explanation overwrites the raw data. Structured observation forces a separation between what can be directly seen and what we conclude from it.
---
## Your Process
**Step 1: Define the Target and Time Boundary**
Name the exact thing being observed and the scope. What counts as inside this observation, and what is out of scope?
**Framing check:** Confirm the specific subject before continuing. State what you've identified — the actual object being observed and its boundaries — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific subject and scope]. Is that right?"
- **Header:** "Framing"s4h-social
When your agent uses it
Entry point for the social dynamics toolkit. Routes to the right social skill based on your situation. Use when you say 'social', 'people', 'politics', 'who decides', 'group dynamics', 'who do I need to get on board', 'follow the incentives', 'who has power', or want social/organizational reasoning applied without knowing which specific tool fits.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,093 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Coalition Mapping
- Dynamics Analysis
- Incentive Analysis
- Power Mapping
Files
SKILL.mdcore5,279 bytes
Read SKILL.md
# Social
Applies social and organizational reasoning to group dynamics, power, incentives, and coalition-building. Diagnoses what kind of social analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Map who needs to be aligned and how to build support | coalition-mapping |
| Understand the group psychology shaping a team or discussion | dynamics-analysis |
| Find the actual incentives driving behavior | incentive-analysis |
| Map who holds formal and informal power | power-mapping |
## Routing Decisions4h-social-coalition-mapping
When your agent uses it
Maps who needs to be aligned, who already is, and how to build the coalition a proposal needs to succeed. Triggers: 'coalition building', 'who do I need to get on board', 'map the support', 'build alignment', 'who will support this', 'who will block this'.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,139 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,145 bytes
Read SKILL.md
# Coalition Mapping
Proposals fail not because they are wrong, but because they lack the support needed to move. Coalition mapping makes the social landscape explicit: who is already on board, who is opposed, who is persuadable, and what sequence of engagement gives the best chance of success.
---
## Your Process
**Step 1: Define the Required Support**
What does success require? Formal approval from whom? Informal buy-in from whom? What is the minimum needed for the proposal to move?
**Framing check:** Confirm the specific proposal and its success conditions before continuing. State what you've identified — the actual proposal being mapped, who owns it, and what "winning" looks like — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the proposal, its goal, and the decision-making context]. Is that right?"
- **Header:** "Framing"s4h-social-dynamics-analysis
When your agent uses it
Identifies group psychology shaping a discussion or team — groupthink, status dynamics, coalition formation, psychological safety. Triggers: 'group dynamics', 'why does this team behave like this', 'groupthink check', 'why won't people speak up', 'meeting dynamics', 'team dysfunction'.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,180 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,566 bytes
Read SKILL.md
# Group Dynamics Analysis
Groups develop collective behaviours that are invisible from inside them. Premature consensus, status-based deference, and psychological unsafety all degrade decision quality — and they are self-reinforcing. Naming the dynamic is the first step to changing it.
---
## Your Process
**Step 1: Observe or Recall Group Behaviour**
Work from specific, concrete instances of how the group acts — not general impressions. What actually happened in the last meeting or decision? What was said? What was not said?
**Framing check:** Confirm the specific group and context before continuing. State what you've identified — the actual group being analyzed and the situation or event in focus — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the group and the situation or event in focus]. Is that right?"
- **Header:** "Framing"s4h-social-incentive-analysis
When your agent uses it
Maps the actual incentives driving behaviour — distinguishing stated motivations from the real incentive structures that shape what people do. Triggers: 'incentive analysis', 'why are they doing this', 'what are the actual incentives', 'follow the incentives', 'what does the system reward'.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,055 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,012 bytes
Read SKILL.md
# Incentive Analysis
Most behaviour that looks irrational is perfectly rational given the actual incentives. The problem is that systems are designed around intended incentives while people respond to actual ones. Finding the gap between the two explains what is happening and points to what would change it.
---
## Your Process
**Step 1: Describe the Behaviour**
Name the specific behaviour to explain or change. Be concrete — not "people aren't engaged" but "engineers don't attend architecture reviews and don't comment on RFCs."
**Framing check:** Confirm the specific behaviour and its context before continuing. State what you've identified — the actual behaviour being analysed, who is exhibiting it, and the system or setting it occurs in — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific behaviour, the actors involved, and the context]. Is that right?"
- **Header:** "Framing"s4h-social-power-mapping
When your agent uses it
Maps who holds power — formal authority, informal influence, gatekeeping, expertise — and how it flows. Triggers: 'power map', 'who has power here', 'who actually decides', 'map the politics', 'who do I need to get on board', 'who are the gatekeepers'.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
966 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,458 bytes
Read SKILL.md
# Power Mapping
Org charts describe formal authority. Power is different. It includes informal influence (whose opinion shifts decisions), gatekeeping (who controls access), and expertise (whose knowledge others depend on). A proposal that ignores actual power distribution will fail even if it is correct.
---
## Your Process
**Step 1: List Relevant Actors**
Name every person, role, or group that could affect or be affected by the situation. Include those who seem peripheral — they are sometimes the most important.
**Framing check:** Confirm the specific situation and scope before continuing. State what you've identified — the context, the decision or change at stake, and whose power dynamics are in question — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the situation, the decision or change involved, and the organisational context]. Is that right?"
- **Header:** "Framing"s4h-strategy
When your agent uses it
Routes to the right strategy skill for any adversarial or competitive reasoning situation. Triggers: 'how do I beat X', 'competitive strategy', 'outmaneuver', 'I'm up against', 'position myself', 'what's my play here', any situation involving competitive pressure, adversarial dynamics, negotiation, or resource-constrained contest.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,067 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 Process
- Routing Confirmation
- Output Format
- Notes
Files
SKILL.mdcore4,994 bytes
Read SKILL.md
# Strategy
Sun Tzu's central insight: "The victorious warrior wins first and then goes to war, while the defeated warrior goes to war first and then seeks to win." Strategy is what happens before the contest. It is the discipline of creating conditions — position, intelligence, timing, alliances — so that when the contest begins, the outcome is already determined.
The strategy skills in this category draw on Sun Tzu (*The Art of War*), Clausewitz (*On War*), Miyamoto Musashi (*Book of Five Rings*), and competitive theory. They are not about aggression. They are about reading competitive contexts clearly and acting with economy, intelligence, and timing.
---
## Your Process
Read the user's situation carefully. Identify which strategic challenge is primary, then present the options below — briefly and specifically — and ask which fits. Execute immediately on selection.
**Framing check:** Confirm the competitive situation before continuing. State what you've identified — the actor, the opponent or competitive pressure, and the primary objective at stake — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the actor, the adversarial dynamic, and the goal]. Is that right?"s4h-strategy-alliance
When your agent uses it
Maps parties, identifies natural allies and swing parties, and assesses alliance stability for coalition-building in competitive contexts. Triggers: 'build alliances', 'coalition building', 'who are my allies', 'manage stakeholders', 'political coalition', 'alliance strategy', 'who do I need on my side', 'get people on board', 'organizational politics'.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,590 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,613 bytes
Read SKILL.md
# Strategy: Alliance
Machiavelli's counter-intuitive warning in *The Prince*: alliances built on goodwill are fragile; alliances built on shared interest are durable. A prince who relies on gratitude will be disappointed the moment the interest calculus changes. A prince who builds alliances on the foundation of mutual benefit will hold them through adversity because both parties have a reason — independent of sentiment — to maintain the relationship.
Sun Tzu's operational principle complements this: "Know the local situation." Before deciding who to ally with, who to neutralize, and who to oppose, you must know what each party actually wants — not what they say they want, not what you hope they want, but what their actual interest is in this situation. Misreading a party's interest and trying to ally with them on incorrect assumptions produces a fragile alliance at best and an active opponent at worst.
The most common alliance error is the inverse: trying to win everyone over. Alliances have a cost — they create obligations, signal positions, and consume relationship capital. The discipline is identifying which alliances are necessary, which neutralizations are sufficient, and which parties are simply not worth the investment. Alliances managed poorly — obligations created without the support they were supposed to purchase — are worse than no alliances. They drain resources and signal weakness.
---
## Your Process
**Step 1: Party map**
List everyone involved in or affected by this situation. For each: what do they actually want (not what they say), what is their current position relative to your objective, and what is their capacity to help or hurt you?s4h-strategy-deception
When your agent uses it
Manages information asymmetry in legitimate competitive contexts — what to protect, what impressions work in your favor, and what your opponent may be concealing from you. Triggers: 'conceal my position', 'information asymmetry', 'misdirection', 'what should I reveal vs conceal', 'negotiation deception', 'strategic ambiguity', 'manage what they know about me', 'read their signals'.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,420 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,167 bytes
Read SKILL.md
# Strategy: Deception
Sun Tzu's most provocative statement: "All warfare is based on deception." Its operational meaning is not that lying is the path to victory. It is that controlling what your opponent believes about you is as important as controlling what you do. A general who moves in predictable, transparent ways gives the opponent full information and eliminates the element of surprise. A general who manages information deliberately — signaling strength where they are strong, concealing weakness, appearing where unexpected — compounds their effective advantage at no additional resource cost.
In legitimate competitive contexts — negotiation, market positioning, competitive product strategy, organizational politics — managing information asymmetry is standard practice. Revealing your walk-away point in a negotiation, publishing your roadmap before it's locked, announcing your strategy before executing it: each of these transfers advantage to the other side. The discipline is not dishonesty; it is choosing what to make visible and what to protect.
One structural constraint governs everything: **whatever you conceal must be consistently concealed.** A single inconsistency destroys the deception more efficiently than disclosure. Inconsistency broadcasts that you are managing information — which is worse than transparency. The cost of a deception that collapses mid-contest is higher than the cost of not deploying it at all.
> **Important:** This skill applies to legitimate competitive contexts where information management is appropriate — commercial negotiation, competitive strategy, organizational positioning, market timing. It does not apply to fraud, manipulation of parties in positions of vulnerability, or deception that causes disproportionate harm to people who cannot protect themselves.
---
## Your Process
s4h-strategy-force-economy
When your agent uses it
Finds the minimum intervention that achieves the objective — especially when you're outgunned or under-resourced. Triggers: 'do more with less', 'force economy', 'we're under-resourced', 'asymmetric advantage', 'outgunned', 'leverage point', 'how do we win when they have more', 'we can't outspend them', 'small team big problem'.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,548 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,403 bytesSKILL.mdcore7,403 bytesSKILL.mdcore7,403 bytes
Read SKILL.md
# Strategy: Force Economy
Sun Tzu's highest strategic achievement is the victory that costs nothing — where the opponent's resistance collapses without direct contest: "Supreme excellence consists in breaking the enemy's resistance without fighting." This is not passivity. It is the discipline of identifying where a small input creates a large output — where the terrain, timing, information asymmetry, or a single relationship multiplies your effective force without requiring you to match the opponent unit for unit.
The force economy principle asks: what is the minimum intervention that achieves the objective? Not merely because resources must be conserved (though they must), but because the maximum-force approach almost always generates the maximum resistance. Brute force signals intention, consumes capital, and invites a symmetrical response from an opponent with more of everything. The indirect approach — Basil Liddell Hart's formulation — achieves more by creating the conditions in which less is required.
The discipline is finding the leverage point: the node in the system where a small input produces a disproportionate output. Not all nodes are equal. Most effort has roughly proportional effect. Leverage points are structural exceptions — and finding them before acting is the core skill.
---
## Your Process
**Step 1: State the objective**
Define what success looks like clearly and specifically. Vague objectives produce vague force economy analyses. What must be true for this to be considered won?s4h-strategy-intelligence
When your agent uses it
Audits what you actually know vs. what you're assuming about yourself and your opponent before acting. Triggers: 'what do I actually know', 'intelligence audit', 'know your enemy', 'what am I assuming vs knowing', 'prep for negotiation', 'what information do I have', 'what don't I know about them', 'am I missing something important'.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,460 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,714 bytes
Read SKILL.md
# Strategy: Intelligence
Sun Tzu's most quoted principle — "Know yourself and know your enemy; in a hundred battles you will never be in peril" — is often treated as a slogan. Its operational meaning is precise: knowledge asymmetry determines outcomes before any action is taken. A general who knows the terrain, the opponent's strength, the opponent's commander, and his own limitations will defeat an equivalent force every time. A general who acts on assumption held as fact will suffer the predictable consequence.
The self-audit is as important as the opponent audit, and harder. Self-flattery is the most common intelligence failure. We know our strengths clearly; we hold our weaknesses vaguely. We know our opponent's stated position; we assume their actual constraints, motives, and fallback options. The intelligence discipline is the discipline of holding the line between what is known and what is assumed — because the gap is where strategic surprises live.
---
## Your Process
**Step 1: Self-audit**
List actual strengths, weaknesses, hard constraints, and available resources. Do not soften the weaknesses. Ask: what would embarrass you to admit in this situation? Those admissions are the accurate self-assessment. What dependencies do you have? What time pressures? What is your actual walk-away position?
**Framing check:** Confirm the specific situation before continuing. State what you've identified — the strategic situation, the opponent or counterparty, and the decision at stake — in one sentence, then use `AskUserQuestion`:s4h-strategy-positioning
When your agent uses it
Builds the conditions for competitive unassailability before the contest begins. Triggers: 'create a position', 'competitive positioning', 'make myself the obvious choice', 'how do I make myself hard to compete with', 'strategic positioning', 'establish advantage before competing', 'what makes me hard to displace', 'build a moat'.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,462 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,853 bytes
Read SKILL.md
# Strategy: Positioning
Sun Tzu: "The good fighters of old first put themselves beyond the possibility of defeat, and then waited for an opportunity of defeating the enemy." The first move is not to attack — it is to make yourself unassailable. Position precedes contest.
Michael Porter's parallel insight in competitive theory: sustainable advantage comes not from trying to be best at everything, but from choosing not to compete everywhere. A position that is genuinely defensible requires trade-offs — commitments that make you excellent in one direction at the cost of flexibility in others. The value of the trade-off is precisely that it cannot be easily replicated by a competitor without abandoning their own position. A competitor who tries to copy you has to give up what they've optimized for. That is what makes a position real.
The failure mode is positioning by assertion: saying you occupy a position without doing the investment that makes it true. Genuine positioning requires assets, capabilities, relationships, or reputations that are costly to build and therefore difficult to replicate. The question is not "where do I want to be?" but "what would I need to truly hold this ground?"
---
## Your Process
**Step 1: Ideal unassailable position**
What would it look like to hold a position that a rational, well-resourced opponent would choose to go around rather than contest directly? Describe the ideal: what would you be known for, what would you own, what would your relationships and reputation make you? Be specific — "market leader" is not a position. "The only reliable provider for this niche, with a five-year track record and the three key relationships in the sector" is a position.s4h-strategy-terrain
When your agent uses it
Maps the competitive landscape to identify where you have advantage, where contests are evenly matched, and where engagement is costly. Triggers: 'map the landscape', 'terrain analysis', 'where should I compete', 'what's the ground like', 'competitive landscape', 'where do I have advantage', 'which markets should I enter', 'is this fight worth having'.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,473 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,018 bytes
Read SKILL.md
# Strategy: Terrain
Sun Tzu identifies six types of terrain and nine strategic situations in *The Art of War*, each demanding different conduct. The underlying principle is that position shapes outcome before the contest begins: "He who occupies the ground first and awaits the enemy is at ease; he who comes later and hastens to fight is weary." The key strategic question is not "how do I win this battle?" but "which battles should be fought at all?" Terrain analysis is the discipline of answering that question before committing resources.
Sun Tzu's nine situations range from dispersive ground (where retreat is correct) to deadly ground (where fighting hard is the only option). What unifies them is this: each type of ground demands a different response, and treating all ground as equal is a reliable path to defeat. A position that is unfavorable for you may be excellent for your opponent. A position that looks contested may be yours to win with the right move first.
---
## Your Process
**Step 1: Landscape inventory**
What are the available positions in this competitive context? Include: markets or segments, relationships, information asymmetries, timing windows, resource positions, and reputation or brand territory. List them without judgment first — the goal is completeness before evaluation.
**Framing check:** Confirm the competitive context before continuing. State the specific situation being analyzed — who the actor is, what arena they are operating in, and what strategic question is at stake — in one sentence, then use `AskUserQuestion`:s4h-strategy-timing
When your agent uses it
Analyzes whether to act now or wait, reads your opponent's rhythm, and identifies trigger conditions for the right moment. Triggers: 'when should I act', 'timing analysis', 'is now the right moment', 'should I wait', 'when to launch', 'when to make my move', 'is the window closing', 'am I too early', 'am I too late'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,440 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,635 bytes
Read SKILL.md
# Strategy: Timing
Miyamoto Musashi opens *The Book of Five Rings* with a meditation on timing: "Timing exists in everything." His insight is not simply that timing matters — it is that timing must be actively read rather than passively experienced. A swordsman who ignores his opponent's rhythm and attacks on his own preferred schedule will find the interval closed. A swordsman who reads when the opponent is overextended, committed, or off-balance will find the interval open.
Sun Tzu's complementary metaphor: "Water shapes its course according to the nature of the ground over which it flows; the soldier works out his victory in relation to the foe he is facing." Water does not insist on a fixed form. It adapts to the terrain continuously. The question is never simply "should I act?" — it is: "does the current moment give me an advantage that waiting would not compound, or does waiting improve conditions beyond what action now delivers?"
Both Musashi and Sun Tzu agree on one further principle: the opponent's timing is as important as your own. Attacking when your opponent is preparing is different from attacking when they are overextended. The interval is not a point on your schedule; it is a relationship between two rhythms.
---
## Your Process
**Step 1: Conditions favoring action now**
What is true right now that will not be true later? What windows are closing — competitor moves, decision-maker availability, market conditions, relationships, information advantages that decay? What cost do you pay for each week of delay?s4h-strategy-victory
When your agent uses it
Defines what winning actually means before the contest begins — prevents the pyrrhic trap of winning in ways that lose the larger goal. Triggers: 'what does winning look like', 'define victory', 'victory conditions', 'what are we actually trying to achieve', 'define success', 'is winning worth it', 'pyrrhic trap', 'are we optimizing for the right thing'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,427 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore6,766 bytes
Read SKILL.md
# Strategy: Victory
Clausewitz's central insight in *On War*: "War is the continuation of politics by other means." The military contest is not the point; it is a means to a political end. The moment a commander loses sight of the political objective and optimizes purely for military victory, they have already failed strategically — because a military win that undermines the political aim is worse than a negotiated settlement.
The same principle applies to any contest. A company that wins a price war by destroying its margins has won the battle and lost the business. A legal team that wins at trial and spends three years doing it, producing a verdict worth less than the settlement foregone, has won the judgment and lost the case. A negotiator who extracts every possible concession and destroys the relationship needed for implementation has won the negotiation and lost the outcome. The pyrrhic trap is the failure to define victory before the contest forces its own definition on you.
Sun Tzu's corollary: "The supreme art of war is to subdue the enemy without fighting." This is not a counsel of passivity — it is the recognition that the cheapest possible victory is the right objective. A victory that requires the maximum cost is a strategic failure even when it succeeds. Minimum victory conditions exist for a reason: they prevent over-prosecution of a contest that has already been won.
---
## Your Process
**Step 1: Stated objective**
What are you trying to achieve? Name it as it is currently framed.s4h-systems
When your agent uses it
Entry point for the systems thinking toolkit. Routes to the right systems skill based on your situation. Use when you say 'systems', 'feedback loops', 'how does this system work', 'where should we intervene', 'unexpected behavior', 'what archetype is this', 'find the leverage', or want systems thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,111 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Archetype Matching
- Emergence Detection
- Feedback Mapping
- Leverage Analysis
Files
SKILL.mdcore5,595 bytes
Read SKILL.md
# Systems
Applies systems thinking to complex, dynamic situations. Diagnoses what kind of systems analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Recognize what recurring system pattern this is | archetype-matching |
| Understand unexpected or counterintuitive system behavior | emergence-detection |
| Map the feedback loops driving behavior | feedback-mapping |
| Find where small interventions produce large change | leverage-analysis |
## Routing Decisions4h-systems-archetype-matching
When your agent uses it
Applies the 8 classic system archetypes (Senge) to diagnose recurring system behavior. Use when asked 'this keeps repeating', 'the fix made it worse', 'we've solved this before', 'identify the pattern', or 'system archetype'.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,180 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,437 bytes
Read SKILL.md
# Systems Archetype Matching
Recurring system behaviors are not unique — they follow a small set of structural patterns that have known causes and known high-leverage responses. Senge's eight archetypes give names to these patterns. Matching the current situation to an archetype tells you what structure is producing the behavior and what intervention actually works, rather than re-discovering the same solution each cycle.
---
## Your Process
**Step 1: Describe the Recurring Behavior**
State what keeps happening. Include: what was tried, what temporarily worked, what came back. The more specific, the better the match.
**Framing check:** Confirm the specific system and its recurring behavior before continuing. State what you've identified — the system in question, the behavior that keeps repeating, and what has been tried — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the system and recurring behavior]. Is that right?"
- **Header:** "Framing"s4h-systems-emergence-detection
When your agent uses it
Identifies system-level properties that exist nowhere in any individual component. Use when asked about 'emergent behavior', 'components are fine but the system isn't', 'why does the whole behave like this', or 'what creates this property'.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,089 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,212 bytes
Read SKILL.md
# Systems Emergence Detection
Emergent properties are the most important features of complex systems and the least designed for. They arise from interactions between components, not from the components themselves — which is why fixing individual parts often fails to fix system-level problems. Identifying emergence requires asking not what each component does, but what arises when they interact.
---
## Your Process
**Step 1: State the System-Level Property**
Name the property to explain or design for. Be precise: "the platform feels trustworthy", "the team produces poor decisions", "the market self-corrects". Vague properties produce vague analysis.
**Framing check:** Confirm the specific system and emergent property before continuing. State what you've identified — the actual system being analyzed and the property you are tracing — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the system and the emergent property in focus]. Is that right?"
- **Header:** "Framing"s4h-systems-feedback-mapping
When your agent uses it
Identifies all reinforcing (+) and balancing (−) feedback loops in a system. Use when asked to 'map the feedback loops', 'why does this keep happening', 'unintended consequences', or 'system keeps oscillating'.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,113 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytes
Read SKILL.md
# Systems Feedback Mapping
Most system failures come from unrecognized feedback loops — especially delayed balancing loops that cause overshoot and collapse. Reinforcing loops amplify change in one direction; balancing loops push back toward a target. Until both types are visible and named, diagnosis and intervention are guesswork.
---
## Your Process
**Step 1: Define System Boundary**
State what is inside the system and what is outside it. Name the time horizon and the key behavior to explain (growth, oscillation, collapse, stagnation).
**Framing check:** Confirm the specific system and the feedback relationship in focus before continuing. State what you've identified — the actual system being analyzed, its time horizon, and the behavior you're mapping — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the system, time horizon, and behavior to explain]. Is that right?"
- **Header:** "Framing"s4h-systems-leverage-analysis
When your agent uses it
Finds where small interventions produce large, lasting change using Donella Meadows' leverage point hierarchy. Use when asked 'where should we intervene', 'highest leverage', 'what actually changes this system', or 'find the lever'.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,069 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,033 bytes
Read SKILL.md
# Systems Leverage Analysis
Most interventions target low-leverage parameters — adjusting numbers, tweaking rates — when high-leverage structural points are available and being ignored. Donella Meadows identified 12 places to intervene in a system, ranging from parameters (nearly powerless) to paradigm (most powerful). The reason high-leverage points go unused is that they face the highest resistance; understanding this is part of the analysis.
---
## Your Process
**Step 1: List Candidate Interventions**
Gather all interventions currently being considered or tried. Include past attempts that failed.
**Framing check:** Confirm the specific system and the interventions in focus before continuing. State what you've identified — the system being analysed and the intervention set you're working with — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the system and the interventions being examined]. Is that right?"
- **Header:** "Framing"s4h-temporal
When your agent uses it
Entry point for the temporal thinking toolkit. Routes to the right temporal skill based on your situation. Use when you say 'temporal', 'timing', 'when', 'long term', 'what happens in 5 years', 'what cycle is this', 'should we wait', 'possible futures', or want time-horizon thinking applied without knowing which specific tool fits.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,175 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
- Which tool fits
- Routing Decision
- Confirm Direction
- Cycle Detection
- Horizon Mapping
- Futures Mapping
- Timing Analysis
Files
SKILL.mdcore5,584 bytes
Read SKILL.md
# Temporal
Applies temporal reasoning to timing, horizons, cycles, and futures. Diagnoses what kind of time-based analysis is needed and applies the right tool.
## Which tool fits
| You need to... | Tool |
|---|---|
| Identify what cycle this is and where in it you are | cycle-detection |
| Map consequences across short, medium, and long horizons | horizon-mapping |
| Explore possible, probable, and preferable futures | futures-mapping |
| Assess whether now is the right time to act | timing-analysis |
## Routing Decisions4h-temporal-cycle-detection
When your agent uses it
Identifies what recurring cycle a situation is an instance of and where in that cycle you currently are. Use when asked 'what cycle is this', 'where are we in the cycle', 'have we seen this before', 'detect the pattern', 'hype cycle', or 'where in the curve'.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,094 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,092 bytes
Read SKILL.md
# Temporal Cycle Detection
Every situation that feels unprecedented is usually an instance of a recurring cycle. Knowing your position in the cycle tells you what phase is coming, what actions are appropriate now versus premature, and which signals indicate divergence from the typical pattern — the most important signal of all. Acting as if a situation is unique when it is not forfeits the pattern's predictive value.
---
## Your Process
**Step 1: Describe Current State and Trajectory**
State what is happening now and how the situation has moved over the past period. Include: rate of change, sentiment, who is entering or exiting, resource flows, expectations.
**Framing check:** Confirm the specific situation before continuing. State what you've identified — the actual phenomenon or domain being analyzed and its key observable parameters — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific situation and what is changing]. Is that right?"
- **Header:** "Framing"s4h-temporal-futures-mapping
When your agent uses it
Explores possible, probable, and preferable futures using scenario thinking. Use when asked about 'scenario planning', 'futures thinking', 'possible futures', 'how might this play out', 'futures cone', or 'what could happen'.
What it loads into context
Frontmatter
64 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
- Your Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,904 bytes
Read SKILL.md
# Temporal Futures Mapping
The future is not a single path — it is a cone of possibilities that narrows as time passes and choices are made. Scenario thinking does not predict the future; it maps the cone so that plans can be tested against multiple plausible worlds rather than a single assumed one. Plans that only work in one scenario are fragile. Plans robust across several are resilient.
---
## Your Process
**Step 1: Define Time Horizon and Decision Context**
State the specific decision or question being stress-tested and the time horizon (1 year, 5 years, 10 years). The scenarios must be built around a decision, not just as general futures.
**Framing check:** Confirm the specific decision context before continuing. State what you've identified — the actual decision or question being stress-tested and the time horizon — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the decision and time horizon]. Is that right?"
- **Header:** "Framing"s4h-temporal-horizon-mapping
When your agent uses it
Maps consequences of a decision across short, medium, and long time horizons. Use when asked about 'time horizons', 'what does this look like in 5 years', 'short-term vs long-term', 'map the implications over time', or 'think through the long-term'.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,162 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore5,336 bytesSKILL.mdcore5,336 bytes
Read SKILL.md
# Temporal Horizon Mapping
Decisions that look good now often look very different at 1, 3, or 10 years. The most consequential errors in judgment come not from bad reasoning in the moment but from evaluating a decision at the wrong time horizon — optimizing for the immediate while the real costs land later. Making all three horizons explicit forces the tradeoff into view rather than leaving it implicit.
---
## Your Process
**Step 1: State the Decision**
Name the decision being evaluated and the current context in which it is being made. Clarity here prevents analysis drifting to adjacent decisions.
**Framing check:** Confirm the specific decision before continuing. State what you've identified — the actual decision being evaluated and the context in which it is being made — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the specific decision and its context]. Is that right?"
- **Header:** "Framing"s4h-temporal-timing-analysis
When your agent uses it
Assesses whether now is the right time to act, wait, or prepare. Use when asked 'is now the right time', 'should we wait', 'are we too early', 'timing this decision', 'when to move', or 'momentum'.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
985 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore4,618 bytes
Read SKILL.md
# Temporal Timing Analysis
Timing is often as consequential as the decision itself. The right action at the wrong time fails — too early before conditions are ready, too late after the window has closed. Most timing judgments are made implicitly, with the urgency of the moment substituting for analysis. Making timing explicit means identifying which conditions are present, which are absent, and whether the environment is moving toward or away from readiness.
---
## Your Process
**Step 1: State the Action and Current Context**
Name the action under consideration and describe current conditions — market, organizational, political, technical. The timing analysis is grounded in this specific context.
**Framing check:** Confirm the specific action and context before continuing. State what you've identified — the actual action being timed and the domain it sits in — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the action and its current context]. Is that right?"
- **Header:** "Framing"s4h-writing
When your agent uses it
Routes to the right writing skill for any fiction, non-fiction, or professional writing challenge. Use when you say 'my character feels flat', 'the story isn't working', 'this scene falls flat', 'the dialogue sounds wrong', 'the prose is clunky', 'the argument isn't landing', 'write a report', 'executive summary', 'the tone keeps shifting', 'line editing', 'my world feels thin', 'POV problems', 'inconsistency check', 'write copy', 'technical documentation', 'audience calibration', 'rhetorical analysis', or any time you have a writing problem but aren't sure which specific tool fits.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
2,106 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 Process
- Routing Guide
- Notes
Files
SKILL.mdcore8,792 bytes
Read SKILL.md
# Writing
Every writing problem has a name. Name it precisely, and the fix becomes obvious. The most common mistake is treating a structural problem as a prose problem, or a character problem as a plot problem — applying the wrong tool while the real issue goes unaddressed.
This routing skill reads your situation, identifies the problem type, and connects you to the right technique immediately.
---
## Your Process
### Step 1: Read the Situation
If the user hasn't described their writing challenge yet, ask:
s4h-writing-arc-design
When your agent uses it
Maps and repairs character arcs and thematic arcs by aligning external plot events with internal change. Use when an arc feels unearned, a change feels sudden, or the ending doesn't land. Triggers: 'the arc feels unearned', 'arc design', 'the ending doesn't land', 'character arc', 'thematic arc', 'the change feels sudden', 'the character just changes at the end'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,735 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,122 bytes
Read SKILL.md
# Writing: Arc Design
Arcs feel unearned when the external plot and internal change are independent — when the character changes because the story requires it, not because the events forced it. This is the most common arc failure, and it produces the most visceral reader response: "the character just suddenly becomes a different person." The reader is right. The change happened on a schedule, not as a consequence.
The fundamental principle: the external must create the conditions for the internal. The plot does not just happen *alongside* the character — it *acts on* the character in ways that make the internal change not just possible but necessary. The protagonist's wound must be pressed on, repeatedly, by the specific events of the plot. The defence must be made untenable by the story's demands. The arc endpoint is not the character deciding to change — it is the character having no remaining option except to change, or to break.
The ending is not the change. The ending is the consequence of the change. This distinction matters enormously: if the character's internal shift and the external resolution happen simultaneously, the causation is lost. The internal shift must precede the external resolution, making it possible. The reader needs to see the new belief or new capacity tested against the story's central problem — and the test must require exactly what the old self couldn't have provided.
---
## Your Process
**Step 1: Start State**
What is the character's belief, wound, and worldview at the story's opening? Be specific: not "she is closed off" but "she believes that needing people is weakness — a belief installed by her mother's abandonment when she was nine, which she has managed by becoming self-sufficient to a degree that reads as coldness." The start state must be specific enough to be testable: you should be able to ask of any scene "is this character acting from their opening belief?" and get a clear answer.s4h-writing-argument
When your agent uses it
Builds and repairs persuasive arguments by surfacing the warrant, auditing evidence, addressing counterarguments, and identifying rhetorical substitutes. Use when an argument has holes, the case isn't landing, or evidence isn't connecting to the claim. Triggers: 'build an argument', 'argument structure', 'the argument isn't working', 'op-ed', 'persuasive writing', 'make the case for', 'my argument has holes', 'the evidence doesn't land'.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,736 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,216 bytes
Read SKILL.md
# Writing: Argument
Arguments fail not in the evidence but in the warrant — the unstated principle connecting evidence to claim. The warrant is the assumption that makes the argument work. Most writers never surface it, because to them it is obvious. But the reader may be supplying a different warrant — and reaching a different conclusion from the same evidence.
The structure of every argument:
- **Claim:** What you are asserting to be true
- **Evidence:** The facts, data, examples, or observations that support it
- **Warrant:** The principle or assumption that connects the evidence to the claim
Example: "Remote workers are more productive (evidence). Therefore we should adopt a remote work policy (claim)." The warrant — "policies should be adopted when they increase productivity" — sounds obvious but is not. A reader who believes "productivity must be balanced against team cohesion and culture" will not accept the warrant, and the argument fails for them even if the evidence is strong. Making the warrant explicit forces both writer and reader to examine the actual assumption.
The second most common failure: the strongest counterargument is not addressed. An argument that doesn't engage its best objection is not a complete argument — it is a one-sided brief that any reader with reservations can dismiss. Addressing the counterargument, not to concede but to answer it, is what makes an argument persuasive rather than merely insistent.
---s4h-writing-audience-calibration
When your agent uses it
Calibrates writing for a specific reader by profiling their knowledge, concerns, and relationship to the topic — then rewriting for that reader without changing the substance. Use when content is too technical, too basic, or framed for the wrong audience. Triggers: 'write for a specific audience', 'audience calibration', 'this needs to work for non-technical readers', 'the audience isn't the right fit', 'calibrate this for', 'it's too technical / not technical enough', 'recalibrate this for'.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
1,590 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,727 bytes
Read SKILL.md
# Writing: Audience Calibration
Calibration failures come in two forms: over-explanation and under-explanation. Over-explanation treats experts as novices — it defines terms they know, explains concepts they've mastered, and adds context they don't need. This reads as condescending, and the expert reader disengages. Under-explanation treats novices as experts — it uses jargon without definition, assumes mental models the reader doesn't have, and skips the connections that make the logic followable. This reads as inaccessible, and the novice reader gives up.
The critical insight: calibration does not require changing the substance of what is being communicated. The same analysis can serve a technical expert and a non-technical decision-maker if it is correctly calibrated for each. The facts don't change; the entry point, assumed knowledge, vocabulary, framing, and emphasis all do.
The three dimensions of calibration:
- **Knowledge calibration:** What does this reader already know? What can be assumed, what needs brief context, what needs explanation?
- **Stakes calibration:** What does this reader care about? The engineer cares about implementation; the product manager cares about user impact; the executive cares about business consequences. Same finding, different emphasis.
- **Relationship calibration:** Is the reader expert or novice, friendly or skeptical, time-pressed or engaged? Each requires different structural choices.
---
## Your Processs4h-writing-character-development
When your agent uses it
Engineers psychologically compelling characters by mapping want vs. need, wound, defence mechanism, and defining contradiction. Use when a character feels flat, underdeveloped, or unconvincing. Triggers: 'my character feels flat', 'character development', 'make this character feel real', 'this character isn't working', 'character work', 'how do I develop this character'.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,713 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,190 bytes
Read SKILL.md
# Writing: Character Development
Flat characters come from describing traits rather than engineering contradictions. When a writer says "she's brave and determined," they have a label — not a person. Compelling characters feel real because they hold two things in tension simultaneously: they want something and need something different; they have a strength that doubles as a weakness; they act from a wound they can't fully see. These tensions generate unpredictable, specific behaviour that no list of adjectives could produce.
The key diagnostic is the want/need split. The want is what the character consciously pursues — their stated goal, their driving motivation as they'd describe it. The need is what would actually fulfil them — which is always different, often the opposite, and usually something they're avoiding. This gap between want and need is where character lives. It generates internal conflict, drives the arc, and makes every action simultaneously understandable and complicated.
---
## Your Process
**Step 1: State the Core Want vs. Core Need**
Name what the character consciously wants (their goal as they understand it) and what they actually need (what would genuinely fulfil or redeem them). These should differ — the want is typically external, visible, and achievable; the need is internal, invisible to the character, and requires change. If want and need are identical, the character has no arc.
**Framing check:** Confirm the specific character before continuing. State what you've identified — the character's name or role, the story context, and the central tension as you've read it — in one sentence, then use `AskUserQuestion`:s4h-writing-copy
When your agent uses it
Writes and audits marketing copy, landing pages, ad copy, email copy, and product descriptions using the attention-desire-action framework. Use when copy isn't converting, describes features instead of benefits, or fails to earn the reader's next step. Triggers: 'copywriting', 'ad copy', 'landing page', 'email copy', 'marketing copy', 'write copy', 'the copy isn't converting', 'product description', 'headline isn't working'.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,800 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,116 bytes
Read SKILL.md
# Writing: Copy
Copy fails when it describes the product rather than the reader's experience of having it. "Comprehensive workflow management platform with real-time collaboration" describes features. "Your team stops losing work in email chains" describes an experience. The reader buys the experience, not the feature set. Every piece of copy that describes the product from the product's point of view rather than the reader's is leaving conversion on the table.
The three-layer model maps every effective piece of copy:
**Attention (the opening):** The sole function of the first line is to earn the second line. Not to establish credibility, explain the product, or summarise the offer — to earn the next sentence. Attention is lost in the first three seconds. The headline must name a specific benefit or problem, not a category. "Project management software" is a category. "Your team ships on time, every time" is a claim that addresses a specific pain.
**Desire (the body):** The body must make the reader feel the gap between their current state and a better one. This is not enthusiasm or puffery — it is specificity. "Boost productivity" is enthusiasm. "Cut the time your team spends on status updates from 3 hours a week to 10 minutes" is specific and credible. The desire is created not by telling the reader the product is good, but by making them feel what it would be like to have the problem solved.
**Action (the CTA):** The call to action must be singular (one action only), specific (not "learn more" but "start your free trial"), and low-friction (the language should make action feel easy and obvious, not like a commitment or a risk).
---
s4h-writing-dialogue
When your agent uses it
Diagnoses and repairs dialogue for subtext, voice differentiation, exposition, and forward momentum. Use when dialogue sounds wrong, on-the-nose, or when characters all sound the same. Triggers: 'the dialogue sounds wrong', 'dialogue feels on the nose', 'dialogue review', 'characters sound the same', 'dialogue fix', 'dialogue is too direct', 'the dialogue explains too much'.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,665 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,832 bytes
Read SKILL.md
# Writing: Dialogue
Dialogue fails in two primary ways: it says exactly what it means (no subtext), or it explains things the characters already know (exposition dressed as conversation). Both failures produce the same effect on the reader — a sense of flatness, of the author's hand visible, of characters becoming mouthpieces rather than people.
Real conversation is oblique. People in conflict rarely say "I'm angry with you." They talk about something else. The anger is present in what they say about the dishes, the schedule, the way someone looks. The subtext *is* the scene — the surface conversation is the vehicle for it. When dialogue is on the nose, the subtext and the surface are the same thing, which means there is no scene — only information delivery.
Voice differentiation is the second major failure point. Every character has a distinct rhythm of thought, a vocabulary range shaped by their history, evasion patterns specific to their wound, and a relationship to silence. When characters sound interchangeable, the dialogue's only differentiator is the attribution ("he said / she said") — which means the characters, on the page, don't exist yet.
---
## Your Process
**Step 1: Speaker Goals — Surface vs. Subtext**
For each speaker in the exchange, identify:s4h-writing-executive-summary
When your agent uses it
Produces executive summaries, 1-page briefs, and board-level documents by extracting the situation, key findings, implications, and recommendation — answer-first, one page maximum. Use when a lengthy document needs a senior-audience brief that enables a decision. Triggers: 'executive summary', 'summarise this for a senior audience', '1-page brief', 'TL;DR for leadership', 'distil this', 'board summary', 'write a brief'.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
1,715 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,911 bytesSKILL.mdcore7,911 bytes
Read SKILL.md
# Writing: Executive Summary
Executive summaries fail when they summarise the document rather than answering the reader's question. A summary of a 40-page analysis is not what an executive needs. They need: what is the situation, what are the three things most important to know, what does it mean for their decision, and what should happen next. In that order. In one page.
The fundamental principle: the executive is not the end reader of your analysis — they are a decision-maker who needs the *output* of your analysis in a form that enables action. The detail, the methodology, the full data — that stays in the main document. The executive summary gives them what they need to act without reading the full document.
Four common failures:
- **Summarising the process, not the answer:** "We conducted a comprehensive analysis of three market segments, reviewing 47 data sources over 8 weeks." The executive doesn't need to know how long it took — they need to know what it found.
- **Findings without implications:** Stating what happened without stating what it means for the decision at hand.
- **False balance:** Including minor findings to be thorough, diluting the signal with noise. Three things that matter are better than twelve things that range from critical to marginal.
- **Passive language on the recommendation:** "It may be worth considering..." — the executive summary is where the recommendation is made, not hedged.
---
s4h-writing-inconsistency-audit
When your agent uses it
Runs four systematic passes to identify timeline errors, character logic violations, world-rule breaks, and physical continuity errors. Use when a manuscript has contradictions, continuity problems, or logic violations. Triggers: 'there are contradictions', 'continuity errors', 'inconsistency check', 'the character shouldn't know that', 'timeline doesn't add up', 'continuity audit', 'inconsistencies in the manuscript'.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
1,694 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,252 bytes
Read SKILL.md
# Writing: Inconsistency Audit
Inconsistencies undermine the reader's trust more efficiently than almost any other flaw — because they signal that the author lost track of their own world. The reader's contract with a story is: I will suspend disbelief in exchange for internal coherence. One visible inconsistency tells the reader the author may have lost the thread, and the reader will spend the rest of the story half-watching for the next crack rather than being inside the experience.
Four types of inconsistency require separate passes, because they operate at different levels and have different causes:
**Timeline inconsistency:** Events that are out of chronological order, time spans that don't add up, characters who are in two places at once, seasons that shift unexpectedly.
**Character logic inconsistency:** Characters who act contrary to their established psychology without earned cause, who know things they couldn't know, who forget things they must know, who respond to situations in ways their established temperament doesn't allow.
**World-rules inconsistency:** The story's established physics, magic, technology, or social rules that function differently in different scenes — usually because the plot needs them to.
**Physical continuity inconsistency:** Objects that change hands, locations, or appearance without explanation; characters whose physical description changes; room layouts that contradict themselves.
s4h-writing-line-editing
When your agent uses it
Applies five-category line-editing passes to identify and repair redundancy, nominalisations, passive voice, rhythmic monotony, and throat-clearing. Use when prose is clunky, wordy, or mechanically flawed. Triggers: 'the sentences are clunky', 'line editing', 'the prose is wordy', 'tighten this up', 'sentence-level editing', 'too many passive constructions', 'the writing is verbose'.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,723 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,995 bytes
Read SKILL.md
# Writing: Line Editing
Line editing addresses mechanical failures at the sentence level — the problems that make competent writing feel clunky, slow, or airless. These are distinct from prose quality problems (which `/s4h-writing-prose-elevation` addresses): line editing is about removing what is broken, not elevating what is merely flat.
Five failures account for the majority of sentence-level problems:
**Redundancy:** Saying the same thing twice, either in the same sentence or in adjacent sentences. Often invisible to the writer because the repetition feels like emphasis or clarity.
**Nominalisation (zombie nouns):** Converting verbs and adjectives into noun forms, burying the action inside the noun. "Made a decision" instead of "decided." "Had a realisation" instead of "realised." "Conducted an investigation" instead of "investigated." Every nominalisation costs one verb, reduces clarity, and adds bureaucratic weight.
**Agency-obscuring passive voice:** Not all passive voice is wrong — "Mistakes were made" is passive, but sometimes the subject genuinely isn't known or relevant. The problem is passive voice that obscures *who did what*, when the agent matters: "The decision was made to cut the programme" when the sentence needs to say who cut it.
**Rhythmic monotony:** All sentences the same length. All sentences starting the same way. A page that reads like a manual because every sentence is a main clause, subject-verb-object, approximately fifteen words, followed by another exactly like it. Rhythm variation creates pace, emphasis, and the sense of a living mind behind the prose.
s4h-writing-plot-structure
When your agent uses it
Diagnoses structural failures in a story using the five-beat dramatic framework — inciting incident, first turning point, midpoint, dark night, climax. Use when a plot isn't working, the middle drags, momentum is lost, or the story feels loose. Triggers: 'the story isn't working', 'plot structure', 'my middle drags', 'the plot feels loose', 'story structure', 'momentum problem', 'the structure is off'.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
1,549 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,318 bytes
Read SKILL.md
# Writing: Plot Structure
Most plot problems are structural. When readers say "it loses momentum," "the middle drags," or "the ending felt rushed," they are usually reporting structural failures, not prose failures. The sentences may be excellent. The problem is in the architecture.
The five-beat structure is not a formula — it is a description of how dramatic tension works. Each beat is defined by what it does to the story's central question, not by where it falls in the word count. A thriller and a literary novel obey the same structural logic: the reader holds a question, the beats escalate the stakes of that question, and the climax answers it. The internal and external arcs must mirror each other: the external plot generates the conditions that force the internal change.
The most common structural failures: a missing first turning point (so the protagonist never truly commits, meaning there are no real stakes); a flat midpoint (so the story runs in a straight line rather than shifting direction); and a dark night that is too short (so the climax feels unearned).
---
## Your Process
**Step 1: Inciting Incident**
What disrupts the equilibrium? Identify the event that breaks the story's opening state and raises the central question. Diagnostic: does this event happen *to* the protagonist, or merely *near* them? An inciting incident that the protagonist can ignore is not functioning — it must demand response. Does it raise a specific, answerable question that will carry the story?s4h-writing-pov
When your agent uses it
Audits point-of-view for violations, consistency, and fit. Use when narration feels inconsistent, when there is unwanted head-hopping, or when the chosen POV isn't serving the story. Triggers: 'POV problems', 'head-hopping', 'point of view', 'the narration feels inconsistent', 'POV violations', 'narrative perspective', 'sometimes we know things the character shouldn't'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,606 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,603 bytes
Read SKILL.md
# Writing: Point of View
POV is a contract with the reader about what the narration can know. The moment that contract is violated — the moment the narration accesses something it has promised not to access — the reader's trust breaks. Usually they don't know why. They just feel the seam, the moment the author's hand becomes visible. "How did we know that?" is the diagnostic question.
Each POV type makes a different promise:
**First person:** The narrator tells us what they experienced, observed, thought, and felt. They cannot know what other characters are thinking unless they are told or infer it (and the inference should be flagged as inference). They can be unreliable — their account of events may be shaped by their psychology, their blindspots, their desire to present themselves well.
**Close third person:** Narration follows one character's subjective experience. The narration can access their thoughts and feelings but cannot access anyone else's interior. Physical details that the POV character couldn't observe (what their own face looks like, what's happening in a room they're not in) require specific handling. Thought and feeling are rendered from inside, not described from outside.
**Omniscient:** The narrator has access to any mind. But omniscient POV is not a licence for chaos — it must be used consistently. An omniscient narrator who dips into three minds in one scene and then goes external in the next has not chosen omniscient POV; they have abandoned POV control entirely.
The fit question is as important as the violation question: does the chosen POV serve what the story is trying to do? A story whose power lives in dramatic irony (the reader knows something the protagonist doesn't) may work better in third than first. A story whose power is unreliable memory may need first person. The POV choice is not arbitrary — the story's core effect often depends on it.
s4h-writing-prose-elevation
When your agent uses it
Raises the quality of competent but flat prose by targeting abstraction, weak verbs, and sensory absence. Use when writing is error-free but doesn't sing — when it reads as competent but not compelling. Triggers: 'the writing is flat', 'prose elevation', 'competent but not compelling', 'lift this writing', 'the prose needs work but isn't broken', 'make this sing', 'the prose is fine but forgettable'.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,767 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,179 bytes
Read SKILL.md
# Writing: Prose Elevation
Prose elevation is not about imposing a style — it's about realising the latent quality already present. Flat prose usually fails in three specific ways, and fixing these three things is enough to significantly raise the quality without overwriting or artificially inflating the voice.
**Abstraction without grounding:** The writer reaches for the general statement — "she felt profound grief" — when a specific image would land harder and trust the reader more. "She kept finding his reading glasses in places she hadn't thought to look." Abstraction summarises experience; specific images recreate it. The reader feels what the abstract statement tries to tell them.
**Weak verbs:** Was, had, got, made, felt, seemed, looked, walked, went. These verbs are not wrong — they are just underloaded. "The room was cold" tells us almost nothing. "The cold crept in under the door and settled at floor level" gives us a room. Precise verbs do the work that adverbs are often asked to do — and do it better.
**Sensory absence:** Prose that lives entirely in dialogue and action, with no texture of the physical world — no temperature, smell, sound, surface — feels disembodied. The reader floats above the scene rather than inhabiting it. Sensory detail is not decoration; it is the mechanism by which the reader is placed inside the experience.
These three failures are addressable without changing a writer's voice. The elevation preserves what is already working and deepens it.
---
s4h-writing-report
When your agent uses it
Writes and audits business reports, briefing documents, and information reports for answer-first structure, precision, hierarchy, and navigability. Use when a report buries its findings, is written for the writer rather than the reader, or lacks clear structure. Triggers: 'write a report', 'report writing', 'business report', 'briefing document', 'information report', 'research summary', 'the report isn't clear', 'buries the findings'.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,543 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,204 bytes
Read SKILL.md
# Writing: Report
Reports fail when they are written for the writer rather than the reader. The writer knows the context, did the work, and wants to show the rigour of the process. The reader needs to know the answer, understand its implications, and decide what to do — usually in less time than the writer spent writing. These are incompatible objectives, and when the report serves the writer's needs, it fails the reader.
The most common report failures:
**Context before answer:** The report explains how the analysis was done before stating what it found. The reader who needs to act has to mine through methodology to find the claim.
**Findings without implications:** The report states what happened but not what it means. "Revenue declined 12% in Q3" is a finding. "Revenue declined 12% in Q3, driven primarily by a 31% drop in enterprise segment that is likely to continue unless the pricing model is revised" is an implication. Readers who need to decide need implications, not just findings.
**Vague quantification:** "Significant growth," "substantial decline," "many customers." These phrases communicate nothing. If a number exists, use it. If it doesn't, acknowledge the absence explicitly.
**Non-navigability:** A report that can only be understood by reading it from beginning to end has failed. The reader who needs the answer to one specific question should be able to find it. Section headers, a clear hierarchy, and an executive summary are not optional niceties — they are the delivery mechanism.
s4h-writing-restructure
When your agent uses it
Diagnoses and repairs structural problems in non-fiction, essays, and documents — wrong order, buried lead, wrong ending, proportion errors. Use when a piece is in the wrong order, starts too late, or spends space on the wrong things. Triggers: 'the piece is in the wrong order', 'restructure', 'buries the lede', 'the structure is off', 'reorganise this', 'the ending is in the wrong place', 'takes too long to get to the point'.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,579 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,394 bytes
Read SKILL.md
# Writing: Restructure
Structural problems are the hardest to see from inside the piece — because from inside, structure is invisible. The writer always knows where they're going; they know the context, the backstory, why the claim matters. The reader only knows where they've been. The result: pieces that are perfectly clear to the writer and impenetrable to the reader, because the reader doesn't have the context that makes the opening make sense, doesn't know that the important claim is on page four, and has no way to distinguish the load-bearing material from the scaffolding.
Three structural failures account for the majority of structurally broken pieces:
**Burying the lead:** The piece starts with context, background, or setup rather than the claim or finding. The writer needed to write the setup to arrive at the claim. The reader doesn't need it — or needs a fraction of it, after the claim has been stated.
**Wrong ending:** The piece stops before it resolves. The real insight is in the second-to-last paragraph. The final paragraph is a softening or a retreat. Or the piece stops at the conclusion of the argument but before its implications — leaving the reader with the logic but not the meaning.
**Wrong proportion:** The piece spends three pages on the least important point and half a page on the most important one. The proportion reflects the order in which the writer discovered things, not the order of their importance.
All three failures have the same cause: the structure was not designed for the reader — it was inherited from the process of writing.
s4h-writing-rhetoric
When your agent uses it
Analyses what a piece of writing is doing rhetorically — its rhetorical situation, explicit argument vs. buried frame, appeals map, and loaded language. Use to surface assumptions, examine persuasion techniques, or understand how a piece is working. Triggers: 'rhetorical analysis', 'what is this piece doing rhetorically', 'rhetoric', 'analyze this argument', 'how is this persuasive', 'what assumptions is this making', 'loaded language', 'hidden assumptions', 'what is this piece really arguing'.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
1,865 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore8,827 bytes
Read SKILL.md
# Writing: Rhetoric
Rhetoric analysis asks not "what does this say" but "what is this doing." Every piece of writing has a rhetorical situation — a speaker, an audience, a purpose, a context — and makes rhetorical moves that are often invisible to both writer and reader. The analysis surfaces what is operating below the explicit argument.
The most important distinction: **the explicit argument vs. the rhetorical frame**. The explicit argument is what the text claims. The rhetorical frame is what the text assumes without stating — the premises, values, and world-views that must be accepted for the argument to work, and which are never examined because they are presented as neutral common ground. The frame often does more work than the argument, and it is almost never examined.
Example: a piece arguing for stricter immigration policy may frame "the nation" as a coherent entity with interests that can be defended, may frame immigration as a *flow* rather than people making decisions, and may frame the relevant question as "how many" rather than "who benefits and who bears costs." None of these framing choices are acknowledged as choices — they are presented as the natural way to think about the issue. But they are doing enormous rhetorical work.
The classical appeals — logos (reason), ethos (authority/credibility), pathos (emotion) — describe the rhetorical resources available to any writer. Understanding which appeals dominate a piece, and whether they are being used proportionately and honestly, is central to rhetorical analysis.
---
## Your Process
s4h-writing-scene-construction
When your agent uses it
Diagnoses and repairs individual scenes using the want/obstacle/outcome framework. Every scene must change the story's state. Use when a scene feels flat, static, or purposeless. Triggers: 'this scene isn't working', 'scene construction', 'scene feels flat', 'scene review', 'fix this scene', 'the scene doesn't do anything', 'should I cut this scene'.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,674 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,490 bytes
Read SKILL.md
# Writing: Scene Construction
Every scene is a mini-story. It needs a want, an obstacle, and an outcome. Without these three elements, it is not a scene — it is a passage of time. The reader experiences the difference viscerally, even if they can't name it: a scene without these elements reads as static, as nothing happening, as the story marking time.
The outcome is the most frequently broken element. Every scene must end in a different state than it began. The outcome must be one of four types: **yes-but** (protagonist gets what they want but at a cost or complication), **no-and** (denied, and things are worse), **no-but** (denied, but something else is gained), or **yes-and** (achieved, and something else follows). Any scene that ends with an unmodified yes or no is a scene that hasn't done its work.
The second most common failure: scenes that serve one function when they need to serve two. A scene that only reveals character, only provides information, or only advances plot is vulnerable to cutting. The best scenes do two or three things at once — and the obligation to do multiple things simultaneously is what generates the density that makes scenes feel necessary.
---
## Your Process
**Step 1: Scene Goal**
What does the POV character want in *this scene*? Not what they want in the story — what they want right now, from this specific situation. Be concrete: "to convince Marcus to lend her the money," not "to solve her financial problems." If the goal can't be stated specifically, the scene has no engine.s4h-writing-technical
When your agent uses it
Writes and audits technical documentation, API docs, user guides, and specifications for completeness, sequence, precision, and audience calibration. Use when documentation is confusing, assumes too much knowledge, or leaves gaps a user can't bridge. Triggers: 'technical writing', 'API documentation', 'write documentation', 'user guide', 'technical docs', 'the documentation is confusing', 'write a spec', 'docs are missing steps'.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,635 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,979 bytes
Read SKILL.md
# Writing: Technical
Technical writing fails when it is written for the person who already knows how the system works. The person who already knows doesn't need the document. The document is for the person who doesn't know — and that person's experience of the document is the only test that matters. The test is simple: can a reader with the assumed knowledge execute the task using only this document? If they cannot, something is missing.
This is a higher bar than it sounds. Technical writers who know the system well have difficulty seeing the gaps — because for them, nothing is missing. The prerequisite knowledge is so obvious it doesn't seem worth stating. The step that requires understanding the system's mental model doesn't look like a step — it looks like common sense. These invisible assumptions are where most documentation fails.
The five failure modes in technical writing:
**Audience miscalibration:** Assumes knowledge the reader doesn't have, or over-explains what the reader already knows. Both are wrong. The first makes the document unusable; the second makes it condescending.
**Incompleteness:** Steps that require bridging knowledge the document doesn't provide. Often invisible to the writer because the knowledge is automatic.
**Sequence errors:** Prerequisites stated after they are needed, steps in the wrong order, troubleshooting information buried after the task it applies to.
s4h-writing-tone-alignment
When your agent uses it
Diagnoses and repairs tone drift — shifts in register, formality, warmth, or rhythm that make a piece feel like it was written by multiple people or in multiple moods. Use when the voice changes mid-piece without intention. Triggers: 'the tone keeps shifting', 'tone drift', 'tone alignment', 'inconsistent register', 'the voice changes mid-piece', 'this sounds like different writers'.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,573 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,424 bytesSKILL.mdcore7,424 bytesSKILL.mdcore7,424 bytesSKILL.mdcore7,424 bytes
Read SKILL.md
# Writing: Tone Alignment
Tone drift is what happens when a piece moves through multiple registers without intention — formal to casual, warm to clinical, urgent to contemplative — destroying the reader's sense of who is speaking. The reader cannot trust a voice they cannot locate. When they feel the voice shift, they become aware they are reading a *document* rather than inhabiting a communication. The intimacy, or the authority, or the momentum — whatever the piece was building — dissolves.
Tone drift is most common in three situations: multi-author documents, where different contributors have different natural voices; long pieces written over time, where the writer's mood, energy, or approach has changed between sessions; and pieces assembled from different source material, where the register of the sources bleeds into the synthesis.
Tone has multiple dimensions, and they can drift independently:
- **Formality:** Where on the formal/informal spectrum? Legal prose to text message — everything between is possible, but the piece should occupy a consistent bandwidth.
- **Warmth:** Where on the cold-to-warm spectrum? Institutional distance to personal intimacy?
- **Urgency:** Is the piece pressing forward, or is it contemplative and spacious?
- **Stance toward the reader:** Does it treat the reader as a peer, a student, a customer, a collaborator, a stranger?
- **Sentence rhythm:** Short and punchy, or long and periodic? The rhythm carries register even when the words don't shift.
---s4h-writing-voice-consistency
When your agent uses it
Extracts a voice fingerprint from strong existing passages and uses it to audit and repair voice departures. Use when multiple contributors have created a fractured document, when brand voice has drifted, or when the writing doesn't sound like one person. Triggers: 'the voice isn't consistent', 'voice consistency', 'this doesn't sound like us', 'multi-author document', 'maintain voice', 'brand voice', 'the writing sounds like different people'.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,654 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,738 bytes
Read SKILL.md
# Writing: Voice Consistency
Voice is the sum of choices: sentence length preference, vocabulary range, degree of formality, stance toward the reader, use of metaphor and analogy, tolerance for digression, the character that comes through even in functional writing. It is recognisable even when you can't name what you're recognising. When it's absent or fractured, the reader feels it as a nagging sense that the writing has no centre — that no one is actually speaking to them.
The critical insight: voice can be *extracted* and *characterised* from strong existing passages, and that characterisation becomes an auditable standard. This means voice consistency is not a mysterious quality that can only be felt — it is a set of identifiable, describable choices that can be held constant across contributors, sections, and time.
For brand and organisational writing, this extracted voice fingerprint becomes the foundation of a practical style brief — not a list of rules about comma usage, but a description of who is speaking and how they sound, with examples that any contributor can use as a reference.
---
## Your Process
**Step 1: Extract Defining Characteristics**
From the strongest existing passages — the sections that feel most alive, most like the brand or the writer's best work — identify 5–7 defining characteristics. These should be specific enough to be testable. Not "clear and friendly" but:s4h-writing-worldbuilding
When your agent uses it
Audits a fictional world for internal consistency, texture, economy, and constraint-story alignment. Use when a world feels thin, generic, like a backdrop rather than a place people actually inhabit. Triggers: 'the world feels thin', 'worldbuilding', 'my world doesn't feel real', 'the setting is generic', 'world audit', 'the world feels like a backdrop'.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,538 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 Process
- Human Check-in
- Output Format
- Notes
- What's Next
Files
SKILL.mdcore7,464 bytes
Read SKILL.md
# Writing: Worldbuilding
Worlds fail when they are described rather than inhabited. The difference is texture. A described world tells you what things are — "a dystopian future where technology controls society." An inhabited world shows you what it costs to live there: what people eat, what they fear, what they fight over, what they take for granted, what they lie about. The first is a category. The second is a place.
The test of a well-built world is not comprehensiveness — it's necessity. Does the world create the story's conflict, or is it merely a backdrop? In a well-integrated world, the story's central problem could only happen in this world, in this configuration. The colony's resource scarcity creates the political structure that creates the protagonist's impossible choice. Remove the world, and the story doesn't exist. In a backdrop world, you could set the same story in contemporary New York without changing anything essential.
The second test: specificity of texture. The world must feel inhabited not through encyclopaedic exposition, but through specific, surprising detail that implies a larger reality. One specific food item, one specific ritual, one specific slang term tells the reader more about the world than three pages of history. The detail does double duty — it characterises the world and implies the systems that produced it.
---
## Your Process
**Step 1: Rules**
Map the world's governing systems: physical, social, technological, magical, or political. What are the rules that cannot be broken? Are they internally consistent — does the magic system create loopholes the story conveniently exploits? Does the technology appear and disappear based on plot convenience? Rules only function as worldbuilding if they constrain the story.Skills included
- s4h
- s4h-aesthetic
- s4h-aesthetic-coherence-check
- s4h-aesthetic-elegance-testing
- s4h-aesthetic-pattern-detection
- s4h-aesthetic-simplicity-analysis
- s4h-analogy
- s4h-analogy-boundary-testing
- s4h-analogy-domain-transfer
- s4h-analogy-perspective-shifting
- s4h-analogy-structure-mapping
- s4h-cognition
- s4h-cognition-attention
- s4h-cognition-cognitive-load
- s4h-cognition-mental-models
- s4h-cognition-metacognition
- s4h-communication
- s4h-communication-audience-modeling
- s4h-communication-clarity-audit
- s4h-communication-medium-selection
- s4h-communication-objection-mapping
- s4h-constraint
- s4h-constraint-hardness-testing
- s4h-constraint-rule-inversion
- s4h-constraint-scope-reduction
- s4h-constraint-workaround-mapping
- s4h-creativity
- s4h-creativity-alternatives
- s4h-creativity-assumption-excavator
- s4h-creativity-brainstorm
- s4h-creativity-concept-fan
- s4h-creativity-consider-factors
- s4h-creativity-lateral-thinking
- s4h-creativity-other-perspectives
- s4h-creativity-plus-minus-interesting
- s4h-creativity-provocation
- s4h-creativity-random-entry
- s4h-creativity-six-hats
- s4h-creativity-water-logic
- s4h-decision
- s4h-decision-criteria-weighting
- s4h-decision-option-mapping
- s4h-decision-premortem-analysis
- s4h-decision-reversibility-analysis
- s4h-design
- s4h-design-constraints
- s4h-design-iteration
- s4h-design-simplicity
- s4h-design-user-needs
- s4h-ecology
- s4h-ecology-carrying-capacity
- s4h-ecology-interdependence
- s4h-ecology-keystone-species
- s4h-ecology-succession
- s4h-economics
- s4h-economics-coordination
- s4h-economics-externalities
- s4h-economics-incentive-mapping
- s4h-economics-margin
- s4h-economics-opportunity-cost
- s4h-emotional
- s4h-emotional-motivation-mapping
- s4h-emotional-resistance-diagnosis
- s4h-emotional-stakes-mapping
- s4h-emotional-trust-audit
- s4h-epistemology
- s4h-epistemology-epistemic-status
- s4h-epistemology-justification
- s4h-epistemology-knowledge-types
- s4h-epistemology-limits
- s4h-ethics
- s4h-ethics-bias-check
- s4h-ethics-check
- s4h-ethics-consent-review
- s4h-ethics-council
- s4h-ethics-crisis-triage
- s4h-ethics-data-audit
- s4h-ethics-empathy-circle
- s4h-ethics-impact-scan
- s4h-ethics-vendor-review
- s4h-evolution
- s4h-evolution-arms-race
- s4h-evolution-fitness-landscape
- s4h-evolution-niche
- s4h-evolution-variation-selection
- s4h-game-theory
- s4h-game-theory-auction
- s4h-game-theory-coalition
- s4h-game-theory-equilibrium
- s4h-game-theory-iterated
- s4h-game-theory-mechanism-design
- s4h-game-theory-prisoners-dilemma
- s4h-game-theory-signaling
- s4h-historical
- s4h-historical-cycle-detection
- s4h-historical-failure-analysis
- s4h-historical-lesson-extraction
- s4h-historical-precedent-analysis
- s4h-identity
- s4h-identity-character-testing
- s4h-identity-mission-alignment
- s4h-identity-values-clarification
- s4h-information
- s4h-information-compression
- s4h-information-entropy
- s4h-information-redundancy
- s4h-information-signal-noise
- s4h-investigation
- s4h-investigation-claim-decomposition
- s4h-investigation-counter-hypothesis
- s4h-investigation-evidence-audit
- s4h-investigation-source-trace
- s4h-investigation-triangulation
- s4h-linguistics
- s4h-linguistics-connotation
- s4h-linguistics-framing
- s4h-linguistics-pragmatics
- s4h-linguistics-semantic-drift
- s4h-logic
- s4h-logic-argument-validation
- s4h-logic-causality-mapping
- s4h-logic-check
- s4h-logic-consistency-check
- s4h-logic-constraint-mapping
- s4h-logic-council
- s4h-logic-fixer
- s4h-mindset
- s4h-mindset-flow
- s4h-mindset-growth
- s4h-mindset-positive
- s4h-mindset-reframe
- s4h-mindset-stoic
- s4h-narrative
- s4h-narrative-audience-modeling
- s4h-narrative-frame-analysis
- s4h-narrative-structure-mapping
- s4h-narrative-tension-mapping
- s4h-network
- s4h-network-centrality
- s4h-network-contagion
- s4h-network-effects
- s4h-network-weak-ties
- s4h-play
- s4h-play-constraint-inversion
- s4h-play-perspective-reversal
- s4h-play-stimulus-generation
- s4h-play-worst-case-reversal
- s4h-probability
- s4h-probability-base-rate-anchoring
- s4h-probability-confidence-calibration
- s4h-probability-expected-value-calculation
- s4h-probability-scenario-weighting
- s4h-psychology
- s4h-psychology-behavior-change
- s4h-psychology-cognitive-biases
- s4h-psychology-heuristics
- s4h-psychology-motivation
- s4h-psychology-persuasion
- s4h-resource
- s4h-resource-allocation-analysis
- s4h-resource-bottleneck-analysis
- s4h-resource-leverage-mapping
- s4h-resource-waste-audit
- s4h-sensory
- s4h-sensory-detail-mining
- s4h-sensory-signal-detection
- s4h-sensory-structured-observation
- s4h-social
- s4h-social-coalition-mapping
- s4h-social-dynamics-analysis
- s4h-social-incentive-analysis
- s4h-social-power-mapping
- s4h-strategy
- s4h-strategy-alliance
- s4h-strategy-deception
- s4h-strategy-force-economy
- s4h-strategy-intelligence
- s4h-strategy-positioning
- s4h-strategy-terrain
- s4h-strategy-timing
- s4h-strategy-victory
- s4h-systems
- s4h-systems-archetype-matching
- s4h-systems-emergence-detection
- s4h-systems-feedback-mapping
- s4h-systems-leverage-analysis
- s4h-temporal
- s4h-temporal-cycle-detection
- s4h-temporal-futures-mapping
- s4h-temporal-horizon-mapping
- s4h-temporal-timing-analysis
- s4h-writing
- s4h-writing-arc-design
- s4h-writing-argument
- s4h-writing-audience-calibration
- s4h-writing-character-development
- s4h-writing-copy
- s4h-writing-dialogue
- s4h-writing-executive-summary
- s4h-writing-inconsistency-audit
- s4h-writing-line-editing
- s4h-writing-plot-structure
- s4h-writing-pov
- s4h-writing-prose-elevation
- s4h-writing-report
- s4h-writing-restructure
- s4h-writing-rhetoric
- s4h-writing-scene-construction
- s4h-writing-technical
- s4h-writing-tone-alignment
- s4h-writing-voice-consistency
- s4h-writing-worldbuilding
Repository facts
- License
- MIT
- Created
- May 23, 2026
- Last pushed
- Jul 15, 2026
- Forks
- 25
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 92 notes
skills/s4h-aesthetic-coherence-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-aesthetic-pattern-detection/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-analogy-boundary-testing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-analogy-structure-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-cognition-attention/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-hardness-testing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-hardness-testing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-hardness-testing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-workaround-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-workaround-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-constraint-workaround-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-creativity-assumption-excavator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-creativity-water-logic/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology-interdependence/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology-interdependence/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology-interdependence/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology-interdependence/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/s4h-ecology-keystone-species/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 3 network referencesin 1 file: .claude-plugin/plugin.json:7
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: s4h-writing-technical/SKILL.md:59
- No requests to vote in Hot
Show all 4 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"email": "fitzsimons.finn@gmail.com" }, "repository": "https://github.com/human-avatar/skills-for-humanity", - Network accessline 8
}, "repository": "https://github.com/human-avatar/skills-for-humanity", "license": "MIT", - Network accessline 9
"repository": "https://github.com/human-avatar/skills-for-humanity",
skills/s4h-writing-technical/SKILL.md
- Access to secretsline 59
[Credential-related source omitted]
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.
Signal confidence: 1 fact
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored values4h-writing-technical/SKILL.md:59Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/s4h/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/s4h/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/s4h/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/s4h/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/s4h/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.
