Not in the top 1,000 by GitHub stars
yogsoth-ai/de-anthropocentric-research-engine
Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis formation and experiment design itself. 267 markdown skills form a research graph: 51 operations built from 216 atomic steps, any order, explicit backtracking; the plan is approved before it runs and interrupted runs resume. npx install, no runtime, no API key
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/abstract-structure/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/adjudicate-exchange/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/adjust-abstraction-scope/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/adversarial-deliberation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/aggregate-ranking/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analogical-discovery/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-constraints-readiness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-experiment-results/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-future-scenarios/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-heterogeneity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-intervention/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-leaderboard-dynamics/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-patent-citation-network/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-scaling-regime/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/analyze-temporal-trajectory/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/apply-perturbation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/apply-question-framework/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/apply-separation-principle/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/apply-stage-gate/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/apply-veto-filter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/appreciative-reframe/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-construct-validity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-evidence-saturation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-goal-feasibility/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-patent-claim-scope/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-patent-legal-status/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-prior-art-and-claims/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-problem-wickedness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-publication-bias/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-question-quality/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-ranking-consistency/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-readiness-dimension/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-removability/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-sensitivity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assess-system-boundary/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/assumption-stress-test/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/atomize-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/atomize-concept/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/attach-evidence-to-relation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-benchmark-validity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-convergence-independence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-data-contamination/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-explanatory-compression/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-reporting-quality/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-structural-equivalence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-structure-consistency/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-study-validity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/audit-validator-independence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/biologize-problem/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/biomimetic-transfer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/build-concept-fan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/build-current-reality-tree/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/build-domain-ontology/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/build-failure-chain/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/build-noncircularity-matrix/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/calibrate-adversarial-confidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/calibrate-probability-forecast/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/canonicalize-entity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/categorize-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/challenge-assumption/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/characterize-anomaly/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/check-dominance/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-assumption-vulnerability/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-constraint/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-falsification-verdict/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-research-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-simplicity-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/classify-stakeholder-salience/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/collect-independent-judgments/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/compare-evaluation-protocols/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/compare-hypotheses/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/compare-pair/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/conceptual-blending/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-argument-map/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-causal-model/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-counterfactual/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-critique/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-defense/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-design-matrix/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-evidence-network/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-hierarchy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-input-spaces/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-perspective-set/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-scenario/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/construct-validity-envelope/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/counterfactual-causal-analysis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/coverage-white-space-search/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/cross-examine/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/crystallize-north-star/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/dare/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-and-or-goal/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-components/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-evaluation-metric/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-global-sensitivity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-ishikawa/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-research-goal/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/decompose-research-question/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/define-analysis-dimensions/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/define-criteria/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/define-evidence-protocol/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/define-objective/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/derive-consequences/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-data-extraction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-discriminating-prediction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-experiment/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-falsification-test/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-mitigation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-randomness-protocol/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/design-study-inclusion/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/destructive-ideation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-breakpoint/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-contradiction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-coverage-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-feedback-loop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-pass-by-construction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/detect-performance-discrepancy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/discover-biological-analog/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/document-counterclaim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/downgrade-equivalence-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/drill-five-whys/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/drill-root-causes/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/elicit-weights/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/enumerate-combinations/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/enumerate-dimension-values/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/enumerate-failure-modes/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/enumerate-validator-assumptions/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/establish-empirical-baseline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/estimate-effective-evidence-count/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/estimate-performance-headroom/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/estimate-sample-size/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-compatibility/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-falsifiability/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-necessity-sufficiency/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-optionality/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-scenario-impact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evaluate-scenario-robustness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/evolve-solution-population/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/execute-probe/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/execute-research-spec/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/explore-dimensional-space/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-biological-strategy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-causal-structure/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-concepts/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-constructive-movement/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-core-conflict/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-empirical-regularity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-evaluation-protocol/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-evidence-record/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-generic-space/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/extract-structural-mapping/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/falsifiability-audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/falsification-first-audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/filter-false-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/fmea-risk-analysis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/formulate-hypotheses/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/formulate-meta-analysis-scope/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/formulate-research-question/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/formulate-top-goal/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-alternative-model/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-attack-vector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-candidate-directions/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-competing-hypotheses/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-counterexample/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-provocation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/generate-subquestions/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-bottleneck/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-critical-chain/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-dominant-frame/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-inventive-contradiction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-load-bearing-factors/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-obstacles/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-scenario-drivers/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-shared-priors/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-theory/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/identify-variables/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/instantiate-transfer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/inventory-reference-items/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/list-undesirable-effects/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-ablation-components/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-analogy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-coverage-space/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-dependencies/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-disagreement/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-patent-white-space/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-productive-polarity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-research-landscape/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-stakeholder-jobs/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-stakeholder-system/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-threat-surface/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/map-validity-envelope/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/measure-portfolio-diversity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/mine-patent-landscape/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/mutate-solution-population/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/navigate-patent-classification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/negate-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/normalize-comparison-scale/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/normalize-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/operationalize-construct/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/optimize-design-under-budget/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/optimize-pareto-frontier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/pairwise-ranking/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/parse-patent-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/plan-effect-size/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/portfolio-optimization/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/predict-competitive-move/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/probe-benchmark-artifact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/problem-reframing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/project-future-reality/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/propagate-uncertainty/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/quantify-information-value/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/quantify-resource-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/rank-candidates/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/reductio-counterexample-analysis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/refine-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/represent-mechanism-edge/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/research-catalog/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/resolve-inventive-contradiction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/robustness-analysis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/rotate-perspective/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/run-convergence-round/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/scope-domain/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/score-fmea-risk/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/score-object/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/screen-evidence-multistage/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/search-minimal-flip/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-critical-case/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-experimental-baseline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-from-frontier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-inventive-principle/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-next-pair/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-seed-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-solution-variants/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/select-statistical-method/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/sensitivity-analysis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/sequence-work/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/set-threshold/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/sharpen-falsifiable-claim/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/simulate-emergent-properties/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/specify-boundaries/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/specify-execution-environment/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/specify-metrics/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/specify-relationship/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/specify-reproducibility-protocol/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/statistical-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/structural-transformation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/structured-consensus/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/structured-red-team/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/surface-assumptions/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/synthesize-field-panorama/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/synthesize-idea/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/synthesize-literature-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/synthesize-meta-analytic-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/test-risky-prediction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/test-structure-preservation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/trace-assumption-cascade/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/trace-causal-chain/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/trace-citation-neighborhood/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/trace-patent-family/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/transform-component/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/type-relation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/update-confidence-from-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/update-cumulative-evidence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/update-pairwise-rating/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/validate-axis-independence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/validate-causal-link/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/validate-goal-tree/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/validate-mitigation-effect/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/validate-research-gap/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/verify-evidence-independence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/verify-reproducibility/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
skills/write-research-spec/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 41f752b8444e
No earlier version was observed for comparison.
Heat
5.9- 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
- abstract-structure
skills/abstract-structure - adjudicate-exchange
skills/adjudicate-exchange - adjust-abstraction-scope
skills/adjust-abstraction-scope - adversarial-deliberation
skills/adversarial-deliberation - aggregate-ranking
skills/aggregate-ranking - analogical-discovery
skills/analogical-discovery - analyze-constraints-readiness
skills/analyze-constraints-readiness - analyze-experiment-results
skills/analyze-experiment-results - analyze-future-scenarios
skills/analyze-future-scenarios - analyze-heterogeneity
skills/analyze-heterogeneity - analyze-intervention
skills/analyze-intervention - analyze-leaderboard-dynamics
skills/analyze-leaderboard-dynamics - analyze-patent-citation-network
skills/analyze-patent-citation-network - analyze-scaling-regime
skills/analyze-scaling-regime - analyze-temporal-trajectory
skills/analyze-temporal-trajectory - apply-perturbation
skills/apply-perturbation - apply-question-framework
skills/apply-question-framework - apply-separation-principle
skills/apply-separation-principle - apply-stage-gate
skills/apply-stage-gate - apply-veto-filter
skills/apply-veto-filter - appreciative-reframe
skills/appreciative-reframe - assess-construct-validity
skills/assess-construct-validity - assess-evidence-saturation
skills/assess-evidence-saturation - assess-goal-feasibility
skills/assess-goal-feasibility - assess-patent-claim-scope
skills/assess-patent-claim-scope - assess-patent-legal-status
skills/assess-patent-legal-status - assess-prior-art-and-claims
skills/assess-prior-art-and-claims - assess-problem-wickedness
skills/assess-problem-wickedness - assess-publication-bias
skills/assess-publication-bias - assess-question-quality
skills/assess-question-quality - assess-ranking-consistency
skills/assess-ranking-consistency - assess-readiness-dimension
skills/assess-readiness-dimension - assess-removability
skills/assess-removability - assess-sensitivity
skills/assess-sensitivity - assess-system-boundary
skills/assess-system-boundary - assumption-stress-test
skills/assumption-stress-test - atomize-claim
skills/atomize-claim - atomize-concept
skills/atomize-concept - attach-evidence-to-relation
skills/attach-evidence-to-relation - audit-benchmark-validity
skills/audit-benchmark-validity - audit-convergence-independence
skills/audit-convergence-independence - audit-data-contamination
skills/audit-data-contamination - audit-explanatory-compression
skills/audit-explanatory-compression - audit-reporting-quality
skills/audit-reporting-quality - audit-structural-equivalence
skills/audit-structural-equivalence - audit-structure-consistency
skills/audit-structure-consistency - audit-study-validity
skills/audit-study-validity - audit-validator-independence
skills/audit-validator-independence - biologize-problem
skills/biologize-problem - biomimetic-transfer
skills/biomimetic-transfer - build-concept-fan
skills/build-concept-fan - build-current-reality-tree
skills/build-current-reality-tree - build-domain-ontology
skills/build-domain-ontology - build-failure-chain
skills/build-failure-chain - build-noncircularity-matrix
skills/build-noncircularity-matrix - calibrate-adversarial-confidence
skills/calibrate-adversarial-confidence - calibrate-probability-forecast
skills/calibrate-probability-forecast - canonicalize-entity
skills/canonicalize-entity - categorize-evidence
skills/categorize-evidence - challenge-assumption
skills/challenge-assumption - characterize-anomaly
skills/characterize-anomaly - check-dominance
skills/check-dominance - classify-assumption-vulnerability
skills/classify-assumption-vulnerability - classify-constraint
skills/classify-constraint - classify-falsification-verdict
skills/classify-falsification-verdict - classify-research-gap
skills/classify-research-gap - classify-simplicity-evidence
skills/classify-simplicity-evidence - classify-stakeholder-salience
skills/classify-stakeholder-salience - collect-independent-judgments
skills/collect-independent-judgments - compare-evaluation-protocols
skills/compare-evaluation-protocols - compare-hypotheses
skills/compare-hypotheses - compare-pair
skills/compare-pair - conceptual-blending
skills/conceptual-blending - construct-argument-map
skills/construct-argument-map - construct-causal-model
skills/construct-causal-model - construct-counterfactual
skills/construct-counterfactual - construct-critique
skills/construct-critique - construct-defense
skills/construct-defense - construct-design-matrix
skills/construct-design-matrix - construct-evidence-network
skills/construct-evidence-network - construct-hierarchy
skills/construct-hierarchy - construct-input-spaces
skills/construct-input-spaces - construct-perspective-set
skills/construct-perspective-set - construct-scenario
skills/construct-scenario - construct-validity-envelope
skills/construct-validity-envelope - counterfactual-causal-analysis
skills/counterfactual-causal-analysis - coverage-white-space-search
skills/coverage-white-space-search - cross-examine
skills/cross-examine - crystallize-north-star
skills/crystallize-north-star - dare
skills/dare - decompose-and-or-goal
skills/decompose-and-or-goal - decompose-components
skills/decompose-components - decompose-evaluation-metric
skills/decompose-evaluation-metric - decompose-global-sensitivity
skills/decompose-global-sensitivity - decompose-ishikawa
skills/decompose-ishikawa - decompose-research-goal
skills/decompose-research-goal - decompose-research-question
skills/decompose-research-question - define-analysis-dimensions
skills/define-analysis-dimensions - define-criteria
skills/define-criteria - define-evidence-protocol
skills/define-evidence-protocol - define-objective
skills/define-objective - derive-consequences
skills/derive-consequences - design-data-extraction
skills/design-data-extraction - design-discriminating-prediction
skills/design-discriminating-prediction - design-experiment
skills/design-experiment - design-falsification-test
skills/design-falsification-test - design-mitigation
skills/design-mitigation - design-randomness-protocol
skills/design-randomness-protocol - design-study-inclusion
skills/design-study-inclusion - destructive-ideation
skills/destructive-ideation - detect-breakpoint
skills/detect-breakpoint - detect-contradiction
skills/detect-contradiction - detect-coverage-gap
skills/detect-coverage-gap - detect-feedback-loop
skills/detect-feedback-loop - detect-pass-by-construction
skills/detect-pass-by-construction - detect-performance-discrepancy
skills/detect-performance-discrepancy - discover-biological-analog
skills/discover-biological-analog - document-counterclaim
skills/document-counterclaim - downgrade-equivalence-claim
skills/downgrade-equivalence-claim - drill-five-whys
skills/drill-five-whys - drill-root-causes
skills/drill-root-causes - elicit-weights
skills/elicit-weights - enumerate-combinations
skills/enumerate-combinations - enumerate-dimension-values
skills/enumerate-dimension-values - enumerate-failure-modes
skills/enumerate-failure-modes - enumerate-validator-assumptions
skills/enumerate-validator-assumptions - establish-empirical-baseline
skills/establish-empirical-baseline - estimate-effective-evidence-count
skills/estimate-effective-evidence-count - estimate-performance-headroom
skills/estimate-performance-headroom - estimate-sample-size
skills/estimate-sample-size - evaluate-compatibility
skills/evaluate-compatibility - evaluate-falsifiability
skills/evaluate-falsifiability - evaluate-necessity-sufficiency
skills/evaluate-necessity-sufficiency - evaluate-optionality
skills/evaluate-optionality - evaluate-scenario-impact
skills/evaluate-scenario-impact - evaluate-scenario-robustness
skills/evaluate-scenario-robustness - evolve-solution-population
skills/evolve-solution-population - execute-probe
skills/execute-probe - execute-research-spec
skills/execute-research-spec - explore-dimensional-space
skills/explore-dimensional-space - extract-biological-strategy
skills/extract-biological-strategy - extract-causal-structure
skills/extract-causal-structure - extract-concepts
skills/extract-concepts - extract-constructive-movement
skills/extract-constructive-movement - extract-core-conflict
skills/extract-core-conflict - extract-empirical-regularity
skills/extract-empirical-regularity - extract-evaluation-protocol
skills/extract-evaluation-protocol - extract-evidence-record
skills/extract-evidence-record - extract-generic-space
skills/extract-generic-space - extract-structural-mapping
skills/extract-structural-mapping - falsifiability-audit
skills/falsifiability-audit - falsification-first-audit
skills/falsification-first-audit - filter-false-gap
skills/filter-false-gap - fmea-risk-analysis
skills/fmea-risk-analysis - formulate-hypotheses
skills/formulate-hypotheses - formulate-meta-analysis-scope
skills/formulate-meta-analysis-scope - formulate-research-question
skills/formulate-research-question - formulate-top-goal
skills/formulate-top-goal - generate-alternative-model
skills/generate-alternative-model - generate-attack-vector
skills/generate-attack-vector - generate-candidate-directions
skills/generate-candidate-directions - generate-competing-hypotheses
skills/generate-competing-hypotheses - generate-counterexample
skills/generate-counterexample - generate-provocation
skills/generate-provocation - generate-subquestions
skills/generate-subquestions - identify-bottleneck
skills/identify-bottleneck - identify-critical-chain
skills/identify-critical-chain - identify-dominant-frame
skills/identify-dominant-frame - identify-inventive-contradiction
skills/identify-inventive-contradiction - identify-load-bearing-factors
skills/identify-load-bearing-factors - identify-obstacles
skills/identify-obstacles - identify-scenario-drivers
skills/identify-scenario-drivers - identify-shared-priors
skills/identify-shared-priors - identify-theory
skills/identify-theory - identify-variables
skills/identify-variables - instantiate-transfer
skills/instantiate-transfer - inventory-reference-items
skills/inventory-reference-items - list-undesirable-effects
skills/list-undesirable-effects - map-ablation-components
skills/map-ablation-components - map-analogy
skills/map-analogy - map-coverage-space
skills/map-coverage-space - map-dependencies
skills/map-dependencies - map-disagreement
skills/map-disagreement - map-patent-white-space
skills/map-patent-white-space - map-productive-polarity
skills/map-productive-polarity - map-research-landscape
skills/map-research-landscape - map-stakeholder-jobs
skills/map-stakeholder-jobs - map-stakeholder-system
skills/map-stakeholder-system - map-threat-surface
skills/map-threat-surface - map-validity-envelope
skills/map-validity-envelope - measure-portfolio-diversity
skills/measure-portfolio-diversity - mine-patent-landscape
skills/mine-patent-landscape - mutate-solution-population
skills/mutate-solution-population - navigate-patent-classification
skills/navigate-patent-classification - negate-claim
skills/negate-claim - normalize-comparison-scale
skills/normalize-comparison-scale - normalize-gap
skills/normalize-gap - operationalize-construct
skills/operationalize-construct - optimize-design-under-budget
skills/optimize-design-under-budget - optimize-pareto-frontier
skills/optimize-pareto-frontier - pairwise-ranking
skills/pairwise-ranking - parse-patent-claim
skills/parse-patent-claim - plan-effect-size
skills/plan-effect-size - portfolio-optimization
skills/portfolio-optimization - predict-competitive-move
skills/predict-competitive-move - probe-benchmark-artifact
skills/probe-benchmark-artifact - problem-reframing
skills/problem-reframing - project-future-reality
skills/project-future-reality - propagate-uncertainty
skills/propagate-uncertainty - quantify-information-value
skills/quantify-information-value - quantify-resource-gap
skills/quantify-resource-gap - rank-candidates
skills/rank-candidates - reductio-counterexample-analysis
skills/reductio-counterexample-analysis - refine-claim
skills/refine-claim - represent-mechanism-edge
skills/represent-mechanism-edge - research-catalog
skills/research-catalog - resolve-inventive-contradiction
skills/resolve-inventive-contradiction - robustness-analysis
skills/robustness-analysis - rotate-perspective
skills/rotate-perspective - run-convergence-round
skills/run-convergence-round - scope-domain
skills/scope-domain - score-fmea-risk
skills/score-fmea-risk - score-object
skills/score-object - screen-evidence-multistage
skills/screen-evidence-multistage - search-minimal-flip
skills/search-minimal-flip - select-critical-case
skills/select-critical-case - select-experimental-baseline
skills/select-experimental-baseline - select-from-frontier
skills/select-from-frontier - select-inventive-principle
skills/select-inventive-principle - select-next-pair
skills/select-next-pair - select-seed-evidence
skills/select-seed-evidence - select-solution-variants
skills/select-solution-variants - select-statistical-method
skills/select-statistical-method - sensitivity-analysis
skills/sensitivity-analysis - sequence-work
skills/sequence-work - set-threshold
skills/set-threshold - sharpen-falsifiable-claim
skills/sharpen-falsifiable-claim - simulate-emergent-properties
skills/simulate-emergent-properties - specify-boundaries
skills/specify-boundaries - specify-execution-environment
skills/specify-execution-environment - specify-metrics
skills/specify-metrics - specify-relationship
skills/specify-relationship - specify-reproducibility-protocol
skills/specify-reproducibility-protocol - statistical-testing
skills/statistical-testing - structural-transformation
skills/structural-transformation - structured-consensus
skills/structured-consensus - structured-red-team
skills/structured-red-team - surface-assumptions
skills/surface-assumptions - synthesize-field-panorama
skills/synthesize-field-panorama - synthesize-idea
skills/synthesize-idea - synthesize-literature-evidence
skills/synthesize-literature-evidence - synthesize-meta-analytic-evidence
skills/synthesize-meta-analytic-evidence - test-risky-prediction
skills/test-risky-prediction - test-structure-preservation
skills/test-structure-preservation - trace-assumption-cascade
skills/trace-assumption-cascade - trace-causal-chain
skills/trace-causal-chain - trace-citation-neighborhood
skills/trace-citation-neighborhood - trace-patent-family
skills/trace-patent-family - transform-component
skills/transform-component - type-relation
skills/type-relation - update-confidence-from-evidence
skills/update-confidence-from-evidence - update-cumulative-evidence
skills/update-cumulative-evidence - update-pairwise-rating
skills/update-pairwise-rating - validate-axis-independence
skills/validate-axis-independence - validate-causal-link
skills/validate-causal-link - validate-goal-tree
skills/validate-goal-tree - validate-mitigation-effect
skills/validate-mitigation-effect - validate-research-gap
skills/validate-research-gap - verify-evidence-independence
skills/verify-evidence-independence - verify-reproducibility
skills/verify-reproducibility - write-research-spec
skills/write-research-spec
How it works
abstract-structure
When your agent uses it
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
270 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,349 bytesSKILL.mdcore1,349 bytesSKILL.mdcore1,349 bytes
Read SKILL.md
# abstract-structure
## Purpose
Strip domain surface detail and retain transferable relations or mechanisms at a declared abstraction level.
## Input contract
```yaml
required: [source_case, abstraction_level]
optional: [relation_schema, invariants]
constraints: [preserve causal or functional roles while removing incidental labels]
```
## Procedure
1. List entities, actions, constraints, and outcomes in the source case.
2. Replace domain labels with role and relation types at the requested level.
3. Record invariants and details intentionally discarded.
## Output contractadjudicate-exchange
When your agent uses it
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
296 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,474 bytes
Read SKILL.md
# adjudicate-exchange
## Purpose
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
## Input contract
```yaml
required: [arguments, critique_set, adjudication_criteria]
optional: [evidence_records, burden_of_proof, verdict_vocabulary]
constraints: [each argument and critique receives an explicit disposition]
```
## Procedure
1. Normalize claims, warrants, evidence, and objections.
2. Map each objection to the argument component it tests.
3. Weigh support and weaknesses against the supplied criteria.
4. Emit ACCEPT, REJECT, or REVISE with conditions and uncertainty.adjust-abstraction-scope
When your agent uses it
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful explanatory and experimental leverage.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
471 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,333 bytesSKILL.mdcore2,333 bytes
Read SKILL.md
# adjust-abstraction-scope
## Purpose
Move a scientific object up or down in abstraction, or narrow/broaden scope dimensions, until explanatory and experimental leverage improve.
## Input contract
```yaml
required: [research_object, current_scope, leverage_failure]
optional: [candidate_levels, context_constraints, target_use]
constraints: [retain object identity; change representation or declared scope explicitly]
```
## Procedure
1. Record object, current level, and scope dimensions (population, mechanism, context, outcome, timeframe, boundary).adversarial-deliberation
When your agent uses it
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth, loser-resurrection, and steelman/winner-stress modes are parameters; role execution is runtime-agnostic.
What it loads into context
Frontmatter
63 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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore5,250 bytesSKILL.mdcore5,250 bytesSKILL.mdcore5,250 bytesSKILL.mdcore5,250 bytesSKILL.mdcore5,250 bytesSKILL.mdcore5,250 bytes
Read SKILL.md
# adversarial-deliberation
## Purpose
Run structured attack, defense, cross-examination, and adjudication over a claim, candidate, criterion set, or current winner.
## Input contract
```yaml
mode_contracts:
critic-defender-judge: &deliberation_input
required: [target, claim_or_candidate, criteria]
optional: [perspectives, escalation_depth]
constraints: [target_scope_and_criteria_must_be_explicit, evidence_provenance_required]
courtroom: *deliberation_input
winner-stress: *deliberation_input
resurrection-advocacy: *deliberation_input
criteria-interrogation: *deliberation_inputaggregate-ranking
When your agent uses it
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
433 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,241 bytesSKILL.mdcore2,241 bytes
Read SKILL.md
# aggregate-ranking
## Purpose
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
## Input contract
```yaml
required: [candidate_set, criterion_results, aggregation_rule]
optional: [tie_break_rule, missing_value_policy, uncertainty_annotations]
constraints: [criterion directions and scales must be declared; no silent imputation]
```
## Procedure
1. Align candidate identifiers, criterion directions, units, and validity flags.analogical-discovery
When your agent uses it
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
496 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytesSKILL.mdcore2,530 bytes
Read SKILL.md
# analogical-discovery
## Purpose
Transfer a validated relational structure from a source domain into a target research problem.
## Input contract
```yaml
required: [target_problem, source_domain]
optional: [candidate_sources, transfer_constraints]
constraints: [source and target roles must be explicit]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `abstract-structure` to abstract the relational structure.
2. You MUST load skill `map-analogy` to map source relations to the target.analyze-constraints-readiness
When your agent uses it
Characterize what blocks a research target: readiness dimensions, obstacles, bottlenecks, resource gaps, causal constraints, dependencies, conflicts, removability, and mitigation pathways. Depth selects lightweight triage, readiness assessment, or causal/TOC-style constraint analysis.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
3,282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore14,595 bytesSKILL.mdcore14,595 bytesSKILL.mdcore14,595 bytesSKILL.mdcore14,595 bytesSKILL.mdcore14,595 bytesSKILL.mdcore14,595 bytes
Read SKILL.md
# analyze-constraints-readiness
## Purpose
Assess feasibility and readiness by identifying constraints, resources, dependencies, bottlenecks, and maturation gates.
## Input contract
```yaml
mode_contracts:
obstacle-triage: &readiness_input
required: [candidate_or_plan, readiness_dimensions]
optional: [resource_estimates, dependencies, assumptions, target_gates]
constraints: [evidence_must_be_attached_to_each_scored_dimension]analyze-experiment-results
When your agent uses it
Interpret completed experimental outputs after host/runtime execution using pre-declared statistical tests, effect/uncertainty estimates, reproducibility checks, and calibrated synthesis.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,925 bytesSKILL.mdcore2,925 bytes
Read SKILL.md
# analyze-experiment-results
## Purpose
Interpret completed experimental outputs after host/runtime execution using pre-declared statistical tests, effect/uncertainty estimates, reproducibility checks, and calibrated synthesis.
## Input contract
```yaml
required: [experiment_results, predeclared_analysis_plan, reproducibility_target]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
analyze-future-scenarios
When your agent uses it
Construct and compare plausible future/competitive/temporal/stress scenarios and test whether the research path remains robust across them.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
697 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,410 bytesSKILL.mdcore3,410 bytes
Read SKILL.md
# analyze-future-scenarios
## Purpose
Construct and compare plausible future/competitive/temporal/stress scenarios and test whether the research path remains robust across them.
## Input contract
```yaml
required: [research_path, scenario_axes, uncertainty_drivers]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
analyze-heterogeneity
When your agent uses it
Identify clinical, methodological, and statistical heterogeneity sources and prioritize subgroup/meta-regression/outlier investigation.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
337 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,781 bytesSKILL.mdcore1,781 bytes
Read SKILL.md
# analyze-heterogeneity
## Purpose
Identify clinical, methodological, and statistical heterogeneity sources and prioritize subgroup, meta-regression, or outlier investigation.
## Input contract
```yaml
required: [evidence_records, outcome_schema, comparison_context]
optional: [covariate_schema, effect_estimates, subgroup_hypotheses]
constraints: [heterogeneity claims require record-level conditions and provenance]
```
analyze-intervention
When your agent uses it
Apply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
286 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,578 bytes
Read SKILL.md
# analyze-intervention
## Purpose
Analyze an intervention's target, mechanism, implementation conditions, and observed effects.
## Input contract
```yaml
required: [intervention, target_system, outcome_records]
optional: [implementation_records, comparator, mechanism_hypotheses]
constraints: [effect interpretation must retain implementation and comparison conditions]
```
analyze-leaderboard-dynamics
When your agent uses it
Analyze leaderboard score distributions, compression/saturation, anomalies, selective reporting, and regime shifts.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
284 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,508 bytes
Read SKILL.md
# analyze-leaderboard-dynamics
## Purpose
Analyze leaderboard score distributions, compression or saturation, anomalies, selective reporting, and regime shifts.
## Input contract
```yaml
required: [leaderboard_records, metric_schema, time_or_version_field]
optional: [evaluation_protocols, source_quality, method_metadata]
constraints: [scores require task, metric, condition, source, and observation provenance]
```
analyze-patent-citation-network
When your agent uses it
Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,513 bytesSKILL.mdcore1,513 bytes
Read SKILL.md
# analyze-patent-citation-network
## Purpose
Analyze patent citation and family relationships to identify central prior art, lineages, clusters, bridge patents, and citation anomalies.
## Input contract
```yaml
required: [patent_records, citation_edges, family_keys]
optional: [classification_schema, assignee_keys, time_window]
constraints: [edge direction, source, jurisdiction, and date must be retained]
```
analyze-scaling-regime
When your agent uses it
Analyze how conclusions/performance change across scale and identify regime shifts, saturation, power-law/log-law behavior, or frontier transitions.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,005 bytesSKILL.mdcore2,005 bytes
Read SKILL.md
# analyze-scaling-regime
## Purpose
Analyze how conclusions or performance change across scale and identify regime shifts, saturation, scaling-law behavior, or frontier transitions.
## Input contract
```yaml
required: [scale_variable, outcome_series, observation_context]
optional: [candidate_scaling_laws, uncertainty_model, suspected_breakpoints]
constraints: [scale units and outcome direction must be explicit; observations remain ordered]
```
## Procedure
1. Normalize scale and outcome definitions while retaining original units.analyze-temporal-trajectory
When your agent uses it
Analyze an ordered temporal trajectory, including persistence/narrowing/widening tests, regime changes, inflection points, and optional extrapolation with uncertainty. Entity type, window, and forecast mode are parameters.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
809 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore3,899 bytesSKILL.mdcore3,899 bytesSKILL.mdcore3,899 bytesSKILL.mdcore3,899 bytesSKILL.mdcore3,899 bytes
Read SKILL.md
# analyze-temporal-trajectory
## Purpose
Analyze an ordered temporal trajectory for persistence, narrowing or widening, regime changes, inflection points, and optional uncertain extrapolation.
## Input contract
```yaml
required: [time_indexed_records, entity_type, metric, window]
optional: [forecast_mode, uncertainty_model, grouping_keys, event_markers]
constraints: [records are ordered by time; metric direction is explicit; extrapolation is optional and must carry uncertainty]
```
apply-perturbation
When your agent uses it
Apply a controlled change to an assumption, factor, component, parameter, or condition and record response.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
567 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytes
Read SKILL.md
# apply-perturbation
## Purpose
Apply a controlled change to an assumption, factor, component, parameter, or condition and record the response.
## Input contract
```yaml
required: [baseline_artifact, perturbation_target, perturbation_axis, response_metric]
optional: [variation_range, removal_mode, factor_list, uncertainty_model]
constraints: [change one declared target or axis at a time unless the caller explicitly supplies an interaction design; preserve baseline comparability]
```
apply-question-framework
When your agent uses it
Select and instantiate a research-question schema appropriate to study type.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
233 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,185 bytes
Read SKILL.md
# apply-question-framework
## Purpose
Structure an underspecified research question with a declared question framework.
## Input contract
```yaml
required: [question, research_context, framework]
optional: [population, intervention, comparator, outcome, time_horizon]
constraints: [framework fields must be instantiated or marked unknown]
```
apply-separation-principle
When your agent uses it
Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,404 bytes
Read SKILL.md
# apply-separation-principle
## Purpose
Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.
## Input contract
```yaml
required: [contradiction, conflicting_requirements]
optional: [system_boundary, operating_conditions]
constraints: [requirements must be stated as mutually conflicting outcomes]
```
## Procedure
1. State the useful and harmful effects that cannot coexist (`conflicting_requirements`).
2. Test separation in time, space, scale, condition, and system level.
3. Select the separation that removes the conflict and state its operating condition.
## Output contractapply-stage-gate
When your agent uses it
Apply explicit GO / HOLD / RECYCLE / KILL (or supplied) stage-gate criteria with evidence thresholds and next-step conditions.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
421 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,003 bytesSKILL.mdcore2,003 bytes
Read SKILL.md
# apply-stage-gate
## Purpose
Apply explicit GO / HOLD / RECYCLE / KILL gates to a candidate or work package, tying each outcome to evidence thresholds and a next action.
## Input contract
```yaml
required: [candidate_record, gate_criteria, evidence_register]
optional: [prior_gate_decision, remediation_options]
constraints: [each criterion has an observable status; gate outcome and next action are explicit]
```
## Procedure
1. Normalize the candidate, gate criteria, evidence, and unresolved assumptions into a gate table.
2. Evaluate every criterion as met, unmet, or unknown, preserving the cited evidence and threshold direction.
3. Apply precedence: KILL for disqualifying hard failure, RECYCLE for repairable failure, HOLD for insufficient evidence, otherwise GO.
4. Emit the gate decision, failed criteria, evidence gaps, and the smallest justified next action.apply-veto-filter
When your agent uses it
Eliminate alternatives that violate any hard threshold and report the exact violation.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,474 bytes
Read SKILL.md
# apply-veto-filter
## Purpose
Eliminate alternatives that violate any declared hard threshold and expose the exact veto condition for each removal.
## Input contract
```yaml
required: [alternatives, hard_constraints, measured_values]
optional: [constraint_priorities, missing_value_policy]
constraints: [each alternative is tested against every hard constraint; missing measurements cannot silently pass]
```
## Procedure
1. Bind each hard constraint to its direction, threshold, unit, and evidence source.
2. Check every alternative against every constraint and record pass, fail, or unknown per cell.
3. Veto an alternative when any hard constraint fails; keep unknowns separate from passes.
4. Return survivors, vetoed alternatives, violated constraints, and unresolved checks.appreciative-reframe
When your agent uses it
Reframe a problem around functioning exceptions, existing strengths, positive deviance, and conditions under which desired behavior already occurs.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
244 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,257 bytes
Read SKILL.md
# appreciative-reframe
## Purpose
Reframe a problem around functioning exceptions, strengths, positive deviance, and conditions supporting desired behavior.
## Input contract
```yaml
required: [problem_statement, functioning_exceptions]
optional: [stakeholders, outcome_definition]
constraints: [exceptions must be observed cases, not aspirations]
```
## Procedure
1. Identify cases where the desired behavior already occurs.
2. Extract the enabling conditions and strengths present in those cases.
3. Rewrite the research question around reproducing or extending those conditions.
## Output contractassess-construct-validity
When your agent uses it
Assess whether a benchmark measures its claimed capability using content, convergent, discriminant, and confound analysis.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
381 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,979 bytes
Read SKILL.md
# assess-construct-validity
## Purpose
Assess whether a benchmark or evaluation construct measures the claimed capability rather than content cues, confounds, or unrelated skill.
## Input contract
```yaml
required: [construct_claim, benchmark_specification, evaluation_records]
optional: [content_analysis, convergent_measures, discriminant_measures, confound_hypotheses]
constraints: [each validity judgment requires an observable indicator, comparison basis, and provenance]
```
assess-evidence-saturation
When your agent uses it
Estimate marginal information gain of new evidence batches relative to the current corpus and classify continuing/near-saturation/saturated.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
365 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,899 bytesSKILL.mdcore1,899 bytes
Read SKILL.md
# assess-evidence-saturation
## Purpose
Compare the marginal information gain of a new evidence batch with the comparable prior batch and classify acquisition as continuing, near-saturation, or saturated.
## Input contract
```yaml
required: [current_corpus, prior_comparable_batch, novelty_schema]
optional: [topic_schema, quality_weights, stopping_policy]
constraints: [batches must share a declared universe and comparable novelty calculation]
```
assess-goal-feasibility
When your agent uses it
Cross-check goal branches against resources, obstacles, and timeline; label feasible/stretch/infeasible and propose OR alternatives.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
367 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,849 bytes
Read SKILL.md
# assess-goal-feasibility
## Purpose
Cross-check goal branches against resources, obstacles, and timeline; label each feasible, stretch, or infeasible and propose OR alternatives.
## Input contract
```yaml
required: [goal_branches, resource_profile, obstacle_register, timeline]
optional: [capability_evidence, dependency_graph, alternative_constraints]
constraints: [each branch must have explicit resource, obstacle, and deadline checks]
```
## Procedure
1. Decompose each branch into deliverables, dependencies, and required capabilities.assess-patent-claim-scope
When your agent uses it
Assess protection breadth, limiting elements, support, overlap, design-around vulnerability, and likely scope uncertainty for a patent claim without making legal conclusions beyond the evidence.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
328 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,677 bytes
Read SKILL.md
# assess-patent-claim-scope
## Purpose
Assess claim breadth, limiting elements, support, overlap, design-around vulnerability, and scope uncertainty without making a legal conclusion beyond the evidence.
## Input contract
```yaml
required: [parsed_claim, cited_support, jurisdiction_scope]
optional: [related_claims, family_map, prior_art_records]
constraints: [each scope judgment must identify claim language, support, jurisdiction, and uncertainty]
```
assess-patent-legal-status
When your agent uses it
Classify observed patent/legal status and flag uncertainty or jurisdiction dependence.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,409 bytesSKILL.mdcore1,409 bytesSKILL.mdcore1,409 bytesSKILL.mdcore1,409 bytes
Read SKILL.md
# assess-patent-legal-status
## Purpose
Classify observed patent status by jurisdiction and observation date while preserving uncertainty and source dependence.
## Input contract
```yaml
required: [patent_record, jurisdiction, observation_date, status_sources]
optional: [family_events, prosecution_events]
constraints: [status is an observation tied to dated sources, not an undated legal inference]
```
assess-prior-art-and-claims
When your agent uses it
Assess novelty/prior art and claim scope by decomposing claims, tracing relevant families, and checking status/provenance.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
633 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytesSKILL.mdcore3,049 bytes
Read SKILL.md
# assess-prior-art-and-claims
## Purpose
Assess novelty, prior art, claim scope, legal-status observations, and provenance without making unsupported legal conclusions.
## Input contract
```yaml
required: [claim_set, target_domain, jurisdiction_scope]
optional: [known_families, search_context, evidence_records]
constraints: [claim text and source provenance required, jurisdiction and observation date must be explicit]
```
assess-problem-wickedness
When your agent uses it
Assess whether the problem is tame, complex, or wicked by examining stakeholder disagreement, moving boundaries, feedback, value conflict, and absence of a stable stopping rule.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
279 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,406 bytes
Read SKILL.md
# assess-problem-wickedness
## Purpose
Assess whether a problem is tame, complex, or wicked using disagreement, moving boundaries, feedback, value conflict, and stopping-rule evidence.
## Input contract
```yaml
required: [problem_statement, stakeholder_views]
optional: [boundary_history, feedback_observations, candidate_stopping_rule]
constraints: [classification must cite observed disagreement or stability indicators]
```
## Procedure
1. Compare stakeholder definitions and desired outcomes.
2. Check boundary movement, feedback loops, and value conflicts.
3. Assess whether a stable stopping rule and agreed solution test exist.
4. Assign tame, complex, or wicked with evidence and uncertainty.assess-publication-bias
When your agent uses it
Assess or plan tests for publication/reporting/time-lag/citation/language bias using appropriate diagnostics.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
329 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,629 bytes
Read SKILL.md
# assess-publication-bias
## Purpose
Assess publication, reporting, time-lag, citation, and language bias using diagnostics appropriate to the evidence design.
## Input contract
```yaml
required: [evidence_records, outcome_schema, inclusion_frame]
optional: [registry_records, search_log, effect_estimates]
constraints: [bias claims require an observable missingness or selection pattern]
```
assess-question-quality
When your agent uses it
Audit a research question for scope and FINER-style quality; return targeted repairs.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
256 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,292 bytes
Read SKILL.md
# assess-question-quality
## Purpose
Assess whether a research question is clear, focused, answerable, relevant, and appropriately scoped.
## Input contract
```yaml
required: [research_question, intended_use]
optional: [constraints, evidence_context, stakeholder_needs]
constraints: [each quality judgment requires a criterion and textual evidence]
```
assess-ranking-consistency
When your agent uses it
Audit pairwise/ranking coherence and identify inconsistent cycles/triads.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,513 bytes
Read SKILL.md
# assess-ranking-consistency
## Purpose
Audit pairwise and aggregate rankings for incoherent cycles, reversals, and unsupported rank transitions.
## Input contract
```yaml
required: [ranked_items, pairwise_judgments, comparison_criteria]
optional: [weights, tie_policy, prior_consistency_report]
constraints: [judgments identify compared items, direction, confidence, and criterion]
```
## Procedure
1. Reconstruct the directed comparison graph and normalize ties and missing edges.
2. Search triads and longer cycles for violations of declared transitivity or criterion direction.
3. Compare aggregate order with its supporting pairwise judgments and flag reversals or low-support placements.
4. Return inconsistency records, affected items, and the minimum judgments requiring review.assess-readiness-dimension
When your agent uses it
Assess one readiness dimension against explicit anchors/evidence.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
348 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,852 bytesSKILL.mdcore1,852 bytes
Read SKILL.md
# assess-readiness-dimension
## Purpose
Assess one readiness dimension against explicit anchors, evidence, and known deficits.
## Input contract
```yaml
required: [subject_record, readiness_dimension, anchor_definition, evidence_register]
optional: [scoring_scale, prior_assessment]
constraints: [anchor levels are ordered and observable; every score cites evidence and a deficit statement]
```
## Procedure
1. Define the dimension, scale, anchor descriptions, and decision relevance.
2. Map each supplied evidence item to the strongest supported anchor and record contrary evidence.
3. Assign the lowest defensible level whose requirements are met; record missing requirements separately.
4. Emit the dimension score, evidence basis, deficits, and reassessment trigger.assess-removability
When your agent uses it
Estimate whether and at what cost a constraint can be removed or relaxed.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
383 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,924 bytesSKILL.mdcore1,924 bytes
Read SKILL.md
# assess-removability
## Purpose
Estimate whether a constraint can be removed or relaxed, at what cost, and with which residual risks.
## Input contract
```yaml
required: [constraint_record, dependency_map, removal_options, cost_model]
optional: [time_horizon, safety_limits, stakeholder_requirements]
constraints: [each option states feasibility, cost units, dependencies, and residual risk]
```
## Procedure
1. Trace the constraint to dependent claims, processes, and safety conditions.
2. Generate removal or relaxation options and estimate direct cost, delay, dependency changes, and residual risk.
3. Test each option against non-negotiable boundaries and identify the cheapest feasible relaxation.
4. Emit removability class, cost/risk profile, and a reversible trial where one exists.assess-sensitivity
When your agent uses it
Perturb a specified input, assumption, model choice, analysis choice, or weight and measure sensitivity of a specified output; report convergence/instability, unstable regions, and dominant drivers.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,183 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore5,198 bytesSKILL.mdcore5,198 bytesSKILL.mdcore5,198 bytesSKILL.mdcore5,198 bytesSKILL.mdcore5,198 bytes
Read SKILL.md
# assess-sensitivity
## Purpose
Perturb a specified input, assumption, model choice, analysis choice, or weight and measure the resulting output sensitivity.
## Input contract
```yaml
required: [baseline_input, perturbation_axes, output, comparison_metric]
optional: [assumptions, perturbation_design, uncertainty_model, baseline_ranking]
constraints: [each perturbation is attributable to one declared axis; the output comparison metric is fixed before evaluation; preserve the caller's scale and direction]
```
assess-system-boundary
When your agent uses it
Define and challenge the system boundary: what actors, processes, externalities, timescales, and value assumptions are included or excluded.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
275 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,337 bytes
Read SKILL.md
# assess-system-boundary
## Purpose
Define and challenge which actors, processes, externalities, timescales, and values are inside or outside a system boundary.
## Input contract
```yaml
required: [target_system, boundary_candidate]
optional: [actors, processes, externalities, time_horizon, value_assumptions]
constraints: [every inclusion and exclusion must be explicit]
```
## Procedure
1. Inventory actors, processes, externalities, and timescales.
2. Mark each item inside, outside, or contested under the candidate boundary.
3. Generate boundary alternatives and compare consequences for the research question.
## Output contractassumption-stress-test
When your agent uses it
Surface load-bearing assumptions, classify vulnerability, challenge or perturb them, and re-check causal logic.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
514 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,474 bytesSKILL.mdcore2,474 bytes
Read SKILL.md
# assumption-stress-test
## Purpose
Expose load-bearing assumptions, classify their vulnerability, perturb them, and re-check causal validity.
## Input contract
```yaml
required: [claim_or_model, assumptions]
optional: [evidence, causal_graph, perturbation_bounds]
constraints: [each assumption must be traceable to a claim or causal link]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `surface-assumptions` to surface load-bearing assumptions.
2. You MUST load skill `classify-assumption-vulnerability` to classify their vulnerability.atomize-claim
When your agent uses it
Decompose a compound position into atomic, independently challengeable/falsifiable claims and expose implicit assumptions.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
248 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,246 bytes
Read SKILL.md
# atomize-claim
## Purpose
Split a compound claim into atomic propositions that can receive separate evidence and confidence judgments.
## Input contract
```yaml
required: [compound_claim]
optional: [argument_context, domain_terms, evidence_records]
constraints: [atomic claims retain logical connectors and scope qualifiers]
```
atomize-concept
When your agent uses it
Decompose compound concepts into atomic, non-overlapping concepts while preserving parent/part relationships.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,299 bytes
Read SKILL.md
# atomize-concept
## Purpose
Split a broad concept into definitional facets and distinguishable subconstructs.
## Input contract
```yaml
required: [concept_definition, domain_context]
optional: [theory, neighboring_concepts, examples]
constraints: [facets must be non-duplicate and retain the parent concept boundary]
```
attach-evidence-to-relation
When your agent uses it
Attach supporting or contradicting evidence to a specific claim/relation with quality, directness, and independence metadata.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
307 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,560 bytesSKILL.mdcore1,560 bytes
Read SKILL.md
# attach-evidence-to-relation
## Purpose
Attach source evidence to a typed relation between concepts, claims, or entities with directness and independence metadata.
## Input contract
```yaml
required: [relation, evidence_records, relation_schema]
optional: [quality_rubric, independence_keys, confidence_prior]
constraints: [evidence must support the relation type and direction claimed]
```
audit-benchmark-validity
When your agent uses it
Treat benchmarks as scientific measurement instruments: audit construct validity, contamination, metric pathology, coverage, leaderboard dynamics, and protocol drift.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
3,511 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytesSKILL.mdcore13,473 bytes
Read SKILL.md
# audit-benchmark-validity
## Purpose
Treat benchmarks as scientific measurement instruments: audit construct validity, contamination, metric pathology, coverage, leaderboard dynamics, and protocol drift.
## Input contract
```yaml
required: [benchmark_spec, task_definition, metric_definition, evaluation_records]
optional: [leaderboard_history, protocol_versions, coverage_target]
constraints: [claims must be linked to benchmark evidence]
```
audit-convergence-independence
When your agent uses it
Audit claims of independent convergence by tracing shared priors, data, framing, models, prompts, assumptions, or upstream evidence; estimate an effective independent evidence count rather than treating nominal N paths as independent.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
687 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytesSKILL.mdcore3,292 bytes
Read SKILL.md
# audit-convergence-independence
## Purpose
Estimate how much nominally independent convergence remains after shared priors, data, models, prompts, framings, assumptions, and upstream evidence are discounted.
## Input contract
```yaml
mode_contracts:
evidence-paths: &convergence_audit_input
required: [evidence_paths, claims, provenance_records]
optional: [dependency_schema, correlation_estimates]
constraints: [each_path_must_be_traceable_to_its_inputs_and_assumptions]
agents: *convergence_audit_input
models: *convergence_audit_input
methods: *convergence_audit_input
```audit-data-contamination
When your agent uses it
Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
291 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,519 bytesSKILL.mdcore1,519 bytes
Read SKILL.md
# audit-data-contamination
## Purpose
Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.
## Input contract
```yaml
required: [dataset_partitions, training_sources, evaluation_records]
optional: [release_history, deduplication_keys, access_logs]
constraints: [each contamination claim requires a matched record, pathway, and comparison basis]
```
audit-explanatory-compression
When your agent uses it
Test whether an elegant/simple explanation earns its compression by forbidding alternatives, subsuming independent facts, or making risky predictions, rather than merely relabeling observations with a compact vocabulary.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
582 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore2,744 bytesSKILL.mdcore2,744 bytesSKILL.mdcore2,744 bytesSKILL.mdcore2,744 bytesSKILL.mdcore2,744 bytes
Read SKILL.md
# audit-explanatory-compression
## Purpose
Test whether an elegant explanation earns compression by excluding alternatives, subsuming independent facts, or making risky predictions.
## Input contract
```yaml
mode_contracts:
earned-simplicity: &compression_audit_input
required: [explanation, covered_facts, alternatives]
optional: [predictions, evidence]
constraints: [facts_and_alternatives_must_be_independently_enumerated]
decorative-simplicity: *compression_audit_input
risky-prediction: *compression_audit_input
```
## Execution protocolaudit-reporting-quality
When your agent uses it
Audit whether a research/evaluation artifact reports the information needed for interpretation and reproduction, using a domain-appropriate checklist.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
318 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,620 bytes
Read SKILL.md
# audit-reporting-quality
## Purpose
Audit whether an artifact reports the information needed for interpretation and reproduction using a declared domain-appropriate checklist.
## Input contract
```yaml
required: [artifact, reporting_checklist]
optional: [domain_schema, reproduction_requirements, source_context]
constraints: [each checklist judgment must cite present, absent, or ambiguous evidence]
```
audit-structural-equivalence
When your agent uses it
Audit a claimed isomorphism/equivalence by constructing an explicit mapping, testing which structures/operations/invariants are preserved, searching counterexamples, and downgrading the claim to the strongest defensible relation when full isomorphism fails.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore3,094 bytesSKILL.mdcore3,094 bytesSKILL.mdcore3,094 bytesSKILL.mdcore3,094 bytesSKILL.mdcore3,094 bytes
Read SKILL.md
# audit-structural-equivalence
## Purpose
Audit a claimed isomorphism or equivalence and downgrade it to the strongest defensible relation when preservation fails.
## Input contract
```yaml
mode_contracts:
isomorphism: &structural_audit_input
required: [source_structure, target_structure, equivalence_claim]
optional: [required_invariants, operations, constraints]
constraints: [mapping_domains_and_preservation_obligations_must_be_explicit]
substructure: *structural_audit_input
homomorphism: *structural_audit_input
shared-invariant: *structural_audit_input
analogy: *structural_audit_inputaudit-structure-consistency
When your agent uses it
Detect cycles, contradictions, orphans, type violations, and structural incoherence in a knowledge model.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
289 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytes
Read SKILL.md
# audit-structure-consistency
## Purpose
Audit whether a concept, argument, or graph preserves its declared structural relations and constraints.
## Input contract
```yaml
required: [structure, relation_schema, consistency_rules]
optional: [source_structure, version_history, exception_rules]
constraints: [each inconsistency identifies nodes, relation, and violated rule]
```
audit-study-validity
When your agent uses it
Audit a study against an appropriate methodological-quality and risk-of-bias rubric; return domain-level judgments, evidence, and overall confidence.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
415 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,049 bytes
Read SKILL.md
# audit-study-validity
## Purpose
Audit a study against an appropriate methodological-quality and risk-of-bias rubric and return domain judgments with evidence and confidence.
## Input contract
```yaml
required: [study_record, validity_rubric]
optional: [protocol, analysis_plan, supplementary_materials]
constraints: [rubric applicability and judgment rationale must be explicit]
```
audit-validator-independence
When your agent uses it
Audit whether a validator, benchmark, sandbox, or test can pass by construction because it embeds the same assumptions as the theory it claims to validate. Build a claim×validator-assumption matrix and demand at least one non-circular failure channel.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
589 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore2,852 bytesSKILL.mdcore2,852 bytesSKILL.mdcore2,852 bytesSKILL.mdcore2,852 bytesSKILL.mdcore2,852 bytes
Read SKILL.md
# audit-validator-independence
## Purpose
Detect validators that pass by construction because they copy the target theory's assumptions.
## Input contract
```yaml
mode_contracts:
validator: &validator_audit_input
required: [target_claim, validator, validator_artifacts]
optional: [data_generation, metric, oracle, acceptance_rule]
constraints: [validator_assumptions_and_target_assumptions_must_be_separately_listed]
benchmark: *validator_audit_input
sandbox: *validator_audit_input
simulation: *validator_audit_input
```biologize-problem
When your agent uses it
Translate a target problem from implementation language into biological function/constraint language suitable for biological analogy search.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,462 bytes
Read SKILL.md
# biologize-problem
## Purpose
Translate an implementation-specific problem into biological function and constraint language for mechanism-directed analogy search.
## Input contract
```yaml
required: [target_problem, target_function]
optional: [materials, environment, performance_constraints]
constraints: [function must be implementation-independent and testable]
```
## Procedure
1. Remove target-domain nouns and restate the desired function.
2. State environmental pressures, resources, and failure constraints.
3. Produce biological search terms at function, process, and adaptation levels.
biomimetic-transfer
When your agent uses it
Reframe a problem in biological functional terms, discover organisms/systems solving analogous functions, extract the causal biological strategy, and transfer the mechanism back into the target domain.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
670 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,130 bytesSKILL.mdcore3,130 bytesSKILL.mdcore3,130 bytes
Read SKILL.md
# biomimetic-transfer
## Purpose
Translate a target problem into biological functions, find analogous living systems, extract causal strategies, and transfer them back.
## Input contract
```yaml
mode_contracts:
biologize-and-discover: &biomimetic_input
required: [target_problem, target_function]
optional: [biological_search_space, compatibility_constraints]
constraints: [function_must_be_stated_independently_of_the_target_implementation]
BioTRIZ: *biomimetic_input
```
## Execution protocol
build-concept-fan
When your agent uses it
Expand a target goal into progressively broader concepts and alternative routes, then descend into new concrete approaches.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
241 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,206 bytes
Read SKILL.md
# build-concept-fan
## Purpose
Expand a goal into broader concepts and alternative routes, then descend into concrete approaches.
## Input contract
```yaml
required: [target_goal]
optional: [known_approaches, abstraction_levels, feasibility_constraints]
constraints: [each branch must state its abstraction level and relation to the goal]
```
## Procedure
1. State the current goal and its immediate concept.
2. Fan upward into broader purposes and downward into alternative implementations.
3. Compare branches and retain distinct routes for further investigation.
## Output contractbuild-current-reality-tree
When your agent uses it
Build a sufficient-cause Current Reality Tree linking undesirable effects to a small root set.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
257 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,242 bytes
Read SKILL.md
# build-current-reality-tree
## Purpose
Build a sufficient-cause Current Reality Tree linking undesirable effects to a small root set.
## Input contract
```yaml
required: [undesirable_effects, causal_evidence]
optional: [candidate_causes, system_boundary]
constraints: [each AND/OR connection requires a stated causal rationale]
```
## Procedure
1. Normalize undesirable effects into observable statements.
2. Connect effects with sufficient-cause relationships, marking AND requirements.
3. Trace converging chains to a small root set and test each link.
## Output contractbuild-domain-ontology
When your agent uses it
Construct a tool-independent domain ontology: scope the domain, atomize concepts, type relations, build hierarchy, audit consistency, detect gaps, and refine confidence.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
780 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,860 bytesSKILL.mdcore3,860 bytesSKILL.mdcore3,860 bytes
Read SKILL.md
# build-domain-ontology
## Purpose
Construct a tool-independent domain ontology: scope the domain, atomize concepts, type relations, build hierarchy, audit consistency, detect gaps, and refine confidence.
## Input contract
```yaml
required: [domain_scope, concept_records, relation_evidence]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
build-failure-chain
When your agent uses it
Build multi-level cause -> failure mode -> effect chains and identify cascades/shared roots.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,136 bytes
Read SKILL.md
# build-failure-chain
## Purpose
Build cause -> failure mode -> effect chains and identify cascades and shared roots.
## Input contract
```yaml
required: [functions_or_process, failure_modes, observed_effects]
optional: [causal_evidence, dependency_graph]
constraints: [each edge needs a mechanism or evidence note]
```
## Procedure
1. Place causes, failure modes, and effects in typed levels.
2. Connect edges and record mechanism/evidence.
3. Mark cascades, shared roots, and unresolved links.
## Output contractbuild-noncircularity-matrix
When your agent uses it
Cross-tabulate target theory claims/assumptions against validator assumptions and mark independent, shared, derived-from-target, or unknown dependencies.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,336 bytes
Read SKILL.md
# build-noncircularity-matrix
## Purpose
Cross-tabulate target claims/assumptions against validator assumptions and expose circularity.
## Input contract
```yaml
required: [target_claims, target_assumptions, validator_assumptions]
optional: [evidence_channels]
constraints: [each cell is independent/shared/derived-from-target/unknown]
```
## Procedure
1. Enumerate both assumption sets.
2. Populate dependency cells with evidence.
3. Identify copied assumptions and independent failure channels.
calibrate-adversarial-confidence
When your agent uses it
Track confidence in competing claims/roles across adversarial rounds and update confidence only when evidence or argument quality warrants it.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,593 bytesSKILL.mdcore1,593 bytes
Read SKILL.md
# calibrate-adversarial-confidence
## Purpose
Track confidence in competing claims or roles across adversarial rounds and update only when evidence or argument quality warrants it.
## Input contract
```yaml
required: [round_records, competing_claims, update_rule]
optional: [prior_confidence, calibration_history]
constraints: [every update cites evidence or argument-quality change]
```
## Procedure
1. Record each round's claims, arguments, and evidence.
2. Apply the declared update rule and preserve dissent.
3. Mark escalation, continuation, termination, or saturation with rationale.
## Output contractcalibrate-probability-forecast
When your agent uses it
Aggregate and iteratively recalibrate probabilistic forecasts, preserving uncertainty, calibration evidence, and unresolved forecaster disagreement.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytes
Read SKILL.md
# calibrate-probability-forecast
## Purpose
Aggregate probabilistic forecasts, compare them with outcomes, and recalibrate without hiding unresolved forecaster disagreement.
## Input contract
```yaml
required: [forecast_records, outcome_records, calibration_rule]
optional: [forecaster_metadata, prior_calibration, aggregation_method]
constraints: [each forecast has a target, probability, timestamp, horizon, and provenance]
```
## Procedure
1. Align forecasts with realized outcomes at the declared horizon and freeze the evaluation set.
2. Compute calibration evidence by probability band and forecaster, preserving sample size and missing outcomes.
3. Update the aggregation or calibration rule only where outcome-linked error supports the change.
4. Emit recalibrated probabilities, calibration diagnostics, disagreement intervals, and the next review trigger.canonicalize-entity
When your agent uses it
Resolve aliases and near-duplicates into canonical entities while preserving provenance and rejecting false merges; entity schema is configurable.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
693 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore3,345 bytesSKILL.mdcore3,345 bytesSKILL.mdcore3,345 bytesSKILL.mdcore3,345 bytesSKILL.mdcore3,345 bytes
Read SKILL.md
# canonicalize-entity
## Purpose
Resolve aliases and near-duplicates into canonical entities while preserving provenance and rejecting false merges.
## Input contract
```yaml
required: [raw_entities, entity_schema, alias_evidence]
optional: [synonym_dictionary, organization_relationships, graph_edges, canonicalization_policy]
constraints: [the entity schema is explicit; merge requires semantic identity evidence; preserve provenance and redirect relationships]
```
categorize-evidence
When your agent uses it
Cluster an evidence corpus by theme, method, chronology, mechanism, or another declared schema.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,597 bytes
Read SKILL.md
# categorize-evidence
## Purpose
Cluster an evidence corpus by a declared thematic, methodological, chronological, mechanistic, or other schema.
## Input contract
```yaml
required: [evidence_records, category_schema]
optional: [coding_rules, multi_label_policy, seed_categories]
constraints: [category assignments require record evidence and allow explicit multi-label or unknown states]
```
challenge-assumption
When your agent uses it
Construct a strong countercase or alternative to an assumption and assess consequence if it fails.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
328 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,701 bytes
Read SKILL.md
# challenge-assumption
## Purpose
Construct a strong countercase or alternative to an assumption and assess the consequence if it fails.
## Input contract
```yaml
required: [assumption, claim_or_decision, supporting_evidence]
optional: [alternative_worlds, dependency_graph, challenge_mode]
constraints: [separate assumption, countercase, evidence, and impact]
```
## Procedure
1. State the assumption's role and dependencies in the target claim.characterize-anomaly
When your agent uses it
Precisely characterize an anomaly by contrasting observation with expectation, quantifying deviation where possible, recording conditions, and excluding obvious/trivial explanations before generating hypotheses.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
306 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,631 bytes
Read SKILL.md
# characterize-anomaly
## Purpose
Characterize an observation that departs from an expected pattern and separate signal from measurement or protocol artifact.
## Input contract
```yaml
required: [observation, reference_pattern, condition_records]
optional: [uncertainty_estimates, replication_records, artifact_hypotheses]
constraints: [anomaly status requires a defined comparison and condition context]
```
check-dominance
When your agent uses it
Identify Pareto-dominated and non-dominated alternatives under strict dominance.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore1,797 bytesSKILL.mdcore1,797 bytes
Read SKILL.md
# check-dominance
## Purpose
Identify Pareto-dominated and non-dominated alternatives under strict dominance.
## Input contract
```yaml
required: [alternative_set, score_matrix, criterion_directions]
optional: [missing_value_policy, equality_tolerance]
constraints: [all compared scores share declared direction and scale]
```
## Procedure
1. Normalize criterion direction and validate comparable rows.classify-assumption-vulnerability
When your agent uses it
Classify assumptions by load-bearing importance and vulnerability.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
235 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,204 bytes
Read SKILL.md
# classify-assumption-vulnerability
## Purpose
Classify assumptions by load-bearing importance and vulnerability to determine which require stress testing.
## Input contract
```yaml
required: [assumption_register, dependent_claims]
optional: [evidence_strength, perturbation_bounds]
constraints: [importance and vulnerability must be scored or categorized separately]
```
## Procedure
1. Link each assumption to the claims or causal edges it supports.
2. Assess consequence of failure and current evidential support.
3. Assign vulnerability class and prioritize assumptions for challenge.
## Output contractclassify-constraint
When your agent uses it
Classify constraints as hard, soft, or assumption-like after explicit identification.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
293 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,489 bytes
Read SKILL.md
# classify-constraint
## Purpose
Classify each identified constraint as hard, soft, or assumption-like and make the consequence of that class explicit.
## Input contract
```yaml
required: [constraint_candidates, evidence_register, decision_context]
optional: [stakeholder_requirements, prior_constraint_ledger]
constraints: [each candidate has a statement, scope, source, and consequence if violated]
```
## Procedure
1. Parse each candidate into condition, scope, source, and violation consequence.
2. Mark hard when violation is disqualifying and externally anchored; soft when tradeable; assumption-like when inferred and testable.
3. Record the evidence and counterevidence supporting the class.
4. Emit the classified ledger and tests or escalation required for uncertain classes.classify-falsification-verdict
When your agent uses it
Classify a tested claim as BROKEN, CORROBORATED, or UNFALSIFIABLE based on whether a legitimate falsifier succeeded, failed under adequate power, or cannot be specified/reached.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
279 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,189 bytes
Read SKILL.md
# classify-falsification-verdict
## Purpose
Classify a tested claim as BROKEN, CORROBORATED, or UNFALSIFIABLE.
## Input contract
```yaml
required: [claim, falsifier, test_result, adequacy_assessment]
optional: [scope, power_or_precision]
constraints: [falsifier must be legitimate and within scope]
```
## Procedure
1. Check the falsifier and scope.
2. Assess whether the test was adequate.
3. Return exactly one permitted verdict with rationale.
## Output contractclassify-research-gap
When your agent uses it
Classify a candidate research gap by type (evidence, method, mechanism, population, theory, measurement, contradiction, boundary, translation, etc.) and record implications for next actions.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,373 bytes
Read SKILL.md
# classify-research-gap
## Purpose
Classify a candidate research gap by type and record implications for the next research action.
## Input contract
```yaml
required: [gap_statement, supporting_evidence]
optional: [domain_scope, candidate_gap_types]
constraints: [gap type must be supported by evidence and distinguished from absence of search]
```
## Procedure
1. Compare the gap claim with the declared evidence and scope.
2. Test evidence, method, mechanism, population, theory, measurement, contradiction, boundary, and translation categories.
3. Assign one or more justified types and map each to a next action.
## Output contractclassify-simplicity-evidence
When your agent uses it
Classify simplicity/compression as earned, weak, or decorative based on whether it forbids alternatives, compresses independent facts, or merely renames/repackages them.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
261 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,281 bytes
Read SKILL.md
# classify-simplicity-evidence
## Purpose
Classify explanatory compression as earned, weak, or decorative.
## Input contract
```yaml
required: [explanation, covered_facts, alternatives, predictions]
optional: [evidence]
constraints: [facts and alternatives must be independently listed]
```
## Procedure
1. Check whether independent facts are compressed.
2. Check whether alternatives are forbidden and predictions constrained.
3. Classify earned, weak, or decorative and preserve rationale.
classify-stakeholder-salience
When your agent uses it
Classify stakeholder salience using power, legitimacy, urgency, dependency, or a supplied salience schema.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
280 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,340 bytes
Read SKILL.md
# classify-stakeholder-salience
## Purpose
Classify stakeholder salience using power, legitimacy, urgency, dependency, or a supplied schema.
## Input contract
```yaml
required: [stakeholder_set, salience_schema]
optional: [power_evidence, legitimacy_evidence, urgency_evidence, dependency_evidence]
constraints: [each classification dimension needs an evidence status]
```
## Procedure
1. Normalize stakeholders and their relevant claims or stakes.
2. Score or categorize each stakeholder on the supplied salience dimensions.
3. Record dependency and conflict effects, then produce a prioritized salience map.
## Output contractcollect-independent-judgments
When your agent uses it
Collect judgments/rankings from multiple genuinely independent evaluators or perspectives before exposing any peer outputs, preserving ballots and rationale for later social-choice aggregation.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
402 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,123 bytesSKILL.mdcore2,123 bytes
Read SKILL.md
# collect-independent-judgments
## Purpose
Collect blinded judgments from genuinely independent evaluators or perspectives before exposing peer outputs.
## Input contract
```yaml
required: [judgment_prompt, evaluator_roster, candidate_set, independence_rules]
optional: [rubric, response_deadline, abstention_policy]
constraints: [evaluators receive no peer judgments; each ballot preserves rationale and provenance]
```
## Procedure
1. Freeze the candidate set, rubric, prompt, and independence rules before collection.
2. Obtain one sealed judgment and rationale per evaluator, recording abstentions and unavailable evidence.
3. Check for shared data, model, prompt, or deliberation leakage before unblinding.
4. Unblind only after collection, then return ballots, independence flags, and an aggregation-ready dataset.compare-evaluation-protocols
When your agent uses it
Build a protocol-difference matrix and estimate which differences can materially change measured performance.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,415 bytes
Read SKILL.md
# compare-evaluation-protocols
## Purpose
Build a protocol-difference matrix and estimate which differences can materially change measured performance.
## Input contract
```yaml
required: [protocol_records, metric_schema, comparison_target]
optional: [paired_results, sensitivity_assumptions]
constraints: [differences require explicit protocol fields and a comparable outcome]
```
compare-hypotheses
When your agent uses it
Build an explicit comparison matrix over hypotheses, predictions, and evidence.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
259 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,330 bytes
Read SKILL.md
# compare-hypotheses
## Purpose
Compare competing hypotheses against shared evidence, predictions, assumptions, and explanatory scope.
## Input contract
```yaml
required: [hypotheses, evidence_records, comparison_criteria]
optional: [priors, discriminating_predictions, model_constraints]
constraints: [criteria and evidence must be applied symmetrically]
```
compare-pair
When your agent uses it
Execute one pairwise comparison under a specified criterion/model and return winner, confidence, and reasons.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
314 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,524 bytes
Read SKILL.md
# compare-pair
## Purpose
Execute one pairwise comparison under a declared criterion and return a winner, confidence, tie status, and reasons.
## Input contract
```yaml
required: [item_a, item_b, comparison_criterion, comparison_model, evidence_register]
optional: [tie_rule, prior_ratings]
constraints: [criterion direction and evidence scope are fixed before comparison]
```
## Procedure
1. Verify that both items are comparable under the same criterion and evidence scope.
2. Assess item A and item B symmetrically, recording criterion-level evidence and limitations.
3. Select A, B, or tie; assign confidence on the declared scale and explain the decisive contrast.
4. Return the comparison record without updating global ratings.conceptual-blending
When your agent uses it
Construct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,173 bytesSKILL.mdcore3,173 bytesSKILL.mdcore3,173 bytesSKILL.mdcore3,173 bytesSKILL.mdcore3,173 bytesSKILL.mdcore3,173 bytes
Read SKILL.md
# conceptual-blending
## Purpose
Blend multiple input spaces through a generic space and selective projection to generate emergent research ideas.
## Input contract
```yaml
mode_contracts:
two-space-blend: &blending_input
required: [input_spaces]
optional: [compatibility_constraints]
constraints: [each_input_space_must_have_explicit_entities_and_relations]
multi-space-blend: *blending_input
emergent-property-search: *blending_input
```
## Execution protocolconstruct-argument-map
When your agent uses it
Atomize claims, expose premises and counterclaims, attach evidence/defeaters, score claim strength, and construct an inspectable argument graph independent of storage format.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,635 bytesSKILL.mdcore3,635 bytesSKILL.mdcore3,635 bytes
Read SKILL.md
# construct-argument-map
## Purpose
Atomize claims, expose premises and counterclaims, attach evidence/defeaters, score claim strength, and construct an inspectable argument graph independent of storage format.
## Input contract
```yaml
required: [claim_records, premise_records, evidence_records]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
construct-causal-model
When your agent uses it
Construct and validate an explicit causal model with measurable variables, mechanism edges, evidence links, feedback loops, interventions, counterevidence, and confidence.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
857 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore4,317 bytesSKILL.mdcore4,317 bytes
Read SKILL.md
# construct-causal-model
## Purpose
Construct and validate an explicit causal model with measurable variables, mechanism edges, evidence links, feedback loops, interventions, counterevidence, and confidence.
## Input contract
```yaml
required: [variable_records, mechanism_candidates, evidence_records]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
construct-counterfactual
When your agent uses it
Construct the minimally or explicitly intervened counterfactual world required by the parent analysis.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
309 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,646 bytes
Read SKILL.md
# construct-counterfactual
## Purpose
Construct the minimally or explicitly intervened counterfactual world required by the parent analysis.
## Input contract
```yaml
required: [baseline_artifact, intervention_target, intervention_specification]
optional: [structural_model, invariants, outcome_query]
constraints: [alter only declared factors; preserve stated invariants]
```
## Procedure
1. Freeze the baseline artifact and enumerate the target factor's dependencies.construct-critique
When your agent uses it
Construct the strongest structured attack on a claim/artifact, grounded in explicit reasons/evidence.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
479 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,267 bytesSKILL.mdcore2,267 bytesSKILL.mdcore2,267 bytes
Read SKILL.md
# construct-critique
## Purpose
Construct the strongest structured attack on a claim or artifact from an explicit perspective, grounded in reasons and evidence.
## Input contract
```yaml
required: [target_claim_or_artifact, critique_perspective, evidence_set]
optional: [argument_schema, known_assumptions, decision_context]
constraints: [separate claim, ground, warrant, rebuttal, and severity; critique must target the supplied artifact]
```
construct-defense
When your agent uses it
Construct the strongest defensible case while acknowledging valid weaknesses.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,412 bytes
Read SKILL.md
# construct-defense
## Purpose
Construct the strongest defensible case while acknowledging valid weaknesses.
## Input contract
```yaml
required: [position, evidence_set, objection_set]
optional: [defense_criteria, audience, weakness_policy]
constraints: [support must be evidence-linked and weaknesses cannot be erased]
```
## Procedure
1. State the position and burden of proof.
2. Select and order the strongest supporting arguments.
3. Address objections and reframe only where evidence supports the reframe.
4. Mark residual weaknesses and scope limits.construct-design-matrix
When your agent uses it
Construct a balanced/randomized/orthogonal experimental design matrix appropriate to the chosen design mode.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,688 bytesSKILL.mdcore1,688 bytesSKILL.mdcore1,688 bytes
Read SKILL.md
# construct-design-matrix
## Purpose
Construct a balanced/randomized/orthogonal experimental design matrix appropriate to the chosen design mode.
## Input contract
```yaml
required: [factor_schema, design_mode, run_budget, randomization_constraints]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
construct-evidence-network
When your agent uses it
Construct a network-meta-analysis evidence graph and evaluate connectivity/transitivity prerequisites.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
293 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,576 bytes
Read SKILL.md
# construct-evidence-network
## Purpose
Construct an evidence graph for network synthesis and evaluate connectivity, transitivity, and comparison support.
## Input contract
```yaml
required: [evidence_records, intervention_nodes, outcome_schema]
optional: [study_designs, effect_sizes, covariate_schema]
constraints: [edges require a shared outcome definition and traceable comparison evidence]
```
construct-hierarchy
When your agent uses it
Construct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,019 bytesSKILL.mdcore2,019 bytesSKILL.mdcore2,019 bytes
Read SKILL.md
# construct-hierarchy
## Purpose
Construct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints.
## Input contract
```yaml
required: [entity_set, relation_assertions, hierarchy_scope]
optional: [root_policy, multiple_inheritance_policy, depth_limit]
constraints: [relations use declared types; cycles are invalid]
```
## Procedure
1. Normalize entity identifiers and relation types.construct-input-spaces
When your agent uses it
Define the structured input spaces for conceptual blending: entities, relations, goals, constraints, and salient dynamics in each source.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
270 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,365 bytesSKILL.mdcore1,365 bytesSKILL.mdcore1,365 bytesSKILL.mdcore1,365 bytes
Read SKILL.md
# construct-input-spaces
## Purpose
Define the explicit source spaces used by conceptual blending.
## Input contract
```yaml
required: [source_domains, blend_goal]
optional: [entities, relations, constraints, salient_dynamics]
constraints: [each source needs entities, relations, goals, and constraints or an explicit unknown]
```
## Procedure
1. Partition each source domain into entities, relations, goals, constraints, and dynamics.
2. Normalize equivalent roles without erasing source-specific structure.
3. Record the blend goal and the items eligible for projection.
construct-perspective-set
When your agent uses it
Construct an explicit set of scientifically relevant viewpoints, roles, worldviews, stakeholder positions, or epistemic lenses to apply to the same object.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
365 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,787 bytes
Read SKILL.md
# construct-perspective-set
## Purpose
Construct an explicit set of relevant viewpoints or epistemic lenses for one object.
## Input contract
```yaml
required: [target_object, perspective_basis, selection_goal]
optional: [stakeholder_set, domain_roles, worldview_constraints]
constraints: [each perspective must have a distinct warrant and scope]
```
## Procedure
1. Enumerate candidate roles, worldviews, and stakeholder positions.
2. Select a coverage-complete set and state inclusion rationale.
3. Record each lens's assumptions, objectives, and blind spots.
4. Return the set with mapping to the target object.construct-scenario
When your agent uses it
Construct a scenario across key uncertainties with explicit assumptions and plausibility. Modes include baseline/narrative, counterfactual, and extreme-but-plausible worst-case with breaking point, failure cascade, recovery assumptions, and distinguishing observables.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
461 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,395 bytesSKILL.mdcore2,395 bytes
Read SKILL.md
# construct-scenario
## Purpose
Construct scenarios across key uncertainties with explicit assumptions and plausibility, including baseline, counterfactual, and extreme-but-plausible modes.
## Input contract
```yaml
required: [context, uncertainty_set, scenario_mode]
optional: [drivers, dependency_model, probability_method, recovery_assumptions]
constraints: [scenario assumptions and distinguishing observables must be explicit]
```
## Procedure
1. Select uncertainty axes and record their state space.construct-validity-envelope
When your agent uses it
Synthesize multi-axis breakpoints into a multidimensional statement of where a claim/method remains valid.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
315 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,581 bytes
Read SKILL.md
# construct-validity-envelope
## Purpose
Synthesize multi-axis breakpoints into a multidimensional statement of where a claim or method remains valid.
## Input contract
```yaml
required: [claim_or_method, axis_results, validity_criteria]
optional: [boundary_interactions, uncertainty_model, extrapolation_policy]
constraints: [each boundary is tied to an axis result and evidence]
```
## Procedure
1. Align axis scales, directions, and validity labels.
2. Combine breakpoint regions and inspect interaction effects.
3. Mark supported, uncertain, and invalid regions.
4. Emit the envelope with extrapolation warnings and monitoring observables.counterfactual-causal-analysis
When your agent uses it
Intervene on factors, construct counterfactual worlds, test necessity/sufficiency, and identify load-bearing causal factors.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
572 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,759 bytesSKILL.mdcore2,759 bytesSKILL.mdcore2,759 bytesSKILL.mdcore2,759 bytesSKILL.mdcore2,759 bytes
Read SKILL.md
# counterfactual-causal-analysis
## Purpose
Intervene on factors, construct counterfactual worlds, test necessity and sufficiency, and identify load-bearing causal factors.
## Input contract
```yaml
required: [causal_claim, variables, intervention_target]
optional: [mechanism_graph, baseline_world, comparison_conditions]
constraints: [intervention and outcome must be measurable or explicitly qualitative]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `extract-causal-structure` to extract the causal structure. You MUST load skill `identify-variables` to type its variables.
2. You MUST load skill `construct-counterfactual` to construct the counterfactual. You MUST load skill `identify-load-bearing-factors` to identify load-bearing factors.coverage-white-space-search
When your agent uses it
Map known methods against problem/parameter space and generate candidates from uncovered and weakly covered intersections. Acquisition mechanism is runtime-selected.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
515 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,629 bytesSKILL.mdcore2,629 bytes
Read SKILL.md
# coverage-white-space-search
## Purpose
Map known methods against a problem space and generate candidates from intersections that are uncovered or covered without being closed.
## Input contract
```yaml
required: [reference_items, coverage_dimensions]
optional: [performance_records, eligibility_rules]
constraints: [reference items and dimension values must be identifiable]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `inventory-reference-items` to inventory references.
2. You MUST load skill `map-coverage-space` to map coverage and grade its strength.cross-examine
When your agent uses it
Probe responses for inconsistency, logic gaps, and unsupported claims.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
208 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore983 bytes
Read SKILL.md
# cross-examine
## Purpose
Probe responses for inconsistency, logic gaps, and unsupported claims.
## Input contract
```yaml
required: [claim, response, questions, evidence]
optional: [criteria, prior_rounds]
constraints: [questions must target explicit claims or assumptions]
```
## Procedure
1. Identify unsupported or inconsistent assertions.
2. Ask targeted follow-up questions.
3. Record answers, unresolved gaps, and evidence requests.
## Output contractcrystallize-north-star
When your agent uses it
Compress the goal structure and intentionality into a specific, ambitious, achievable one-sentence research North Star.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
286 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,414 bytes
Read SKILL.md
# crystallize-north-star
## Purpose
Compress a validated goal structure into one specific, ambitious, achievable research North Star.
## Input contract
```yaml
required: [goal_tree, constraints, intended_effect]
optional: [feasibility_annotations, actor_profile, evidence_context]
constraints: [the statement must preserve the declared outcome and limiting constraints]
```
dare
When your agent uses it
DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
678 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input Contract
- Execution Protocol
- Output Contract
- Completion Criteria
- Failure and Backtrack
- Boundary
Files
SKILL.mdcore3,265 bytesSKILL.mdcore3,265 bytes
Read SKILL.md
# dare
## Purpose
DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution. It is not a scientific graph node and must not be counted among the 267 tactic/SOP nodes.
## Input Contract
```yaml
required: [user_request]
optional: [existing_context, north_star, research_brief, constraints]
constraints:
- a run may start with an existing North Star only when it is explicit and user-confirmed
- execution requires a current SpecView reconstructed from checkpoint eventsdecompose-and-or-goal
When your agent uses it
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
335 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,552 bytes
Read SKILL.md
# decompose-and-or-goal
## Purpose
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
## Input contract
```yaml
required: [top_goal, constraints]
optional: [actor_profile, obstacle_report, existing_subgoals]
constraints: [branch semantics, dependencies, and leaf criteria must be explicit]
```
decompose-components
When your agent uses it
Decompose a system into components/functions and record dependencies relevant to transformation.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
238 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,233 bytes
Read SKILL.md
# decompose-components
## Purpose
Decompose a system into components and functions, preserving dependencies relevant to transformation.
## Input contract
```yaml
required: [system_or_design, decomposition_purpose]
optional: [component_inventory, dependency_evidence]
constraints: [components must have a function or interface and a parent relation]
```
## Procedure
1. Enumerate observable components and their functions.
2. Split compound components until each unit has a distinct transformation boundary.
3. Link dependencies, interfaces, and affected outcomes.
## Output contractdecompose-evaluation-metric
When your agent uses it
Decompose an evaluation metric into rewarded signals, aggregation choices, polarity, ceiling effects, and Goodhart vulnerabilities.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
303 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,574 bytes
Read SKILL.md
# decompose-evaluation-metric
## Purpose
Decompose an evaluation metric into rewarded signals, aggregation choices, polarity, ceiling effects, and Goodhart vulnerabilities.
## Input contract
```yaml
required: [metric_definition, scored_outputs]
optional: [reference_standard, aggregation_rule, known_failure_cases]
constraints: [each component must have a declared direction and interpretation]
```
decompose-global-sensitivity
When your agent uses it
Estimate global main effects and interactions across uncertain inputs using screening/decomposition methods such as Morris→Sobol or an equivalent supplied method.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,592 bytes
Read SKILL.md
# decompose-global-sensitivity
## Purpose
Estimate global main effects and interactions across uncertain inputs using screening and decomposition.
## Input contract
```yaml
required: [model, uncertain_inputs, output_metric]
optional: [input_distributions, screening_method, decomposition_method]
constraints: [input distributions and sampling design must be declared]
```
## Procedure
1. Define input ranges/distributions and the output metric.
2. Screen influential variables with Morris or an equivalent declared method.
3. Estimate main and interaction effects with Sobol or an equivalent variance decomposition.
4. Compare sensitivity rankings across sampling assumptions.decompose-ishikawa
When your agent uses it
Build an Ishikawa-style causal decomposition across relevant cause families.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
243 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,120 bytes
Read SKILL.md
# decompose-ishikawa
## Purpose
Build an Ishikawa causal decomposition across relevant cause families.
## Input contract
```yaml
required: [effect_statement, cause_families]
optional: [evidence_records, system_boundary]
constraints: [cause families must be named and causes linked to the effect]
```
## Procedure
1. Place the normalized effect at the head of the diagram.
2. Populate relevant method, data, theory, measurement, researcher, and environment branches.
3. Subdivide each branch into testable causes and mark evidence status.
## Output contractdecompose-research-goal
When your agent uses it
Turn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
613 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,921 bytesSKILL.mdcore2,921 bytesSKILL.mdcore2,921 bytesSKILL.mdcore2,921 bytesSKILL.mdcore2,921 bytesSKILL.mdcore2,921 bytes
Read SKILL.md
# decompose-research-goal
## Purpose
Turn a research direction into an AND/OR goal DAG with testable leaves, dependencies, and feasibility annotations.
## Input contract
```yaml
required: [research_direction, constraints]
optional: [actor_profile, obstacle_report, timeline, north_star]
constraints: [goal wording, constraints, and source context must be explicit]
```
decompose-research-question
When your agent uses it
Decompose a complex RQ into MECE subquestions, map dependencies, and schedule the answering order.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
484 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,387 bytesSKILL.mdcore2,387 bytes
Read SKILL.md
# decompose-research-question
## Purpose
Decompose a complex RQ into MECE subquestions, map dependencies, and schedule the answering order.
## Input contract
```yaml
required: [research_question, scope_constraints, dependency_evidence]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
define-analysis-dimensions
When your agent uses it
Identify approximately independent dimensions/axes that span the relevant problem, design, or validity space and define their semantics.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
474 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,378 bytesSKILL.mdcore2,378 bytesSKILL.mdcore2,378 bytes
Read SKILL.md
# define-analysis-dimensions
## Purpose
Define approximately independent, measurable axes that span a problem, design, or validity space.
## Input contract
```yaml
required: [problem_or_artifact, target_outcome, dimension_ontology]
optional: [candidate_axes, domain_constraints, measurement_plan]
constraints: [each axis has semantics, type, direction, and measurement rule; correlated axes are flagged]
```
define-criteria
When your agent uses it
Derive explicit evaluation criteria from the research objective and candidate set.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
442 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,250 bytesSKILL.mdcore2,250 bytes
Read SKILL.md
# define-criteria
## Purpose
Derive explicit evaluation criteria from the research objective and candidate set.
## Input contract
```yaml
required: [research_objective, candidate_set, decision_context]
optional: [stakeholder_priorities, measurement_constraints, candidate_domains]
constraints: [criteria must be mutually interpretable across candidates]
```
## Procedure
1. Extract desired outcomes and constraints from the objective.define-evidence-protocol
When your agent uses it
Define research questions, evidence scope, queries/concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence for an acquisition task.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
362 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,860 bytesSKILL.mdcore1,860 bytes
Read SKILL.md
# define-evidence-protocol
## Purpose
Define research questions, eligible evidence scope, query concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence.
## Input contract
```yaml
required: [research_question, evidence_scope, inclusion_rules]
optional: [exclusion_rules, query_concepts, quality_rubric, stopping_policy]
constraints: [eligible universe, provenance fields, and stopping evidence must be explicit]
```
define-objective
When your agent uses it
Formalize objectives, constraints, and tradeoff preferences for optimization.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
371 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,004 bytesSKILL.mdcore2,004 bytes
Read SKILL.md
# define-objective
## Purpose
Formalize objectives, constraints, and tradeoff preferences before an optimization or selection decision.
## Input contract
```yaml
required: [decision_context, candidate_set, stakeholder_preferences]
optional: [hard_constraints, utility_scale, priority_weights]
constraints: [objectives are measurable or operationalized; tradeoffs and constraint direction are explicit]
```
## Procedure
1. Elicit the desired outcome, affected scope, stakeholders, and time horizon.
2. Separate objectives from constraints and preferences, then define each objective's direction and measurement.
3. Record conflicts, permissible tradeoffs, and any weights or lexicographic priorities with their rationale.
4. Emit an objective schema suitable for comparison, optimization, and later audit.derive-consequences
When your agent uses it
Trace logically valid consequences from an altered premise, provocation, or negated claim.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
297 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,493 bytes
Read SKILL.md
# derive-consequences
## Purpose
Trace valid consequences from an altered premise, provocation, or negated claim.
## Input contract
```yaml
required: [premise_change, base_model, inference_rules]
optional: [time_horizon, boundary_conditions, contradiction_policy]
constraints: [each consequence links to an explicit inference step]
```
## Procedure
1. State the altered premise and preserve unaffected assumptions.
2. Apply inference rules stepwise, recording intermediates and branches.
3. Mark contradictions, uncertainty, and boundary violations.
4. Return consequences with dependency paths and testable implications.design-data-extraction
When your agent uses it
Define a structured extraction form, field semantics, coding rules, and missing-data handling for evidence synthesis.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
303 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,497 bytesSKILL.mdcore1,497 bytes
Read SKILL.md
# design-data-extraction
## Purpose
Define a structured extraction form, field semantics, coding rules, and missing-data handling for evidence synthesis.
## Input contract
```yaml
required: [evidence_question, record_schema]
optional: [coding_guidance, unit_rules, quality_fields]
constraints: [field definitions and missing-data states must be explicit]
```
design-discriminating-prediction
When your agent uses it
Construct a prediction that yields different outcomes under competing hypotheses.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
258 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,347 bytes
Read SKILL.md
# design-discriminating-prediction
## Purpose
Design an observation or test whose outcomes distinguish among competing hypotheses.
## Input contract
```yaml
required: [hypotheses, current_evidence, target_comparison]
optional: [constraints, measurable_variables, candidate_interventions]
constraints: [predictions must differ on an observable outcome]
```
design-experiment
When your agent uses it
Translate a falsifiable hypothesis into a statistically defensible experiment. Factorial, ablation, comparison, scaling, and robustness designs are modes, not strategy nodes.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
3,269 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
- Purpose
- When to use / not applicable
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytesSKILL.mdcore13,716 bytes
Read SKILL.md
# design-experiment
## Purpose
Translate a falsifiable hypothesis into a statistically defensible experiment. Factorial, ablation, comparison, scaling, and robustness are modes.
## When to use / not applicable
Use after a hypothesis has an operational construct and discriminating prediction. Not applicable when the hypothesis or measurable outcome is absent.
## Input contract
```yaml
mode_contracts:design-falsification-test
When your agent uses it
Specify a concrete observation, computation, intervention, counterexample, or measurement that would count against the sharpened claim, prioritizing cheap high-information tests.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
279 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,385 bytes
Read SKILL.md
# design-falsification-test
## Purpose
Specify a concrete observation, computation, intervention, counterexample, or measurement that could count against a claim.
## Input contract
```yaml
required: [sharp_claim, scope, candidate_observables]
optional: [cost, available_tools, competing_predictions]
constraints: [test must identify a failure condition and measurement rule]
```
## Procedure
1. Enumerate claim commitments and possible failure observations.
2. Rank tests by information value and cost.
3. Specify the cheapest decisive test with pass/fail interpretation.
design-mitigation
When your agent uses it
Design an intervention that prevents, detects, responds to, removes, or relaxes a failure mode/constraint; state residual risk and validation evidence.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
387 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,865 bytes
Read SKILL.md
# design-mitigation
## Purpose
Design an intervention that prevents, detects, responds to, removes, or relaxes a failure mode.
## Input contract
```yaml
required: [failure_mode, causal_mechanism, resource_limits]
optional: [existing_controls, timeline, acceptance_criteria]
constraints: [residual risk and validation evidence must be explicit]
```
## Procedure
1. Classify the failure and locate controllable causal points.
2. Generate prevention, detection, response, removal, and relaxation options.
3. Sequence selected actions with resources and validation tests.
4. Estimate residual risk and define escalation conditions.design-randomness-protocol
When your agent uses it
Identify randomness sources and define seed/repetition/propagation rules sufficient for the intended reproducibility level.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
318 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,588 bytesSKILL.mdcore1,588 bytesSKILL.mdcore1,588 bytes
Read SKILL.md
# design-randomness-protocol
## Purpose
Identify randomness sources and define seed/repetition/propagation rules sufficient for the intended reproducibility level.
## Input contract
```yaml
required: [randomness_sources, reproducibility_target, run_plan]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
design-study-inclusion
When your agent uses it
Define study inclusion/exclusion criteria and explicit rules for borderline cases.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
289 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,515 bytesSKILL.mdcore1,515 bytes
Read SKILL.md
# design-study-inclusion
## Purpose
Define study inclusion and exclusion criteria with explicit rules for borderline cases.
## Input contract
```yaml
required: [research_question, eligible_population, study_scope]
optional: [outcome_rules, design_rules, date_language_limits]
constraints: [criteria must be observable from source records]
```
destructive-ideation
When your agent uses it
Break fixation by surfacing assumptions and applying deliberate provocation modes (reversal, negation, random entry, exaggeration, extreme/zero-resource constraint, distortion), then extract constructive movement and synthesize candidate directions.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,699 bytesSKILL.mdcore3,699 bytes
Read SKILL.md
# destructive-ideation
## Purpose
Break fixation with explicit provocation modes, then extract constructive movement and candidate directions.
## Input contract
```yaml
mode_contracts:
reverse: &destructive_input
required: [current_frame, target_problem]
optional: [load_bearing_assumptions, constraints]
constraints: [provocation_must_name_the_frame_or_assumption_it_attacks]
negation: *destructive_input
random-entry: *destructive_input
extreme-constraint: *destructive_input
sacred-cow: *destructive_inputdetect-breakpoint
When your agent uses it
Locate the point or region where performance/validity changes regime or the claim flips.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
309 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,515 bytes
Read SKILL.md
# detect-breakpoint
## Purpose
Locate the point or region where performance, validity, or a claim changes regime.
## Input contract
```yaml
required: [ordered_observations, target_metric, flip_or_regime_rule]
optional: [candidate_axis, smoothing_rule, uncertainty_bounds]
constraints: [ordering and metric direction are explicit]
```
## Procedure
1. Sort observations along the declared axis and validate comparability.
2. Detect abrupt flips, slope changes, saturation, or regime transitions.
3. Estimate boundary region and attach uncertainty.
4. Return witness observations and follow-up tests.detect-contradiction
When your agent uses it
Detect an explicit contradiction in logical derivations, claims, or evidence relations; classify whether it is formal, empirical, scope-dependent, or unresolved.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
513 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,520 bytesSKILL.mdcore2,520 bytesSKILL.mdcore2,520 bytes
Read SKILL.md
# detect-contradiction
## Purpose
Detect and classify explicit contradictions in derivations, claims, or evidence relations.
## Input contract
```yaml
required: [claims_or_derivation, evidence_relations, scope_context]
optional: [logic_rules, causal_graph, contradiction_taxonomy]
constraints: [distinguish formal, empirical, scope-dependent, and unresolved contradiction; preserve both sides]
```
detect-coverage-gap
When your agent uses it
Given an explicit coverage representation (matrix, graph, taxonomy, IP feature space), identify absent, thin, disconnected, or weakly covered regions and characterize why they matter.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
744 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytesSKILL.mdcore3,616 bytes
Read SKILL.md
# detect-coverage-gap
## Purpose
Given an explicit matrix, graph, taxonomy, or IP feature space, identify absent, thin, disconnected, or weakly covered regions and explain why they matter.
## Input contract
```yaml
required: [coverage_representation, universe_definition, coverage_evidence]
optional: [gap_priority_rule, taxonomy, graph_statistics, domain_constraints]
constraints: [the representation and eligible universe are explicit; every reported gap points to an absent, thin, disconnected, or weakly covered region]
```
detect-feedback-loop
When your agent uses it
Detect and characterize reinforcing/balancing feedback loops, participating variables, delays, and possible breakpoints.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,441 bytes
Read SKILL.md
# detect-feedback-loop
## Purpose
Detect reinforcing or balancing feedback loops in a causal or process structure and state the evidence for each loop.
## Input contract
```yaml
required: [causal_graph, node_semantics, edge_polarity]
optional: [time_delays, observed_series, intervention_records]
constraints: [loop classification requires directed edges and polarity or transition evidence]
```
detect-pass-by-construction
When your agent uses it
Identify cases where the validator is structurally unable to reject the target because acceptance follows from assumptions copied from the target theory or construction process.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
247 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,281 bytes
Read SKILL.md
# detect-pass-by-construction
## Purpose
Identify validators structurally unable to reject a target because acceptance follows from copied assumptions.
## Input contract
```yaml
required: [target_claim, validator, noncircularity_matrix]
optional: [acceptance_rule, construction_history]
constraints: [copied, shared, derived, and independent assumptions must be distinguished]
```
## Procedure
1. Find validator assumptions copied from the target.
2. Trace whether acceptance follows without an independent test.
3. Report pass-by-construction and required failure channels.
## Output contractdetect-performance-discrepancy
When your agent uses it
Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,504 bytes
Read SKILL.md
# detect-performance-discrepancy
## Purpose
Detect material score discrepancies for the same method or task across sources and identify plausible condition differences.
## Input contract
```yaml
required: [performance_records, method_key, task_key, metric_schema]
optional: [protocol_records, condition_schema, uncertainty_estimates]
constraints: [comparisons require aligned metric direction and declared conditions]
```
discover-biological-analog
When your agent uses it
Identify biological systems that achieve the target function under comparable constraints, without assuming surface similarity.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
291 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,502 bytes
Read SKILL.md
# discover-biological-analog
## Purpose
Identify biological systems that achieve a target function under comparable constraints.
## Input contract
```yaml
required: [biological_function, biological_constraints]
optional: [search_terms, candidate_taxa, environment]
constraints: [candidate must demonstrate the function, not merely resemble the target]
```
## Procedure
1. Search across organism, process, and ecosystem levels using the function formulation.
2. Verify the candidate's observed function and environmental constraints.
3. Rank candidates by mechanism evidence and transfer relevance.
document-counterclaim
When your agent uses it
Construct a counterclaim, identify its target claim, contradiction type, assumptions, and supporting evidence requirements.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,362 bytes
Read SKILL.md
# document-counterclaim
## Purpose
Document a credible counterclaim, its supporting basis, scope, and implications for the focal claim.
## Input contract
```yaml
required: [focal_claim, counterclaim, evidence_records]
optional: [argument_context, boundary_conditions, response_options]
constraints: [counterclaim must be stated in its strongest evidence-supported form]
```
downgrade-equivalence-claim
When your agent uses it
When full equivalence fails, downgrade to the strongest defensible relation (e.g. substructure, homomorphism, shared invariant, analogy) and record exactly what ceased to be preserved.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,194 bytes
Read SKILL.md
# downgrade-equivalence-claim
## Purpose
When full equivalence fails, downgrade to the strongest defensible relation and record what was not preserved.
## Input contract
```yaml
required: [equivalence_claim, preservation_report, counterexamples]
optional: [relation_ladder, scope]
constraints: [each downgrade must name lost structures or operations]
```
## Procedure
1. List failed preservation obligations.
2. Test candidate weaker relations.
3. Select the strongest relation supported and document exclusions.
## Output contractdrill-five-whys
When your agent uses it
Iteratively ask why, evidence-checking each causal step, to move from symptom toward root cause.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
261 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,179 bytes
Read SKILL.md
# drill-five-whys
## Purpose
Iteratively ask why, checking evidence at each causal step, to move from symptom toward root cause.
## Input contract
```yaml
required: [symptom_statement, causal_evidence]
optional: [initial_cause, max_depth]
constraints: [each why answer must explain the preceding statement and cite evidence or uncertainty]
```
## Procedure
1. Normalize the symptom as an observable effect.
2. Ask why the effect occurs and record the proposed cause.
3. Test the cause against evidence before asking the next why.
4. Stop at a controllable root, an evidence boundary, or a documented unresolved branch.drill-root-causes
When your agent uses it
Move from symptoms to causal structure using complementary root-cause representations and causal-validity checks.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
463 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,099 bytesSKILL.mdcore2,099 bytes
Read SKILL.md
# drill-root-causes
## Purpose
Move from symptoms to causal structure using complementary root-cause representations and validity checks.
## Input contract
```yaml
required: [symptoms_or_undesirable_effects]
optional: [evidence, system_boundary, known_causes]
constraints: [each causal edge needs an evidence or assumption label]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `drill-five-whys` to drill repeated whys.
2. You MUST load skill `decompose-ishikawa` to decompose six causal categories.elicit-weights
When your agent uses it
Produce a normalized criterion-weight vector using a selected elicitation method.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
405 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore1,807 bytesSKILL.mdcore1,807 bytes
Read SKILL.md
# elicit-weights
## Purpose
Produce a normalized criterion-weight vector using a caller-selected elicitation method.
## Input contract
```yaml
required: [criteria, elicitation_method, preference_inputs]
optional: [consistency_threshold, pairwise_scale, missing_preference_policy]
constraints: [weights are nonnegative and sum to 1 within declared tolerance]
```
## Procedure
1. Validate criteria and method applicability.
2. Convert preference inputs to a weight vector using the declared method.
3. Compute consistency diagnostics where the method supports them.
4. Return weights, diagnostics, and unresolved preference gaps.enumerate-combinations
When your agent uses it
Construct combinations across dimensions/values without prematurely judging them.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
290 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,519 bytesSKILL.mdcore1,519 bytes
Read SKILL.md
# enumerate-combinations
## Purpose
Construct combinations across declared dimensions and values without prematurely judging them.
## Input contract
```yaml
required: [dimensions, value_sets, combination_policy]
optional: [exclusion_constraints, sampling_limit, random_seed]
constraints: [every emitted combination records its source values]
```
## Procedure
1. Validate dimensions, values, and exclusions.
2. Generate the Cartesian, constrained, or sampled combinations requested.
3. Preserve provenance of each component and mark omitted combinations.
4. Return the neutral combination set for downstream evaluation.enumerate-dimension-values
When your agent uses it
Enumerate meaningful values/levels for a dimension or factor. Mode controls representative, experimental, boundary, pathological, or adversarial coverage.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
643 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore3,185 bytesSKILL.mdcore3,185 bytesSKILL.mdcore3,185 bytesSKILL.mdcore3,185 bytesSKILL.mdcore3,185 bytes
Read SKILL.md
# enumerate-dimension-values
## Purpose
Enumerate meaningful values or levels for a dimension or factor, including representative, experimental, boundary, pathological, or adversarial coverage.
## Input contract
```yaml
required: [dimensions, value_schema, mode]
optional: [ranges, spacing_strategy, domain_constraints, baseline_values]
constraints: [values are typed to the dimension; mode determines representative, experimental, boundary, pathological, or adversarial coverage]
```
enumerate-failure-modes
When your agent uses it
Convert functions/process steps/scenarios into explicit failure modes.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,058 bytes
Read SKILL.md
# enumerate-failure-modes
## Purpose
Convert functions, process steps, or scenarios into explicit failure modes.
## Input contract
```yaml
required: [functions_or_steps, intended_outcomes, operating_conditions]
optional: [failure_history, stakeholders]
constraints: [failure mode must state deviation from intended outcome]
```
## Procedure
1. Decompose functions or steps.
2. Enumerate plausible deviations and affected outcomes.
3. Record causes, effects, detectability, and evidence gaps.
## Output contractenumerate-validator-assumptions
When your agent uses it
Enumerate assumptions embedded in a validator/test/sandbox, including data-generation, measurement, simulator, oracle, metric, initialization, and acceptance assumptions.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,354 bytesSKILL.mdcore1,354 bytes
Read SKILL.md
# enumerate-validator-assumptions
## Purpose
Enumerate assumptions embedded in a validator, benchmark, sandbox, or test.
## Input contract
```yaml
required: [validator_artifact, target_claim]
optional: [data_generation, measurement, simulator, oracle, metric, initialization, acceptance_rule]
constraints: [assumptions must be classified by source and role]
```
## Procedure
1. Inspect data generation, measurement, simulator, oracle, metric, initialization, and acceptance.
2. Record each assumption and its relation to the target.
3. Mark evidence, uncertainty, and potential circularity.
establish-empirical-baseline
When your agent uses it
Establish a fair empirical baseline by inventorying methods, extracting comparable performance, normalizing conditions/compute, checking discrepancies, and estimating progress/headroom.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,291 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytesSKILL.mdcore13,177 bytes
Read SKILL.md
# establish-empirical-baseline
## Purpose
Establish a fair empirical baseline by inventorying methods, extracting comparable performance, normalizing conditions/compute, checking discrepancies, and estimating progress/headroom.
## Input contract
```yaml
required: [method_records, benchmark_or_task, performance_measure]
optional: [historical_series, compute_metadata, condition_schema]
constraints: [comparability fields and source provenance required]
```
estimate-effective-evidence-count
When your agent uses it
Estimate an effective number of independent evidence/reasoning paths after discounting dependence/correlation; report nominal N, dependence structure, and N_eff.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
232 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,176 bytes
Read SKILL.md
# estimate-effective-evidence-count
## Purpose
Estimate independent evidence count after discounting dependence and correlation.
## Input contract
```yaml
required: [evidence_paths, dependence_structure]
optional: [correlation_estimates, nominal_count]
constraints: [dependence assumptions and uncertainty must be explicit]
```
## Procedure
1. Count nominal paths and trace shared dependencies.
2. Assign dependence classes or correlations.
3. Estimate N_eff and sensitivity to dependence assumptions.
## Output contractestimate-performance-headroom
When your agent uses it
Estimate practical/human/theoretical ceilings and remaining performance headroom under stated assumptions.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,432 bytes
Read SKILL.md
# estimate-performance-headroom
## Purpose
Estimate practical, human, or theoretical ceilings and remaining performance headroom under stated assumptions.
## Input contract
```yaml
required: [current_performance, ceiling_reference, metric_schema]
optional: [human_baseline, oracle_bound, task_constraints, uncertainty_model]
constraints: [each ceiling must name its population, conditions, and assumptions]
```
estimate-sample-size
When your agent uses it
Estimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,688 bytesSKILL.mdcore1,688 bytesSKILL.mdcore1,688 bytes
Read SKILL.md
# estimate-sample-size
## Purpose
Estimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.
## Input contract
```yaml
required: [effect_target, uncertainty_model, power_target, design_structure]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
evaluate-compatibility
When your agent uses it
Evaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
523 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,676 bytesSKILL.mdcore2,676 bytesSKILL.mdcore2,676 bytes
Read SKILL.md
# evaluate-compatibility
## Purpose
Evaluate logical, empirical, and normative compatibility of a candidate combination and prune invalid regions.
## Input contract
```yaml
required: [candidate_combination, component_schema, compatibility_rules, evidence]
optional: [matrix, consistency_judgments, feasibility_criteria, novelty_criteria]
constraints: [each incompatibility is tied to an explicit rule or evidence item; preserve distinct logical, empirical, and normative judgments]
```
evaluate-falsifiability
When your agent uses it
Determine what observation would falsify a hypothesis and flag unfalsifiable formulations.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,390 bytes
Read SKILL.md
# evaluate-falsifiability
## Purpose
Evaluate whether a claim or hypothesis exposes observations that could count against it.
## Input contract
```yaml
required: [claim, prediction_set, observation_domain]
optional: [auxiliary_assumptions, measurement_limits]
constraints: [falsifying conditions must be observable within the declared domain]
```
evaluate-necessity-sufficiency
When your agent uses it
Test whether a proposed cause/mechanism is necessary and/or sufficient under controlled counterfactual or intervention comparisons.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
254 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,250 bytes
Read SKILL.md
# evaluate-necessity-sufficiency
## Purpose
Test whether a proposed cause or mechanism is necessary and/or sufficient under controlled counterfactual or intervention comparisons.
## Input contract
```yaml
required: [cause_or_mechanism, outcome, comparison_conditions]
optional: [counterfactual_worlds, intervention_data]
constraints: [necessary and sufficient tests must be reported separately]
```
## Procedure
1. Define removal/absence and presence/intervention contrasts.
2. Compare outcomes under held-fixed conditions.
3. Report necessity, sufficiency, confounds, and uncertainty.
## Output contractevaluate-optionality
When your agent uses it
Evaluate the value of staging, deferral, reversible commitment, and information-gathering options under uncertainty; return decision-relevant option value and trigger conditions.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
331 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,695 bytes
Read SKILL.md
# evaluate-optionality
## Purpose
Evaluate staging, deferral, reversible commitment, and information-gathering options under uncertainty.
## Input contract
```yaml
required: [decision_options, uncertainty_register, time_horizon, consequence_model]
optional: [irreversibility_costs, information_actions, trigger_conditions]
constraints: [each option states timing, reversibility, information gained, and consequence range]
```
## Procedure
1. Represent immediate, deferred, staged, and information-gathering actions on a common timeline.
2. Estimate each action's reversible value, delay cost, information gain, and downside exposure.
3. Identify trigger conditions that would justify advancing, pausing, or abandoning each staged option.
4. Emit an option-value comparison and the conditions under which deferral is preferable to commitment.evaluate-scenario-impact
When your agent uses it
Evaluate a fixed candidate, research path, or portfolio under one explicit scenario using stable criteria and return impact, tradeoffs, and failure triggers.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
358 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,857 bytes
Read SKILL.md
# evaluate-scenario-impact
## Purpose
Evaluate one fixed candidate, path, or portfolio under one explicit scenario.
## Input contract
```yaml
required: [candidate, scenario, evaluation_criteria]
optional: [baseline, metric_definitions, vulnerability_rules]
constraints: [criteria, units, and scenario assumptions remain fixed during evaluation]
```
## Procedure
1. Instantiate the candidate under scenario assumptions.
2. Compute or qualitatively assess each declared criterion.
3. Identify tradeoffs, vulnerabilities, and failure triggers.
4. Return impact evidence and unresolved uncertainties.evaluate-scenario-robustness
When your agent uses it
Aggregate a candidate, strategy, or portfolio across explicit scenarios under a declared robust-decision rule such as worst-case score, minimax regret, maximin, threshold survival, or pivot-trigger analysis.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
404 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,909 bytes
Read SKILL.md
# evaluate-scenario-robustness
## Purpose
Aggregate candidate performance across explicit scenarios under a declared robust-decision rule.
## Input contract
```yaml
required: [candidate_set, scenario_set, criterion_results, robustness_rule]
optional: [regret_definition, survival_thresholds, pivot_triggers]
constraints: [scenario results use common criteria and direction]
```
## Procedure
1. Verify scenario comparability and criterion direction.
2. Apply the supplied rule: worst-case, minimax regret, maximin, survival, or pivot trigger.
3. Expose scenario-specific failures and tradeoffs.
4. Return ranking, rule sensitivity, and pivot conditions.evolve-solution-population
When your agent uses it
Maintain a diverse population of candidate solutions, mutate/recombine variants, select under explicit fitness and novelty criteria, and iterate while preserving useful niches rather than collapsing prematurely to one winner.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
612 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,011 bytesSKILL.mdcore3,011 bytes
Read SKILL.md
# evolve-solution-population
## Purpose
Maintain diverse candidate solutions, mutate/recombine them, select under fitness and novelty criteria, and avoid premature convergence.
## Input contract
```yaml
mode_contracts:
mutation-selection: &evolution_input
required: [initial_solution_population, fitness_criteria]
optional: [mutation_operators, novelty_criteria, iteration_budget]
constraints: [population_members_must_be_comparable_under_declared_criteria]
novelty-preserving-evolution: *evolution_input
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.execute-probe
When your agent uses it
Execute one test/attack and record outcome, evidence, and severity. Tool use is runtime-selected.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,146 bytes
Read SKILL.md
# execute-probe
## Purpose
Execute one test or attack and record outcome, evidence, and severity.
## Input contract
```yaml
required: [probe_spec, target, success_and_failure_conditions]
optional: [tool_context, severity_scale]
constraints: [probe scope and interpretation rule must be fixed before execution]
```
## Procedure
1. Verify target and probe conditions.
2. Run the probe and capture observations.
3. Classify outcome against the predeclared conditions.
execute-research-spec
When your agent uses it
Execute the approved Research Spec phase by phase, producing checkpointed research state and a final summary.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
916 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input Contract
- Execution Protocol
- Checkpoint Contract
- Recovery Protocol
- Output Contract
- Completion Criteria
- Failure and Backtrack
- Boundary
Files
SKILL.mdcore4,568 bytesSKILL.mdcore4,568 bytesSKILL.mdcore4,568 bytesSKILL.mdcore4,568 bytes
Read SKILL.md
# execute-research-spec
## Purpose
Execute the approved Research Spec phase by phase, producing checkpointed research state and a final summary. The execution path is deterministic from the current SpecView and state events.
## Input Contract
```yaml
required: [approved_spec, context_index, phase_context_file]
optional: [latest_checkpoint]
constraints:
- the target Phase must have exactly one context file
- a complete checkpoint is required before a phase can be considered completeexplore-dimensional-space
When your agent uses it
Represent a problem/research space as validated dimensions and values, enumerate compatible combinations, and optionally map occupancy, detect gaps, prioritize regions, or synthesize candidate questions/ideas.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
882 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore4,378 bytesSKILL.mdcore4,378 bytesSKILL.mdcore4,378 bytesSKILL.mdcore4,378 bytesSKILL.mdcore4,378 bytes
Read SKILL.md
# explore-dimensional-space
## Purpose
Represent a problem space as validated dimensions and values, enumerate compatible combinations, map occupancy, detect gaps, and synthesize candidate questions or ideas.
## Input contract
```yaml
mode_contracts:
morphological-generation: &dimensional_input
required: [target_space, dimensions, values]
optional: [coverage_matrix, compatibility_rules, objective]
constraints: [dimension_semantics_and_independence_posture_must_be_declared]
research-space-mapping: *dimensional_input
gap-mapping: *dimensional_input
```
## Execution protocolextract-biological-strategy
When your agent uses it
Extract the causal strategy/mechanism by which a biological analog achieves its function, including boundary conditions and trade-offs.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,410 bytes
Read SKILL.md
# extract-biological-strategy
## Purpose
Extract the causal mechanism, boundary conditions, and trade-offs by which a biological analog achieves its function.
## Input contract
```yaml
required: [biological_analog, function_evidence]
optional: [mechanism_literature, environmental_conditions, tradeoffs]
constraints: [strategy claims must distinguish mechanism from observed outcome]
```
## Procedure
1. Trace the analog's structures, processes, and feedback that produce the function.
2. State boundary conditions, resources, and failure modes.
3. Separate transferable principles from organism-specific implementation details.
## Output contractextract-causal-structure
When your agent uses it
Extract causal structure from source material at requested granularity: individual causal claims, ordered mechanism chains, mediators, assumptions, and stated boundary conditions.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,615 bytesSKILL.mdcore2,615 bytesSKILL.mdcore2,615 bytesSKILL.mdcore2,615 bytesSKILL.mdcore2,615 bytesSKILL.mdcore2,615 bytes
Read SKILL.md
# extract-causal-structure
## Purpose
Extract causal claims, mechanism chains, mediators, assumptions, and boundary conditions at caller-specified granularity.
## Input contract
```yaml
required: [source_material, extraction_granularity, causal_schema]
optional: [theory_description, domain_ontology, evidence_links]
constraints: [preserve direction and scope; distinguish observed association from asserted causation; attach evidence]
```
extract-concepts
When your agent uses it
Extract candidate concepts from evidence with explicit source provenance and precision/recall posture.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytesSKILL.mdcore1,464 bytes
Read SKILL.md
# extract-concepts
## Purpose
Extract domain concepts, definitions, and relation candidates from a source while preserving source wording and scope.
## Input contract
```yaml
required: [source, extraction_scope]
optional: [concept_schema, domain_ontology, relation_cues]
constraints: [each concept requires a source span and an uncertainty state]
```
extract-constructive-movement
When your agent uses it
Convert an initially absurd/destructive provocation into concrete useful directions.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,324 bytes
Read SKILL.md
# extract-constructive-movement
## Purpose
Convert an absurd or destructive provocation into concrete useful directions.
## Input contract
```yaml
required: [provocation, target_problem]
optional: [current_frame, movement_types]
constraints: [each movement must preserve a useful intent while changing the frame]
```
## Procedure
1. Describe what the provocation makes possible, impossible, or newly visible.
2. Extract moment-to-moment, principle, focus-difference, and positive-aspect movements where applicable.
3. Translate selected movements into testable candidate directions.
## Output contractextract-core-conflict
When your agent uses it
Represent a core constraint conflict in an Evaporating-Cloud-like structure with explicit assumptions on every dependency.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
317 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,584 bytesSKILL.mdcore1,584 bytesSKILL.mdcore1,584 bytes
Read SKILL.md
# extract-core-conflict
## Purpose
Represent a core constraint conflict in an Evaporating-Cloud-like structure with explicit assumptions on every dependency.
## Input contract
```yaml
required: [undesirable_effects, constraint_relations, assumption_records]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
extract-empirical-regularity
When your agent uses it
Extract a repeatable empirical pattern from observations, state its support and exceptions, and generalize cautiously without importing an unsupported mechanism.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,565 bytes
Read SKILL.md
# extract-empirical-regularity
## Purpose
Extract a repeatable empirical pattern from records while preserving conditions, exceptions, and uncertainty.
## Input contract
```yaml
required: [observations, variable_schema, condition_schema]
optional: [replication_records, measurement_uncertainty]
constraints: [regularity claims require multiple comparable observations or an explicit single-case limitation]
```
extract-evaluation-protocol
When your agent uses it
Extract evaluation-protocol elements from a source and mark unstated or ambiguous parameters.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
284 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,386 bytesSKILL.mdcore1,386 bytesSKILL.mdcore1,386 bytesSKILL.mdcore1,386 bytes
Read SKILL.md
# extract-evaluation-protocol
## Purpose
Extract evaluation-protocol elements from a source and mark unstated or ambiguous parameters.
## Input contract
```yaml
required: [source_record, protocol_schema]
optional: [supplementary_materials, domain_defaults]
constraints: [extracted values must distinguish stated, inferred, and missing]
```
extract-evidence-record
When your agent uses it
Extract a schema-declared evidence record from a source, including methods, datasets, metrics/results, conditions, limitations, provenance, and explicitly missing/ambiguous fields.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
405 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,014 bytesSKILL.mdcore2,014 bytesSKILL.mdcore2,014 bytes
Read SKILL.md
# extract-evidence-record
## Purpose
Extract a schema-declared evidence record containing methods, data, metrics, results, conditions, limitations, provenance, and explicit missing fields.
## Input contract
```yaml
required: [source, extraction_schema]
optional: [protocol_record, quality_rubric, condition_schema]
constraints: [each extracted value is source-linked and missing or ambiguous fields remain explicit]
```
extract-generic-space
When your agent uses it
Infer the shared abstract relational structure that is common across conceptual-blend input spaces.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
257 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,294 bytesSKILL.mdcore1,294 bytes
Read SKILL.md
# extract-generic-space
## Purpose
Infer the shared abstract relational structure common across conceptual-blend input spaces.
## Input contract
```yaml
required: [input_space_set]
optional: [candidate_relations, blend_goal]
constraints: [generic relations must be present in at least two input spaces]
```
## Procedure
1. Compare roles and relations across the input spaces.
2. Keep only shared structure and mark source-specific attributes.
3. Validate the generic space against the blend goal before projection.
extract-structural-mapping
When your agent uses it
Construct an explicit source↔target mapping over objects, relations, operations, constraints, and invariants for a claimed structural equivalence.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,297 bytesSKILL.mdcore1,297 bytes
Read SKILL.md
# extract-structural-mapping
## Purpose
Construct an explicit source-to-target mapping over objects, relations, operations, constraints, and invariants.
## Input contract
```yaml
required: [source_structure, target_structure, mapping_claim]
optional: [required_objects, required_relations, invariants]
constraints: [mapping must preserve identity and provenance of mapped elements]
```
## Procedure
1. Enumerate source and target elements.
2. Map objects, relations, operations, constraints, and invariants.
3. Mark unmatched, ambiguous, and many-to-one mappings.
falsifiability-audit
When your agent uses it
Gate a hypothesis on falsifiability, operational definition, and boundary conditions; can be entered from any hypothesis-generation path.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
566 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,770 bytesSKILL.mdcore2,770 bytes
Read SKILL.md
# falsifiability-audit
## Purpose
Gate a hypothesis on falsifiability, operational definition, and boundary conditions; can be entered from any hypothesis-generation path.
## Input contract
```yaml
required: [hypothesis, operational_definition, boundary_conditions]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
falsification-first-audit
When your agent uses it
Convert a sharp scientific claim into the cheapest decisive falsification program. Steelman the claim into a precise testable form, specify observations/computations that could break it, execute the most informative probes first, and return only BROKEN, CORROBORATED, or UNFALSIFIABLE rather than a resilience score.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
878 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore3,931 bytesSKILL.mdcore3,931 bytesSKILL.mdcore3,931 bytesSKILL.mdcore3,931 bytesSKILL.mdcore3,931 bytes
Read SKILL.md
# falsification-first-audit
## Purpose
Convert a sharp claim into the cheapest decisive falsification program and return BROKEN, CORROBORATED, or UNFALSIFIABLE.
## Input contract
```yaml
mode_contracts:
sharp-claim: &falsification_input
required: [claim, scope, available_evidence]
optional: [mechanism, candidate_tests]
constraints: [claim_must_expose_observable_consequences_and_boundary_conditions]
truthseeking-debate: *falsification_input
truthseeking-red-team: *falsification_input
```
## Execution protocolfilter-false-gap
When your agent uses it
Distinguish a real knowledge gap from search failure, questions that prior work closes, and intrinsically unanswerable formulations. Prior work that touches a question without closing it leaves the gap open.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
470 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,201 bytes
Read SKILL.md
# filter-false-gap
## Purpose
Distinguish a real knowledge gap from search failure, closed questions, or unanswerable formulations, judging prior work by whether it closes the question rather than by whether it exists.
## Input contract
```yaml
required: [gap_claim, search_record, evidence_scope]
optional: [prior_findings, answerability_constraints]
constraints: [absence claims must be tied to a declared search and scope; a closure verdict cites the work that closes the question]
```
## Procedure
1. Check whether the search covered the declared evidence scope.
2. Compare the claim with prior findings. Prior work closes the question only when it is independently replicated, measures the construct directly, holds across the scope the claim names, and faces no unresolved contrary result; name each condition that fails and the work it applies to.
3. For a region no prior work touches, state why it is empty: unsearched, incoherent as a combination, unmeasurable, infeasible to study, or open.
4. Test whether the formulation is answerable under stated constraints.fmea-risk-analysis
When your agent uses it
Enumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,536 bytesSKILL.mdcore2,536 bytesSKILL.mdcore2,536 bytesSKILL.mdcore2,536 bytesSKILL.mdcore2,536 bytes
Read SKILL.md
# fmea-risk-analysis
## Purpose
Enumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.
## Input contract
```yaml
required: [system_or_process, functions, operating_conditions]
optional: [failure_history, severity_scale, occurrence_scale, detectability_scale]
constraints: [scales and scoring direction must be declared]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `enumerate-failure-modes` to enumerate failure modes. You MUST load skill `build-failure-chain` to construct their propagation chains.
2. You MUST load skill `score-fmea-risk` to score severity, occurrence, detectability, and priority.formulate-hypotheses
When your agent uses it
Generate testable hypotheses from theory, empirical regularity, anomaly, or explicit explanatory competition. Deductive, inductive, abductive, and competing-hypothesis generation are modes; discriminating predictions and comparison are activated in competing mode.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
4,356 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
- Purpose
- When to use / not applicable
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytesSKILL.mdcore20,584 bytes
Read SKILL.md
# formulate-hypotheses
## Purpose
Generate and refine testable hypotheses from a gap, theory, induction, anomaly, or competing explanations.
## When to use / not applicable
Use when a research gap or insight can be stated. Select `deductive`, `inductive`, `abductive`, or `competing-hypotheses`; operationalization may follow any generation mode.
## Input contract
```yaml
mode_contracts:formulate-meta-analysis-scope
When your agent uses it
Instantiate a typed evidence question schema such as PICO/PECO for quantitative synthesis.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
298 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,498 bytes
Read SKILL.md
# formulate-meta-analysis-scope
## Purpose
Instantiate a typed PICO/PECO-style evidence question for quantitative synthesis.
## Input contract
```yaml
required: [research_problem, population_or_exposure, comparator, outcome]
optional: [time_horizon, study_design, effect_measure]
constraints: [estimand, comparator, and outcome units must be explicit]
```
formulate-research-question
When your agent uses it
Convert a hypothesis into a precise research question with fit-for-purpose framework, scope, feasibility, and success criteria.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
598 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,979 bytesSKILL.mdcore2,979 bytes
Read SKILL.md
# formulate-research-question
## Purpose
Convert a hypothesis into a precise research question with fit-for-purpose framework, scope, feasibility, and success criteria.
## Input contract
```yaml
required: [hypothesis_or_gap, candidate_frameworks, feasibility_constraints]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
formulate-top-goal
When your agent uses it
Formalize a research goal as an outcome, desired effect, and explicit constraints.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
297 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,417 bytes
Read SKILL.md
# formulate-top-goal
## Purpose
Formalize a research goal as an outcome, desired effect, and explicit constraints.
## Input contract
```yaml
required: [research_intent]
optional: [actor_profile, constraints, evidence_context]
constraints: [goal wording must identify an observable outcome and relevant boundary conditions]
```
generate-alternative-model
When your agent uses it
Generate a plausible model variant by relaxing, replacing, or generalizing assumptions.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
237 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,188 bytes
Read SKILL.md
# generate-alternative-model
## Purpose
Generate a plausible model variant by relaxing, replacing, or generalizing assumptions.
## Input contract
```yaml
required: [base_model, load_bearing_assumptions]
optional: [observations, model_constraints, variant_operations]
constraints: [each variant names the changed assumption and retained predictions]
```
## Procedure
1. Identify assumptions that constrain the base model.
2. Relax, replace, or generalize one assumption at a time.
3. Re-derive the model structure and compare predictions or implications.
## Output contractgenerate-attack-vector
When your agent uses it
Generate a concrete executable attack/probe against a chosen threat surface.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,030 bytes
Read SKILL.md
# generate-attack-vector
## Purpose
Generate a concrete executable attack or probe against a chosen threat surface.
## Input contract
```yaml
required: [threat_surface, target, attack_constraints]
optional: [access_level, prior_findings]
constraints: [attack must identify trigger, observable, and failure condition]
```
## Procedure
1. Select an exposed surface and attack objective.
2. Specify trigger, steps, observables, and failure interpretation.
3. Rank priority by information value and severity.
## Output contractgenerate-candidate-directions
When your agent uses it
Generate diverse candidate research fields/subfields consistent with current context while permitting deliberate boundary-crossing.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
292 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,549 bytes
Read SKILL.md
# generate-candidate-directions
## Purpose
Generate diverse candidate research fields or subfields consistent with context while permitting deliberate boundary crossing.
## Input contract
```yaml
required: [research_intent, scope_anchor]
optional: [seed_evidence, actor_profile, constraints, neighboring_domains]
constraints: [each candidate must state fit, boundary crossing, and evidence needs]
```
generate-competing-hypotheses
When your agent uses it
Generate mechanism-distinct explanations rather than superficial paraphrases.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
289 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,514 bytes
Read SKILL.md
# generate-competing-hypotheses
## Purpose
Generate distinct, testable hypotheses that explain a target observation or research problem.
## Input contract
```yaml
required: [problem_statement, observations, scope_constraints]
optional: [existing_theories, analogies, anomaly_records]
constraints: [each hypothesis must imply a differentiating prediction or assumption]
```
generate-counterexample
When your agent uses it
Generate a concrete counterexample candidate that satisfies the target claim's stated scope while violating its conclusion or claimed structural property; record whether exclusion would be principled or ad hoc.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
248 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,279 bytes
Read SKILL.md
# generate-counterexample
## Purpose
Generate a counterexample candidate within the target claim scope and record whether exclusion is principled.
## Input contract
```yaml
required: [claim, scope, claimed_conclusion]
optional: [known_cases, construction_rules]
constraints: [candidate must satisfy stated scope before challenging conclusion]
```
## Procedure
1. Identify the claim's necessary commitments.
2. Construct a candidate satisfying scope but violating conclusion.
3. Test the candidate and classify principled versus ad hoc exclusion.
## Output contractgenerate-provocation
When your agent uses it
Generate a deliberate pattern-breaking perturbation: PO, reversal, negation, random stimulus, exaggeration, or distortion.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
330 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,637 bytes
Read SKILL.md
# generate-provocation
## Purpose
Generate a deliberate pattern-breaking perturbation that opens alternative reasoning paths.
## Input contract
```yaml
required: [target_pattern, provocation_mode, boundary_conditions]
optional: [random_stimulus_pool, intensity, safety_constraints]
constraints: [provocation must be traceable to the target pattern]
```
## Procedure
1. Describe the dominant pattern and its protected assumptions.
2. Apply the selected mode: PO, reversal, negation, random stimulus, exaggeration, or distortion.
3. Record the altered elements and generated questions.
4. Return candidate directions without premature selection.generate-subquestions
When your agent uses it
Decompose a research question into MECE subquestions with coverage and independence arguments.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
289 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,464 bytes
Read SKILL.md
# generate-subquestions
## Purpose
Decompose a research question into MECE subquestions with coverage and independence arguments.
## Input contract
```yaml
required: [main_research_question, scope_statement]
optional: [evidence_map, dependency_constraints, desired_granularity]
constraints: [question must be scoped and complex enough to decompose]
```
## Procedure
1. Parse the main question into objects, mechanisms, conditions, and outcomes.
2. Generate candidate subquestions and assign coverage domains.
3. Remove overlap, test independence, and map dependencies.
4. Return the MECE set with unresolved gaps.identify-bottleneck
When your agent uses it
Identify the limiting dimension or dependency currently constraining progress.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,519 bytes
Read SKILL.md
# identify-bottleneck
## Purpose
Identify the limiting dimension or dependency currently constraining progress.
## Input contract
```yaml
required: [goal_state, dependency_or_factor_set, progress_evidence]
optional: [capacity_limits, intervention_history, bottleneck_definition]
constraints: [bottleneck claim requires a limiting relation and evidence]
```
## Procedure
1. Map factors and dependencies to the blocked outcome.
2. Compare capacities, delays, and failure frequencies.
3. Test candidate limits by tracing counterfactual relief or substitution.
4. Return primary bottleneck, alternatives, and evidence gaps.identify-critical-chain
When your agent uses it
Identify the longest/limiting dependency path while accounting for resource contention and convergence points.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,568 bytesSKILL.mdcore1,568 bytesSKILL.mdcore1,568 bytes
Read SKILL.md
# identify-critical-chain
## Purpose
Identify the longest/limiting dependency path while accounting for resource contention and convergence points.
## Input contract
```yaml
required: [dependency_graph, resource_constraints, convergence_points]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
identify-dominant-frame
When your agent uses it
Identify the dominant framing/paradigm or governing variable constraining the current problem representation.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,374 bytes
Read SKILL.md
# identify-dominant-frame
## Purpose
Identify the framing or governing variable constraining the current problem representation.
## Input contract
```yaml
required: [problem_statement, current_representation]
optional: [stakeholder_views, governing_variables, historical_frames]
constraints: [frame claims must be evidenced by repeated language, choices, or exclusions]
```
## Procedure
1. Extract repeated goals, metaphors, variables, and excluded alternatives.
2. Compare stakeholder or historical formulations for frame convergence.
3. Name the dominant frame and the assumptions it makes salient or invisible.
## Output contractidentify-inventive-contradiction
When your agent uses it
Identify paired parameters or requirements where improving one worsens another, and distinguish technical from physical contradictions.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,455 bytes
Read SKILL.md
# identify-inventive-contradiction
## Purpose
Identify paired requirements where improving one worsens another, distinguishing technical from physical contradictions.
## Input contract
```yaml
required: [system_requirements, improvement_target, worsening_effect]
optional: [parameter_set, operating_conditions]
constraints: [both sides must refer to the same design decision or parameter]
```
## Procedure
1. State the desired improvement and the resulting worsening effect.
2. Determine whether distinct system states or one parameter must satisfy opposing properties.
3. Classify technical versus physical contradiction and record the implicated parameters.
identify-load-bearing-factors
When your agent uses it
Identify factors/assumptions/uncertainties whose change most strongly controls the conclusion.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
410 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,113 bytesSKILL.mdcore2,113 bytesSKILL.mdcore2,113 bytesSKILL.mdcore2,113 bytes
Read SKILL.md
# identify-load-bearing-factors
## Purpose
Identify factors or assumptions whose change most strongly controls the conclusion.
## Input contract
```yaml
required: [conclusion, factor_or_assumption_set, perturbation_evidence]
optional: [necessity_sufficiency_results, uncertainty_contributions, critical_path]
constraints: [load-bearing status is tied to observed or reasoned conclusion change; preserve factor identity]
```
identify-obstacles
When your agent uses it
Enumerate obstacles that block a target goal/direction, with type, evidence, and blocking relation.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
337 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,702 bytes
Read SKILL.md
# identify-obstacles
## Purpose
Enumerate obstacles blocking a target goal or direction, with evidence and blocking relations.
## Input contract
```yaml
required: [target_goal, current_state, domain_context]
optional: [timeline, resource_inventory, prior_failures]
constraints: [each obstacle has type, evidence, and blocking relation]
```
## Procedure
1. Compare target requirements with current capabilities and constraints.
2. Enumerate technical, evidential, resource, temporal, and dependency obstacles.
3. Link each obstacle to blocked outcomes and supporting evidence.
4. Return severity, uncertainty, and candidate removal questions.identify-scenario-drivers
When your agent uses it
Identify high-impact/high-uncertainty drivers and rank them for scenario construction.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
312 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,531 bytesSKILL.mdcore1,531 bytesSKILL.mdcore1,531 bytes
Read SKILL.md
# identify-scenario-drivers
## Purpose
Identify high-impact/high-uncertainty drivers and rank them for scenario construction.
## Input contract
```yaml
required: [candidate_drivers, impact_assessments, uncertainty_assessments]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
identify-shared-priors
When your agent uses it
Trace supposedly independent evidence/reasoning paths to shared priors, datasets, models, prompts, framings, assumptions, or upstream sources that induce correlated errors.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,371 bytes
Read SKILL.md
# identify-shared-priors
## Purpose
Trace supposedly independent paths to shared priors, datasets, models, prompts, framings, assumptions, or upstream sources.
## Input contract
```yaml
required: [evidence_paths, provenance_records]
optional: [prompt_records, model_records, upstream_sources]
constraints: [shared dependency identity and path membership must be explicit]
```
## Procedure
1. Inventory each path's inputs and assumptions.
2. Match shared priors, data, models, prompts, framing, and upstream evidence.
3. Produce dependency clusters and unresolved provenance.
identify-theory
When your agent uses it
Identify theories relevant to a gap and characterize their applicability. Evidence acquisition is not prescribed.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,396 bytes
Read SKILL.md
# identify-theory
## Purpose
Identify the theory or theoretical family that best organizes a claim, mechanism, or observed regularity.
## Input contract
```yaml
required: [claim_or_mechanism, construct_definitions, evidence_context]
optional: [candidate_theories, domain_scope]
constraints: [theory identification requires construct and mechanism correspondence]
```
identify-variables
When your agent uses it
Identify relevant variables/factors and annotate functional roles.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
475 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,409 bytesSKILL.mdcore2,409 bytesSKILL.mdcore2,409 bytes
Read SKILL.md
# identify-variables
## Purpose
Identify relevant variables, factors, conditions, and assumptions and annotate their functional roles.
## Input contract
```yaml
required: [artifact_or_system, target_claim_or_outcome]
optional: [causal_claims, domain_schema, candidate_factors]
constraints: [include explicit and implicit factors; each variable has a role, provenance, and suspected importance]
```
instantiate-transfer
When your agent uses it
Turn an abstract transferred principle into a concrete target-domain design/mechanism.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
256 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,297 bytesSKILL.mdcore1,297 bytes
Read SKILL.md
# instantiate-transfer
## Purpose
Turn an abstract transferred principle into a concrete target-domain design or mechanism.
## Input contract
```yaml
required: [abstract_principle, target_domain, target_constraints]
optional: [source_mapping, implementation_components]
constraints: [retain the source principle's causal role while adapting implementation]
```
## Procedure
1. Map each abstract relation to a target component or operation.
2. Specify the concrete mechanism, interfaces, and operating conditions.
3. Check whether the instantiated design preserves the intended function.
## Output contractinventory-reference-items
When your agent uses it
Build a structured inventory of externally established reference items under a parent-specified schema, preserving applicability/status, key attributes, limitations, and provenance. Typical schemas include benchmark or known-solution/method family.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
449 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,387 bytesSKILL.mdcore2,387 bytesSKILL.mdcore2,387 bytesSKILL.mdcore2,387 bytesSKILL.mdcore2,387 bytes
Read SKILL.md
# inventory-reference-items
## Purpose
Build a structured inventory of externally established reference items under a caller-specified schema.
## Input contract
```yaml
required: [reference_items, item_schema, applicability_rules]
optional: [known_solutions, benchmarks, source_scope, status_vocabulary]
constraints: [preserve applicability, status, limitations, key attributes, and provenance for every item]
```
list-undesirable-effects
When your agent uses it
List observable undesirable effects with evidence and severity as starting points for constraint/root-cause analysis.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,576 bytesSKILL.mdcore1,576 bytesSKILL.mdcore1,576 bytes
Read SKILL.md
# list-undesirable-effects
## Purpose
List observable undesirable effects with evidence and severity as starting points for constraint/root-cause analysis.
## Input contract
```yaml
required: [system_observations, effect_evidence, severity_scale]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
map-ablation-components
When your agent uses it
Map system structure into ablatable units, dependencies, legal removal/replacement operations, and expected contribution hypotheses.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
315 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,612 bytesSKILL.mdcore1,612 bytesSKILL.mdcore1,612 bytes
Read SKILL.md
# map-ablation-components
## Purpose
Map system structure into ablatable units, dependencies, legal removal/replacement operations, and expected contribution hypotheses.
## Input contract
```yaml
required: [system_structure, component_dependencies, removal_constraints]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
map-analogy
When your agent uses it
Map source structure/relations/functions to target structure and annotate match quality.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,320 bytesSKILL.mdcore1,320 bytesSKILL.mdcore1,320 bytesSKILL.mdcore1,320 bytes
Read SKILL.md
# map-analogy
## Purpose
Map source structures, relations, or functions to a target and annotate match quality.
## Input contract
```yaml
required: [source_structure, target_structure, mapping_basis]
optional: [source_constraints, target_constraints]
constraints: [mapping basis must specify structural, functional, or relational correspondence]
```
## Procedure
1. Align source and target entities by role rather than label.
2. Map relations and functions, recording one-to-one, many-to-one, and unmatched cases.
3. Rate each correspondence and identify structural gaps requiring validation.
## Output contractmap-coverage-space
When your agent uses it
Map a set of methods/assets/evidence items against a typed problem, capability, condition, or design space to expose redundancy, coverage structure, and the strength of support in each occupied region.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,307 bytes
Read SKILL.md
# map-coverage-space
## Purpose
Map methods, assets, or evidence against a typed problem or capability space to expose redundancy, gaps, and how strongly each occupied region is supported.
## Input contract
```yaml
required: [item_set, coverage_dimensions, target_space]
optional: [strength_scale, applicability_rules, evidence_links]
constraints: [dimension semantics and coverage states are declared]
```
## Procedure
1. Define cells or regions from the supplied dimensions.
2. Assign each item to the regions it occupies, with evidence.
3. Grade every occupied region on the caller's strength scale, or on supported, partial, or unsupported when none is supplied; a region graded below the top names what it lacks.
4. Merge duplicate coverage and identify uncovered and weakly supported regions.map-dependencies
When your agent uses it
Construct a dependency graph and identify cycles, critical paths, and parallelizable branches.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
431 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,180 bytesSKILL.mdcore2,180 bytesSKILL.mdcore2,180 bytesSKILL.mdcore2,180 bytesSKILL.mdcore2,180 bytes
Read SKILL.md
# map-dependencies
## Purpose
Construct a dependency graph and identify cycles, critical paths, and parallelizable branches.
## Input contract
```yaml
required: [items, dependency_evidence, relation_schema]
optional: [criticality_rule, execution_context, candidate_order]
constraints: [the graph contains at least 2 items when the source protocol applies; dependency direction and strength are explicit]
```
map-disagreement
When your agent uses it
Represent where perspectives/arguments agree, disagree, and why.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,060 bytesSKILL.mdcore2,060 bytesSKILL.mdcore2,060 bytesSKILL.mdcore2,060 bytes
Read SKILL.md
# map-disagreement
## Purpose
Represent where perspectives or arguments agree, disagree, and why.
## Input contract
```yaml
required: [perspectives, claims_or_arguments, comparison_dimensions]
optional: [evidence, clustering_rule, convergence_measure]
constraints: [agreement and disagreement are tied to the same proposition and comparison dimension; preserve minority positions]
```
map-patent-white-space
When your agent uses it
Map protected feature combinations and identify technically meaningful, plausibly unprotected white space.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
491 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,486 bytesSKILL.mdcore2,486 bytesSKILL.mdcore2,486 bytesSKILL.mdcore2,486 bytesSKILL.mdcore2,486 bytes
Read SKILL.md
# map-patent-white-space
## Purpose
Map protected feature combinations and identify technically meaningful, plausibly unprotected white space.
## Input contract
```yaml
required: [patent_records, feature_schema, jurisdiction_scope]
optional: [claim_element_maps, family_map, technical_constraints]
constraints: [feature provenance and claim scope must be retained, unprotected means not evidenced as protected within the declared scope]
```
map-productive-polarity
When your agent uses it
Map a persistent two-pole tension where both poles contain value: upsides/downsides of over-focusing each pole, warning signs, and practices that manage the polarity rather than falsely resolving it.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
324 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,485 bytes
Read SKILL.md
# map-productive-polarity
## Purpose
Map a persistent two-pole tension where both poles contain value and require managed balance.
## Input contract
```yaml
required: [polarity_statement, pole_a, pole_b]
optional: [stakeholder_views, warning_signs, current_practices]
constraints: [each pole must have a valued upside and a harmful overuse pattern]
```
## Procedure
1. State the upside and downside of over-focusing each pole.
2. Identify warning signs that the system has over-corrected toward either pole.
3. Map practices that manage the polarity without falsely resolving it.
map-research-landscape
When your agent uses it
Map candidate research fields or subfields, their maturity, competition, entry barriers, and opportunity structure. Evidence/tool acquisition is host-selected.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,765 bytesSKILL.mdcore2,765 bytesSKILL.mdcore2,765 bytesSKILL.mdcore2,765 bytesSKILL.mdcore2,765 bytesSKILL.mdcore2,765 bytes
Read SKILL.md
# map-research-landscape
## Purpose
Map candidate research fields or subfields, maturity, competition, entry barriers, tractability, and opportunity structure.
## Input contract
```yaml
required: [research_intent, scope_anchor]
optional: [actor_profile, seed_evidence, constraints]
constraints: [candidate fields require evidence references and declared comparison dimensions]
```
map-stakeholder-jobs
When your agent uses it
Represent stakeholder jobs, desired outcomes, pains, gains, dependencies, and conflicts relevant to the research target.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
264 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,235 bytes
Read SKILL.md
# map-stakeholder-jobs
## Purpose
Represent stakeholder jobs, desired outcomes, pains, gains, dependencies, and conflicts.
## Input contract
```yaml
required: [stakeholder_set, research_target]
optional: [interviews, observed_behaviors, service_context]
constraints: [jobs must be stated as outcomes sought, not product features]
```
## Procedure
1. Identify functional, social, and emotional jobs for each stakeholder.
2. Record desired outcomes, pains, gains, and dependencies.
3. Map conflicts between jobs and implications for the research target.
## Output contractmap-stakeholder-system
When your agent uses it
Model the research system from stakeholder and boundary perspectives: define what is inside/outside the system, identify stakeholder jobs and stakes, classify salience, and expose conflicts that alter problem framing or feasibility.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
756 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,665 bytesSKILL.mdcore3,665 bytes
Read SKILL.md
# map-stakeholder-system
## Purpose
Model stakeholders and system boundaries, classify salience, and expose conflicts that alter framing or feasibility.
## Input contract
```yaml
mode_contracts:
critical-systems-heuristics: &stakeholder_input
required: [target_system, stakeholder_set]
optional: [boundary_candidates, stakeholder_evidence, contested_interests]
constraints: [inside_outside_boundary_and_stakeholder_claims_must_be_explicit]
jobs-to-be-done: *stakeholder_input
stakeholder-salience: *stakeholder_input
```
## Execution protocolmap-threat-surface
When your agent uses it
Enumerate attackable dimensions of an artifact and rate exposure/accessibility.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
237 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,126 bytes
Read SKILL.md
# map-threat-surface
## Purpose
Enumerate attackable dimensions of an artifact and rate exposure and accessibility.
## Input contract
```yaml
required: [artifact, threat_model, access_context]
optional: [asset_inventory, severity_scale]
constraints: [surface dimensions, access assumptions, and rating anchors must be explicit]
```
## Procedure
1. Inventory components, interfaces, assumptions, and exposed data.
2. Enumerate attackable dimensions and access paths.
3. Rate exposure/accessibility and record untested surfaces.
## Output contractmap-validity-envelope
When your agent uses it
Map where a claim, method, or design remains valid by defining variation axes, probing systematic or adversarial/boundary values, detecting breakpoints, and constructing a multidimensional validity envelope. Critical-case selection is an optional inference-maximizing mode.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
915 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
- Mode branches
Files
SKILL.mdcore4,343 bytesSKILL.mdcore4,343 bytesSKILL.mdcore4,343 bytesSKILL.mdcore4,343 bytes
Read SKILL.md
# map-validity-envelope
## Purpose
Map where a claim, method, or design remains valid by defining axes, probing values, detecting breakpoints, and constructing a multidimensional validity envelope.
## Input contract
```yaml
mode_contracts:
systematic-perturbation: &validity_input
required: [claim_or_method, validity_target, analysis_dimensions]
optional: [baseline_conditions, critical_case_rule, perturbation_budget]
constraints: [axes_values_outcome_measure_and_breakpoint_rule_must_be_explicit]
boundary-value-stress: *validity_input
critical-case: *validity_input
```
## Execution protocolmeasure-portfolio-diversity
When your agent uses it
Quantify portfolio diversity/coverage across declared feature, mechanism, domain, or failure-mode dimensions and expose concentration/niche collapse.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
365 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore1,842 bytesSKILL.mdcore1,842 bytes
Read SKILL.md
# measure-portfolio-diversity
## Purpose
Quantify portfolio diversity and coverage across declared feature, mechanism, domain, or failure-mode dimensions.
## Input contract
```yaml
required: [portfolio, diversity_dimensions, feature_assignments]
optional: [niche_universe, strength_threshold, concentration_measure]
constraints: [niche definitions and distance/overlap rules are explicit]
```
## Procedure
1. Define niches and assign each portfolio member to them.
2. Compute coverage, concentration, and duplication using the supplied measure.
3. Identify empty niches and collapse risks.
4. Return diversity results with sensitivity to assignment uncertainty.mine-patent-landscape
When your agent uses it
Map a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a patent provider.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
633 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytesSKILL.mdcore3,125 bytes
Read SKILL.md
# mine-patent-landscape
## Purpose
Map a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a provider.
## Input contract
```yaml
required: [technical_domain, jurisdiction_scope, patent_records]
optional: [seed_families, assignee_schema, time_window]
constraints: [family identity, classification, assignee, date, and source provenance must be retained]
```
mutate-solution-population
When your agent uses it
Generate controlled variants of a solution population through mutation/recombination operators while retaining lineage and changed dimensions.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,328 bytes
Read SKILL.md
# mutate-solution-population
## Purpose
Generate controlled solution variants through mutation or recombination while retaining lineage and changed dimensions.
## Input contract
```yaml
required: [solution_population, mutation_or_recombination_rules]
optional: [protected_features, variation_budget]
constraints: [each variant records parent lineage and changed dimensions]
```
## Procedure
1. Select parent solutions and dimensions eligible for change.
2. Apply declared mutation or recombination operations.
3. Validate variant coherence and record lineage, novelty, and protected features.
## Output contractnavigate-patent-classification
When your agent uses it
Traverse IPC/CPC-like classification neighborhoods to expand or delimit a technical patent domain.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
259 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytes
Read SKILL.md
# navigate-patent-classification
## Purpose
Traverse IPC/CPC-like classification neighborhoods to expand or delimit a technical patent domain.
## Input contract
```yaml
required: [seed_classifications, technical_domain]
optional: [patent_records, jurisdiction_scope, depth_limit]
constraints: [each expansion or exclusion must cite a classification relation and domain rationale]
```
negate-claim
When your agent uses it
Produce a scope-preserving logical negation of a claim or assumption.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
219 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore970 bytes
Read SKILL.md
# negate-claim
## Purpose
Produce a scope-preserving logical negation of a claim or assumption.
## Input contract
```yaml
required: [claim, scope, quantifiers]
optional: [formalization, assumptions]
constraints: [negation must preserve the original domain and quantifier structure]
```
## Procedure
1. Formalize the claim's subject, predicate, and quantifiers.
2. Negate the claim without changing its scope.
3. Record changed commitments and ambiguities.
## Output contractnormalize-comparison-scale
When your agent uses it
Normalize heterogeneous values onto a declared comparison scale while preserving direction, units, uncertainty, and the transformation rule. The normalized object may be criterion scores, resource budgets, or another comparable quantity.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
357 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,839 bytesSKILL.mdcore1,839 bytes
Read SKILL.md
# normalize-comparison-scale
## Purpose
Normalize heterogeneous values onto a declared comparison scale while preserving direction, units, uncertainty, and transformation rule.
## Input contract
```yaml
required: [value_set, criterion_definitions, normalization_rule]
optional: [bounds, missing_value_policy, uncertainty_model]
constraints: [direction and units are preserved; rule is declared before transformation]
```
## Procedure
1. Validate units, direction, bounds, and missingness.
2. Apply the caller-supplied transformation to each value.
3. Preserve uncertainty and retain original values for audit.
4. Return normalized values and out-of-bound diagnostics.normalize-gap
When your agent uses it
Normalize heterogeneous gap records into a comparable schema before decision operations.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
257 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,303 bytesSKILL.mdcore1,303 bytesSKILL.mdcore1,303 bytesSKILL.mdcore1,303 bytes
Read SKILL.md
# normalize-gap
## Purpose
Normalize heterogeneous research-gap records into a comparable schema before prioritization or decision operations.
## Input contract
```yaml
required: [gap_records, gap_schema]
optional: [evidence_records, domain_taxonomy, coding_rules]
constraints: [normalization preserves source wording, uncertainty, and gap type]
```
operationalize-construct
When your agent uses it
Turn abstract variables/constructs into measurable operational definitions.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
252 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,306 bytes
Read SKILL.md
# operationalize-construct
## Purpose
Translate an abstract construct into observable indicators, measurement rules, and validity checks.
## Input contract
```yaml
required: [construct_definition, target_context]
optional: [theory, candidate_indicators, measurement_constraints]
constraints: [indicators must map to construct facets and declare direction]
```
optimize-design-under-budget
When your agent uses it
Given cost per run and resource budget, choose the most information-efficient feasible design while preserving essential validity constraints.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
323 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,661 bytesSKILL.mdcore1,661 bytesSKILL.mdcore1,661 bytes
Read SKILL.md
# optimize-design-under-budget
## Purpose
Given cost per run and resource budget, choose the most information-efficient feasible design while preserving essential validity constraints.
## Input contract
```yaml
required: [candidate_designs, run_costs, resource_budget, validity_constraints]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
optimize-pareto-frontier
When your agent uses it
Generate a non-dominated frontier for a multi-objective candidate/portfolio problem.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,667 bytes
Read SKILL.md
# optimize-pareto-frontier
## Purpose
Generate a non-dominated frontier for a multi-objective candidate or portfolio problem while preserving objective tradeoffs.
## Input contract
```yaml
required: [candidate_set, objective_schema, constraint_schema, evaluation_records]
optional: [dominance_rule, feasibility_policy, tie_policy]
constraints: [objective directions, scales, feasibility rules, and missing-value handling are explicit]
```
## Procedure
1. Normalize candidate evaluations to the declared objective directions and units without erasing provenance.
2. Remove infeasible candidates according to hard constraints and mark unknown feasibility separately.
3. Compare every feasible candidate pair for dominance; retain candidates not dominated on all objectives.
4. Verify frontier membership, record sacrificed objectives, and emit unresolved comparisons.pairwise-ranking
When your agent uses it
Select informative comparison pairs, execute judgments, update ratings, and audit coherence until ranking resolution is sufficient.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
600 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,978 bytesSKILL.mdcore2,978 bytes
Read SKILL.md
# pairwise-ranking
## Purpose
Select informative comparison pairs, execute judgments, update ratings, and audit coherence until ranking resolution is sufficient.
## Input contract
```yaml
required: [candidate_set, pairwise_judgments, ranking_objective]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
parse-patent-claim
When your agent uses it
Parse independent/dependent claim structure, extract elements, and map claim features to technical functions/domains.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
302 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,482 bytesSKILL.mdcore1,482 bytes
Read SKILL.md
# parse-patent-claim
## Purpose
Parse independent and dependent claim structure, extract elements, and map claim features to technical functions or domains.
## Input contract
```yaml
required: [claim_text, claim_set]
optional: [technical_ontology, family_context, jurisdiction]
constraints: [element boundaries, dependency links, and source spans must be retained]
```
plan-effect-size
When your agent uses it
Choose effect-size estimands and required conversions/calculation rules appropriate to the outcomes and design.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
279 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,423 bytes
Read SKILL.md
# plan-effect-size
## Purpose
Choose effect-size estimands and conversion rules appropriate to outcomes and study design.
## Input contract
```yaml
required: [outcome_schema, study_designs, comparison_target]
optional: [reported_statistics, variance_rules, transformation_options]
constraints: [estimand, direction, and conversion assumptions must be explicit]
```
portfolio-optimization
When your agent uses it
Formalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore4,115 bytesSKILL.mdcore4,115 bytes
Read SKILL.md
# portfolio-optimization
## Purpose
Formalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.
## Input contract
```yaml
required: [candidate_set, objective_vector, resource_constraints, scenario_set]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
predict-competitive-move
When your agent uses it
Predict plausible competitor research moves, timing, and preemption/priority risk with explicit assumptions.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,555 bytesSKILL.mdcore1,555 bytesSKILL.mdcore1,555 bytes
Read SKILL.md
# predict-competitive-move
## Purpose
Predict plausible competitor research moves, timing, and preemption/priority risk with explicit assumptions.
## Input contract
```yaml
required: [competitor_evidence, research_path, time_horizon]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
probe-benchmark-artifact
When your agent uses it
Probe whether benchmark performance can be explained by shortcuts, artifacts, leakage, annotation cues, metric gaming, or non-target capabilities.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,767 bytesSKILL.mdcore1,767 bytes
Read SKILL.md
# probe-benchmark-artifact
## Purpose
Probe whether benchmark performance is explained by shortcuts, artifacts, leakage, annotation cues, metric gaming, or non-target capability.
## Input contract
```yaml
required: [benchmark, performance_records, construct_claim]
optional: [artifact_hypotheses, perturbation_set, contamination_audit]
constraints: [each probe has a target artifact, comparison, and interpretation rule]
```
problem-reframing
When your agent uses it
Change the problem representation when the current frame is limiting: dominant-frame escape, stakeholder/worldview rotation, forced perspective shifts, dialectical/polarity reframing, or abstraction/scope shifts.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
1,173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore5,417 bytesSKILL.mdcore5,417 bytes
Read SKILL.md
# problem-reframing
## Purpose
Change a limiting problem representation through frame escape, perspective rotation, polarity, or abstraction/scope shifts.
## Input contract
```yaml
mode_contracts:
dominant-frame-escape: &reframing_input
required: [problem_statement, current_frame]
optional: [stakeholders, assumptions]
constraints: [each_reframe_must_state_what_changed_and_what_remains_invariant]
perspective-shift: *reframing_input
stakeholder/worldview: *reframing_input
polarity: *reframing_input
abstraction-scope: *reframing_inputproject-future-reality
When your agent uses it
Project the downstream consequences of a proposed constraint-breaking intervention and detect new undesirable effects.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,566 bytesSKILL.mdcore1,566 bytesSKILL.mdcore1,566 bytes
Read SKILL.md
# project-future-reality
## Purpose
Project the downstream consequences of a proposed constraint-breaking intervention and detect new undesirable effects.
## Input contract
```yaml
required: [intervention, causal_model, undesirable_effects]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
propagate-uncertainty
When your agent uses it
Propagate input/parameter uncertainty through a model or reasoning chain to estimate output distributions, tail behavior, and uncertainty contributions.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,373 bytes
Read SKILL.md
# propagate-uncertainty
## Purpose
Propagate input uncertainty through a model or reasoning chain to estimate output distributions, tails, and contributions.
## Input contract
```yaml
required: [model, uncertain_inputs, output_variables]
optional: [sampling_plan, dependency_structure, tail_metrics]
constraints: [input distributions, dependencies, and sampling method must be declared]
```
## Procedure
1. Represent each uncertain input with its distribution and dependencies.
2. Sample or propagate the inputs through the model.
3. Summarize output distributions, tail behavior, and dominant uncertainty contributors.
## Output contractquantify-information-value
When your agent uses it
Estimate the value of resolving uncertainty (e.g., EVPI/EVSI or qualitative equivalent) to prioritize which unknowns justify further evidence or experiments.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,403 bytes
Read SKILL.md
# quantify-information-value
## Purpose
Estimate the value of resolving an uncertainty to prioritize evidence or experiments.
## Input contract
```yaml
required: [decision_problem, uncertain_variables, decision_options]
optional: [probability_model, utility_model, evidence_costs]
constraints: [value estimate must state decision consequences and uncertainty assumptions]
```
## Procedure
1. Define current uncertainty and decision consequences.
2. Estimate value under perfect or sample information, or state a qualitative equivalent.
3. Compare information value with acquisition or experiment cost.
4. Rank unknowns for follow-up.quantify-resource-gap
When your agent uses it
Quantify resource demand, available supply, gap, severity, and uncertainty for a research/experiment plan.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
312 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,534 bytesSKILL.mdcore1,534 bytesSKILL.mdcore1,534 bytes
Read SKILL.md
# quantify-resource-gap
## Purpose
Quantify resource demand, available supply, gap, severity, and uncertainty for a research/experiment plan.
## Input contract
```yaml
required: [resource_demand, resource_supply, plan_scope]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
rank-candidates
When your agent uses it
Rank, classify, screen, or select typed candidates under explicit criteria and supplied hard constraints. Object schema and decision mode are parameters; pairwise and portfolio cases may jump to dedicated tactics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
3,947 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytesSKILL.mdcore16,512 bytes
Read SKILL.md
# rank-candidates
## Purpose
Rank, classify, screen, or select typed candidates under explicit criteria and hard constraints.
## Input contract
```yaml
mode_contracts:
gap-prioritization: &rank_input
required: [candidates, criteria, decision_rule]
optional: [weights, evidence, hard_constraints, object_schema]
constraints: [criterion_direction_and_missing_value_policy_must_be_explicit]reductio-counterexample-analysis
When your agent uses it
Negate claims, derive consequences, search contradictions/counterexamples, then refine scope rather than merely defend the original wording.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
455 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,160 bytesSKILL.mdcore2,160 bytesSKILL.mdcore2,160 bytesSKILL.mdcore2,160 bytesSKILL.mdcore2,160 bytes
Read SKILL.md
# reductio-counterexample-analysis
## Purpose
Negate claims, derive consequences, detect contradictions and counterexamples, then refine scope.
## Input contract
```yaml
required: [claim, scope, supporting_reasoning]
optional: [known_counterexamples, boundary_conditions]
constraints: [negation must preserve the stated scope]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `negate-claim` to negate the claim. You MUST load skill `derive-consequences` to derive the consequences.
2. You MUST load skill `detect-contradiction` to detect contradictions. You MUST load skill `generate-counterexample` to generate counterexamples.refine-claim
When your agent uses it
Repair a claim via scope narrowing, lemma incorporation, or decomposition while preserving explanatory power.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
229 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,081 bytes
Read SKILL.md
# refine-claim
## Purpose
Repair a claim by narrowing scope, adding a lemma, or decomposing it while preserving explanatory power.
## Input contract
```yaml
required: [claim, failure_or_counterexample, supporting_evidence]
optional: [scope_options, mechanism]
constraints: [every repair must state what was narrowed or added]
```
## Procedure
1. Identify the failed commitment.
2. Generate scope, lemma, or decomposition repairs.
3. Select a repair and record retained explanatory content.
## Output contractrepresent-mechanism-edge
When your agent uses it
Represent a directed mechanism edge with pathway, sign/direction, assumptions, falsifier, strength, and evidence provenance.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,832 bytesSKILL.mdcore1,832 bytesSKILL.mdcore1,832 bytesSKILL.mdcore1,832 bytes
Read SKILL.md
# represent-mechanism-edge
## Purpose
Represent a directed mechanism edge with pathway, sign, assumptions, falsifier, strength, and evidence provenance.
## Input contract
```yaml
required: [source_entity, target_entity, mechanism_pathway, direction, evidence_register]
optional: [edge_type, strength_scale, assumptions, falsifier]
constraints: [source and target are typed; direction, pathway, evidence, and falsifier are explicit]
```
## Procedure
1. Type the source and target entities and select the relation/edge type.
2. State the mechanism pathway and direction, including enabling conditions and assumptions.
3. Attach supporting and contradicting evidence, assign strength on the declared scale, and define a falsifier.
4. Emit the edge record with provenance and unresolved mechanism questions.research-catalog
When your agent uses it
This is the v4 capability menu. It indexes exactly 51 tactics in 10 families and tells the caller when each tactic is useful.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
1,824 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input Contract
- Execution Protocol
- Tactic Index
- Output Contract
- Completion Criteria
- Failure and Backtrack
- Boundary
Files
SKILL.mdcore8,307 bytesSKILL.mdcore8,307 bytes
Read SKILL.md
# research-catalog
## Purpose
This is the v4 capability menu. It indexes exactly 51 tactics in 10 families and tells the caller when each tactic is useful. It does not list SOPs. A selected tactic owns its SOP calls through `You MUST load skill ...` instructions in the tactic body.
## Input Contract
```yaml
required: [confirmed_north_star, research_brief]
optional: [current_spec_view, state_slice, constraints]
constraints:
- return tactic cards, not SOP cards
- preserve the tactic id exactly as listedresolve-inventive-contradiction
When your agent uses it
Turn a design or research contradiction into targeted transformations using inventive-principle and separation reasoning, then evaluate whether the transformed configuration resolves the contradiction without creating a worse one.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
730 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,682 bytesSKILL.mdcore3,682 bytes
Read SKILL.md
# resolve-inventive-contradiction
## Purpose
Turn a technical or physical contradiction into targeted transformations and test whether the contradiction is resolved without creating a worse one.
## Input contract
```yaml
mode_contracts:
technical-contradiction: &contradiction_input
required: [contradiction_statement, conflicting_requirements, system_components]
optional: [operating_conditions, target_metrics, known_principles]
constraints: [improvement_and_worsening_parameters_must_be_explicit]
physical-contradiction: *contradiction_input
separation: *contradiction_input
```
## Execution protocolrobustness-analysis
When your agent uses it
Generate plausible model variants and test whether conclusions converge across assumption/model choices.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
449 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,250 bytesSKILL.mdcore2,250 bytes
Read SKILL.md
# robustness-analysis
## Purpose
Generate plausible model variants and test whether conclusions converge across assumptions and model choices.
## Input contract
```yaml
required: [base_model, conclusion, load_bearing_assumptions]
optional: [evidence, alternative_models, sensitivity_dimensions]
constraints: [variants must preserve the declared target question]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `surface-assumptions` to surface assumptions.
2. You MUST load skill `generate-alternative-model` to generate plausible alternatives.rotate-perspective
When your agent uses it
Apply one perspective at a time to reinterpret the same target while holding the underlying evidence/object fixed; record changed assumptions, objectives, risks, and opportunities.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
311 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,633 bytes
Read SKILL.md
# rotate-perspective
## Purpose
Apply one perspective at a time to reinterpret a fixed target while holding evidence constant.
## Input contract
```yaml
required: [target_object, perspective_sequence, fixed_evidence]
optional: [objective_map, risk_taxonomy, opportunity_taxonomy]
constraints: [only perspective assumptions/objectives may change between passes]
```
## Procedure
1. Freeze target and evidence references.
2. Apply the first perspective and record assumptions, risks, and opportunities.
3. Reset to the frozen target and repeat for each remaining perspective.
4. Compare changed interpretations and retain provenance.run-convergence-round
When your agent uses it
Run one structured revision round that updates arguments/evidence rather than merely averaging opinions.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
373 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,040 bytesSKILL.mdcore2,040 bytes
Read SKILL.md
# run-convergence-round
## Purpose
Run one structured revision round that updates arguments and evidence rather than merely averaging opinions.
## Input contract
```yaml
required: [current_state, participant_judgments, revision_prompt, convergence_rule]
optional: [prior_rounds, dissent_policy, stopping_rule]
constraints: [each participant receives the same state snapshot; revisions cite changed evidence or reasoning]
```
## Procedure
1. Freeze the current claims, evidence, disagreements, and round objective.
2. Collect independent judgments or critiques before distributing peer summaries.
3. Distribute the structured feedback, request revisions, and record what changed or remained disputed.
4. Measure convergence, preserve dissent, and return the next state plus a continue/stop recommendation.scope-domain
When your agent uses it
Define ontology/model scope, inclusion boundaries, granularity, and intended use before structural extraction.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,637 bytes
Read SKILL.md
# scope-domain
## Purpose
Define ontology or model scope, inclusion boundaries, granularity, and intended use before structural extraction.
## Input contract
```yaml
required: [domain_question, seed_concepts, intended_use]
optional: [source_corpus, granularity_target, exclusion_rules, resource_budget]
constraints: [scope boundaries, inclusion criteria, granularity, and intended use are explicit]
```
## Procedure
1. State the domain question, seed concepts, intended users, and decisions the model must support.
2. Set inclusion/exclusion boundaries and the target granularity for entities and relations.
3. Test boundary examples, record out-of-scope items, and freeze the initial scope ledger.
4. Emit the scoped domain specification and a trigger for reopening it.score-fmea-risk
When your agent uses it
Score severity, occurrence, detectability, and derive action priority for a failure mode.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
345 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,713 bytesSKILL.mdcore1,713 bytes
Read SKILL.md
# score-fmea-risk
## Purpose
Score severity, occurrence, detectability, and derive action priority for a failure mode.
## Input contract
```yaml
required: [failure_mode, severity_scale, occurrence_scale, detectability_scale]
optional: [evidence, priority_rule]
constraints: [scale anchors and direction must be declared before scoring]
```
## Procedure
1. Score severity, occurrence, and detectability against anchored scales.
2. Derive action priority using the declared rule.
3. Record evidence, uncertainty, and rationale for each score.
## Output contractscore-object
When your agent uses it
Score a typed object against an explicit rubric with evidence, uncertainty, and rationale. The parent tactic supplies the object schema and rubric (candidate, gap, claim, obstacle, etc.).
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,537 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Verbatim source criteria excerpts
- Preserved source criteria ledger
Files
SKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytesSKILL.mdcore6,634 bytes
Read SKILL.md
# score-object
## Purpose
Score one typed object against a caller-supplied rubric, attaching evidence, uncertainty, and rationale without inventing object-specific criteria.
## Input contract
```yaml
required: [object, object_schema, rubric, evidence, uncertainty_policy]
optional: [weights, aggregation_rule, missing_value_policy, score_scale, provenance]
constraints: [the parent tactic supplies the object schema and rubric; every dimension has an explicit scale and rationale requirement; evidence and uncertainty are attached per dimension]
```
screen-evidence-multistage
When your agent uses it
Apply explicit staged inclusion/exclusion screening (title/abstract/full evidence or equivalent) with reasons and auditability.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,424 bytes
Read SKILL.md
# screen-evidence-multistage
## Purpose
Apply explicit staged inclusion and exclusion screening with reasons and an auditable flow.
## Input contract
```yaml
required: [candidate_records, inclusion_rules, exclusion_reasons]
optional: [title_abstract_fields, full_text_fields, duplicate_rules]
constraints: [each stage records in/out counts and a primary exclusion reason]
```
search-minimal-flip
When your agent uses it
Search for the smallest change to variables/assumptions/conditions that flips a target conclusion, decision, or causal claim.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
248 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,205 bytes
Read SKILL.md
# search-minimal-flip
## Purpose
Search for the smallest change to variables, assumptions, or conditions that flips a target conclusion.
## Input contract
```yaml
required: [target_conclusion, variables_or_assumptions, baseline_state]
optional: [distance_metric, constraints]
constraints: [flip criterion and change metric must be explicit]
```
## Procedure
1. Define baseline conclusion and permitted changes.
2. Enumerate increasingly small candidate changes.
3. Test the first valid flip and verify minimality.
## Output contractselect-critical-case
When your agent uses it
Select most-likely, least-likely, or otherwise inference-maximizing cases that can decisively support/refute a claim under explicit case-selection logic.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
260 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,213 bytes
Read SKILL.md
# select-critical-case
## Purpose
Select most-likely, least-likely, or otherwise inference-maximizing cases that can decisively support or refute a claim.
## Input contract
```yaml
required: [claim, case_universe, selection_logic]
optional: [likelihood_model, boundary_conditions]
constraints: [case selection rule and inference purpose must be explicit]
```
## Procedure
1. Define the eligible case universe and selection objective.
2. Rank cases under the declared logic.
3. Select and justify the critical case, including excluded cases.
## Output contractselect-experimental-baseline
When your agent uses it
Select fair SOTA/simple/oracle/control baselines with provenance and rationale matched to the experimental claim.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
315 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,577 bytesSKILL.mdcore1,577 bytesSKILL.mdcore1,577 bytes
Read SKILL.md
# select-experimental-baseline
## Purpose
Select fair SOTA/simple/oracle/control baselines with provenance and rationale matched to the experimental claim.
## Input contract
```yaml
required: [experimental_claim, candidate_baselines, protocol_context]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
select-from-frontier
When your agent uses it
Select a preferred frontier point/portfolio and state the sacrificed alternatives/tradeoffs.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
324 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,634 bytes
Read SKILL.md
# select-from-frontier
## Purpose
Select a preferred point or portfolio from a Pareto frontier and state the sacrificed alternatives and tradeoffs.
## Input contract
```yaml
required: [pareto_frontier, preference_policy, objective_schema, decision_context]
optional: [tie_breaker, stakeholder_weights, robustness_report]
constraints: [preference direction and acceptable sacrifice bounds are explicit]
```
## Procedure
1. Confirm that each selectable point is feasible and that frontier membership is current.
2. Apply the declared preference policy or tie-breaker to frontier points, preserving objective values.
3. Record the selected point, nearest alternatives, sacrificed objectives, and sensitivity to preference changes.
4. Emit the selection rationale and a re-open trigger if the preference or evidence changes.select-inventive-principle
When your agent uses it
Select one or more inventive principles appropriate to a contradiction or transformation objective and state why each principle applies.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore2,681 bytes
Read SKILL.md
# select-inventive-principle
## Purpose
Select TRIZ inventive principles appropriate to a contradiction or transformation objective and state why each applies.
## Input contract
```yaml
required: [contradiction_statement, improvement_parameter, worsening_parameter]
optional: [system_components, operating_conditions, candidate_principles]
constraints: [selection must cite the contradiction and a concrete transformation rationale]
```
## Procedure
1. Normalize the contradiction and identify the improving and worsening parameters.
2. Consider the full 40-principle TRIZ vocabulary individually: 1 Segmentation; 2 Taking out; 3 Local quality; 4 Asymmetry; 5 Merging; 6 Universality; 7 Nested doll; 8 Counterweight; 9 Preliminary anti-action; 10 Preliminary action; 11 Beforehand cushioning; 12 Equipotentiality; 13 The other way round; 14 Spheroidality/curvature; 15 Dynamics; 16 Partial or excessive action; 17 Another dimension; 18 Mechanical vibration; 19 Periodic action; 20 Continuity of useful action; 21 Skipping; 22 Blessing in disguise; 23 Feedback; 24 Mediator; 25 Self-service; 26 Copying; 27 Cheap short-living objects; 28 Mechanics substitution; 29 Pneumatics/hydraulics; 30 Flexible shells/thin films; 31 Porous materials; 32 Color changes; 33 Homogeneity; 34 Discarding and recovering; 35 Parameter changes; 36 Phase transitions; 37 Thermal expansion; 38 Strong oxidants; 39 Inert atmosphere; 40 Composite materials.
3. For each principle, mark applicable, rejected, or not testable and state the contradiction-specific reason.
4. Rank applicable principles and pass the selected set to transformation.select-next-pair
When your agent uses it
Select the next comparison pair to maximize expected information gain.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
318 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,633 bytes
Read SKILL.md
# select-next-pair
## Purpose
Select the next comparison pair to maximize expected information gain while respecting unresolved uncertainty and coverage.
## Input contract
```yaml
required: [candidate_set, current_ratings, uncertainty_matrix, comparison_budget]
optional: [pair_history, exploration_policy, exclusion_constraints]
constraints: [candidate IDs are stable; expected information gain uses the declared model and available evidence]
```
## Procedure
1. Enumerate eligible unjudged pairs and compute their current uncertainty and decision relevance.
2. Estimate expected information gain under the declared comparison model, including the value of resolving a tie or cycle.
3. Exclude pairs blocked by scope or data constraints, then select the highest-value eligible pair.
4. Return the selected pair, rationale, alternatives considered, and the budget impact.select-seed-evidence
When your agent uses it
Select and rank high-information seed sources for iterative evidence expansion using quality, recency, relevance, and network position.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
309 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,574 bytesSKILL.mdcore1,574 bytesSKILL.mdcore1,574 bytes
Read SKILL.md
# select-seed-evidence
## Purpose
Select and rank high-information seed sources for iterative evidence expansion using quality, recency, relevance, and network position.
## Input contract
```yaml
required: [candidate_sources, research_question, selection_criteria]
optional: [citation_graph, quality_assessments, recency_window]
constraints: [rank rationale and source independence must be explicit]
```
select-solution-variants
When your agent uses it
Select candidate variants under fitness, novelty, constraint, and diversity criteria while avoiding premature population collapse.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
242 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,212 bytes
Read SKILL.md
# select-solution-variants
## Purpose
Select candidate variants under fitness, novelty, constraint, and diversity criteria without premature collapse.
## Input contract
```yaml
required: [variant_population, selection_criteria]
optional: [hard_constraints, diversity_target, protected_niches]
constraints: [criteria weights or vetoes must be explicit]
```
## Procedure
1. Remove variants violating hard constraints.
2. Score fitness, novelty, and diversity for the eligible set.
3. Select a portfolio and record excluded variants and reasons.
## Output contractselect-statistical-method
When your agent uses it
Select statistical inference/estimation method from design, distribution, sample size, pairing, multiplicity, and decision objective.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
357 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,784 bytesSKILL.mdcore1,784 bytesSKILL.mdcore1,784 bytes
Read SKILL.md
# select-statistical-method
## Purpose
Select statistical inference/estimation method from design, distribution, sample size, pairing, multiplicity, and decision objective.
## Input contract
```yaml
required: [design_structure, outcome_type, sample_size, decision_objective]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
sensitivity-analysis
When your agent uses it
Quantify which parameters, assumptions, interactions, or uncertainties dominate the conclusion; select Morris/Sobol/perturbation/Monte-Carlo as modes.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
868 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore4,265 bytesSKILL.mdcore4,265 bytes
Read SKILL.md
# sensitivity-analysis
## Purpose
Quantify which parameters, assumptions, interactions, or uncertainties dominate a conclusion.
## Input contract
```yaml
mode_contracts:
Morris: &sensitivity_input
required: [model_or_reasoning_chain, uncertain_parameters, conclusion_metric]
optional: [input_distributions, perturbation_bounds, decision_options]
constraints: [ranges_and_dependencies_must_be_declared]
Sobol: *sensitivity_input
perturbation: *sensitivity_input
Monte-Carlo: *sensitivity_input
```sequence-work
When your agent uses it
Topologically sequence dependent work while prioritizing fail-fast/high-risk branches.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
274 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,367 bytes
Read SKILL.md
# sequence-work
## Purpose
Topologically sequence dependent work while prioritizing fail-fast and high-risk branches.
## Input contract
```yaml
required: [work_items, dependency_graph, prioritization_policy]
optional: [resource_limits, risk_scores, parallelism_rules]
constraints: [dependencies must be acyclic or cycles explicitly reported]
```
## Procedure
1. Validate nodes and dependency edges.
2. Detect cycles and compute available roots.
3. Rank ready items by fail-fast, risk, and policy priorities.
4. Emit ordered batches and parallelizable branches.set-threshold
When your agent uses it
Define a justified minimum acceptable threshold for each non-compensatory criterion.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
421 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,136 bytesSKILL.mdcore2,136 bytesSKILL.mdcore2,136 bytesSKILL.mdcore2,136 bytes
Read SKILL.md
# set-threshold
## Purpose
Define a justified minimum acceptable threshold for each non-compensatory criterion.
## Input contract
```yaml
required: [criteria, value_domains, decision_context, evidence]
optional: [baseline_distribution, veto_policy, stakeholder_preferences]
constraints: [each threshold lies in the criterion's actual value domain and has an explicit rationale]
```
sharpen-falsifiable-claim
When your agent uses it
Steelman a claim into its strongest precise, bounded, testable form while making hidden quantifiers, scope, mechanisms, and commitments explicit.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
274 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,311 bytes
Read SKILL.md
# sharpen-falsifiable-claim
## Purpose
Steelman a claim into a precise, bounded, testable form with explicit quantifiers, scope, mechanisms, and commitments.
## Input contract
```yaml
required: [claim, context, available_evidence]
optional: [mechanism, boundary_conditions]
constraints: [strengthening may not add unsupported commitments]
```
## Procedure
1. Expose hidden quantifiers, variables, mechanisms, and boundaries.
2. Remove ambiguity while preserving the strongest evidence-supported meaning.
3. State observable consequences and candidate falsifiers.
simulate-emergent-properties
When your agent uses it
Project selected structures into a candidate blend and reason through properties, affordances, contradictions, or mechanisms that emerge only in the blend.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,401 bytesSKILL.mdcore1,401 bytesSKILL.mdcore1,401 bytesSKILL.mdcore1,401 bytesSKILL.mdcore1,401 bytesSKILL.mdcore1,401 bytes
Read SKILL.md
# simulate-emergent-properties
## Purpose
Project selected structures into a blend and identify properties, affordances, contradictions, or mechanisms absent from either source alone.
## Input contract
```yaml
required: [selected_structures, blend_projection]
optional: [source_properties, compatibility_constraints, simulation_assumptions]
constraints: [emergence claim must specify the source properties it combines]
```
## Procedure
1. Project selected relations into the blended configuration.
2. Derive candidate interactions and properties of the blend.
3. Compare each property with the source spaces and flag genuinely emergent effects.
## Output contractspecify-boundaries
When your agent uses it
State applicability assumptions, scope, and known boundary conditions.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
242 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,223 bytes
Read SKILL.md
# specify-boundaries
## Purpose
Specify the population, system, temporal, and conceptual boundaries within which a claim or study is intended to hold.
## Input contract
```yaml
required: [claim_or_question, target_context]
optional: [known_limits, adjacent_domains, time_window]
constraints: [each boundary must be observable or operationally enforceable]
```
specify-execution-environment
When your agent uses it
Specify environment variables that materially affect interpretation or reproducibility: hardware, software, data, configuration, and versioning.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,663 bytesSKILL.mdcore1,663 bytesSKILL.mdcore1,663 bytes
Read SKILL.md
# specify-execution-environment
## Purpose
Specify environment variables that materially affect interpretation or reproducibility: hardware, software, data, configuration, and versioning.
## Input contract
```yaml
required: [hardware_context, software_context, data_context, configuration_context]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
specify-metrics
When your agent uses it
Define primary/secondary metrics, estimands, directionality, uncertainty reporting, and decision thresholds before analysis.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
335 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,661 bytesSKILL.mdcore1,661 bytesSKILL.mdcore1,661 bytes
Read SKILL.md
# specify-metrics
## Purpose
Define primary/secondary metrics, estimands, directionality, uncertainty reporting, and decision thresholds before analysis.
## Input contract
```yaml
required: [estimand, outcome_schema, decision_thresholds]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
specify-relationship
When your agent uses it
Specify direction, functional form, and theoretical basis of relationships among variables.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
254 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,324 bytes
Read SKILL.md
# specify-relationship
## Purpose
Specify the direction, type, and conditions of a relationship among constructs or variables.
## Input contract
```yaml
required: [variables, relationship_claim, observation_context]
optional: [theory, candidate_moderators, causal_assumptions]
constraints: [relationship type and direction must be distinguished from association strength]
```
specify-reproducibility-protocol
When your agent uses it
Define exact/statistical/conceptual reproduction target and the controls needed to test it.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
323 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,571 bytesSKILL.mdcore1,571 bytesSKILL.mdcore1,571 bytes
Read SKILL.md
# specify-reproducibility-protocol
## Purpose
Define exact/statistical/conceptual reproduction target and the controls needed to test it.
## Input contract
```yaml
required: [reproducibility_target, experiment_specification, available_controls]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
statistical-testing
When your agent uses it
Apply the pre-declared statistical/estimation procedure and report effect size, uncertainty, model checks, and decision-relevant interpretation.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
341 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,732 bytesSKILL.mdcore1,732 bytesSKILL.mdcore1,732 bytes
Read SKILL.md
# statistical-testing
## Purpose
Apply the pre-declared statistical/estimation procedure and report effect size, uncertainty, model checks, and decision-relevant interpretation.
## Input contract
```yaml
required: [predeclared_analysis_plan, observations, comparison_structure]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
structural-transformation
When your agent uses it
Decompose a system and apply component/function transformations such as remove, substitute, combine, redistribute, divide, or reverse.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
534 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,714 bytesSKILL.mdcore2,714 bytes
Read SKILL.md
# structural-transformation
## Purpose
Decompose a system and apply explicit SCAMPER structural/function transformations to generate and test alternatives.
## Input contract
```yaml
required: [system_or_design, transformation_target]
optional: [component_inventory, constraints, operator_sequence]
constraints: [operator and affected component must be named for every variant]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `decompose-components` to decompose components and functions.
2. You MUST load skill `transform-component` to apply exactly named SCAMPER operators: Substitute, Combine, Adapt, Modify (including magnify/minify variants), Put to another use, Eliminate, Reverse (including rearrange variants).structured-consensus
When your agent uses it
Map disagreement, iterate evidence/argument refinement, and terminate with an output contract containing stable consensus, unresolved disagreements, confidence/probabilities, and threshold/stop rationale.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore3,054 bytesSKILL.mdcore3,054 bytes
Read SKILL.md
# structured-consensus
## Purpose
Map disagreement, iterate evidence/argument refinement, and terminate with an output contract containing stable consensus, unresolved disagreements, confidence/probabilities, and threshold/stop rationale.
## Input contract
```yaml
required: [judgment_records, evidence_records, stopping_rule]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
```
structured-red-team
When your agent uses it
Map attack surfaces, generate attack vectors, execute probes, and aggregate weaknesses into a resilience picture.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
540 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytesSKILL.mdcore2,649 bytes
Read SKILL.md
# structured-red-team
## Purpose
Map attack surfaces, generate attack vectors, execute probes, and aggregate weaknesses into a resilience picture.
## Input contract
```yaml
required: [artifact, threat_model, probe_scope]
optional: [access_assumptions, severity_scale]
constraints: [attack surface and probe authority must be explicit]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `map-threat-surface` to map attackable dimensions and exposure.
2. You MUST load skill `generate-attack-vector` to generate concrete attack vectors.surface-assumptions
When your agent uses it
Enumerate explicit and implicit assumptions in a claim, model, method, decision, or design.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
480 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,386 bytesSKILL.mdcore2,386 bytesSKILL.mdcore2,386 bytes
Read SKILL.md
# surface-assumptions
## Purpose
Enumerate explicit and implicit assumptions in a claim, model, method, decision, or design and expose their evidential status.
## Input contract
```yaml
required: [artifact, claim_or_decision, context]
optional: [causal_claims, evidence, stakeholder_views, assumption_taxonomy]
constraints: [separate explicit from implicit assumptions; preserve the artifact's wording; attach evidence strength and criticality to each assumption]
```
synthesize-field-panorama
When your agent uses it
Summarize candidate fields by maturity, competition, entry barrier, tractability, and publication/opportunity structure.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
302 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,561 bytes
Read SKILL.md
# synthesize-field-panorama
## Purpose
Summarize candidate fields by maturity, competition, entry barrier, tractability, and opportunity structure.
## Input contract
```yaml
required: [candidate_fields, evidence_records, comparison_dimensions]
optional: [actor_profile, constraints, time_window]
constraints: [each dimension requires supporting evidence or an explicit missing marker]
```
synthesize-idea
When your agent uses it
Integrate generated fragments into a coherent candidate with mechanism, provenance, and next-test hooks.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
300 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,413 bytesSKILL.mdcore1,413 bytes
Read SKILL.md
# synthesize-idea
## Purpose
Integrate generated fragments into a coherent candidate with mechanism, provenance, and next-test hooks.
## Input contract
```yaml
required: [idea_fragments, target_problem]
optional: [mechanism_evidence, constraints, candidate_relations]
constraints: [candidate must state function, mechanism, assumptions, and unresolved risks]
```
## Procedure
1. Cluster compatible fragments around a target function.
2. Compose a candidate mechanism and identify required assumptions.
3. Attach provenance and define the next discriminating test or evidence request.
## Output contractsynthesize-literature-evidence
When your agent uses it
Build a reproducible literature evidence base. Scoping, systematic, deep, narrative, and snowball are execution modes selected from intent and budget, not separate strategy nodes.
What it loads into context
Frontmatter
46 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
- Purpose
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore8,295 bytesSKILL.mdcore8,295 bytesSKILL.mdcore8,295 bytesSKILL.mdcore8,295 bytesSKILL.mdcore8,295 bytesSKILL.mdcore8,295 bytes
Read SKILL.md
# synthesize-literature-evidence
## Purpose
Build a reproducible literature evidence base across scoping, systematic, deep, narrative, and snowball modes.
## Input contract
```yaml
mode_contracts:
scoping:
required: [research_question, evidence_scope, inclusion_rules]
optional: [seed_sources, query_set, time_window]
constraints: [abstract_or_metadata_orientation_only, declared_universe_and_coverage_ratio]synthesize-meta-analytic-evidence
When your agent uses it
Design or execute a quantitative evidence synthesis with pairwise/network/cumulative/heterogeneity/bias modes while preserving study-level quality and sensitivity logic.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
3,859 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use / not applicable
- Input contract
- Execution protocol
- Mode branches
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Legacy context checkpoint / Delta notes
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytesSKILL.mdcore14,913 bytes
Read SKILL.md
# synthesize-meta-analytic-evidence
## Purpose
Design or execute quantitative evidence synthesis while preserving study-level quality, heterogeneity, bias, and sensitivity logic.
## When to use / not applicable
Use when multiple studies or comparable effect estimates must be combined. Not applicable when evidence is a single case or no comparable outcome can be defined.
## Input contract
```yaml
mode_contracts:test-risky-prediction
When your agent uses it
Derive a risky/nontrivial prediction uniquely or strongly implied by an explanation and test whether available evidence supports it; distinguish post-hoc accommodation from prospective constraint.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,215 bytes
Read SKILL.md
# test-risky-prediction
## Purpose
Derive a risky prediction uniquely or strongly implied by an explanation and test it against evidence.
## Input contract
```yaml
required: [explanation, alternatives, available_evidence]
optional: [prospective_predictions, test_conditions]
constraints: [prediction must distinguish the explanation from at least one alternative]
```
## Procedure
1. Derive prediction and its distinguishing conditions.
2. Check whether it was prospective or post-hoc.
3. Compare evidence and classify support, failure, or accommodation.
## Output contracttest-structure-preservation
When your agent uses it
Test whether the proposed mapping preserves the required relations/operations/invariants and actively search for a minimal counterexample to preservation.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
258 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,251 bytes
Read SKILL.md
# test-structure-preservation
## Purpose
Test whether a proposed mapping preserves required relations, operations, and invariants, while searching a minimal counterexample.
## Input contract
```yaml
required: [mapping, preservation_obligations, source_and_target]
optional: [counterexample_search_space]
constraints: [obligations must be enumerated before testing]
```
## Procedure
1. Evaluate each relation, operation, and invariant.
2. Search for the smallest preservation failure.
3. Record pass, fail, unknown, and counterexample evidence.
trace-assumption-cascade
When your agent uses it
Trace downstream claims, methods, and conclusions that fail when a selected assumption is invalidated; distinguish local from cascading failure.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
342 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,756 bytesSKILL.mdcore1,756 bytes
Read SKILL.md
# trace-assumption-cascade
## Purpose
Trace downstream claims, methods, and conclusions that fail when a selected assumption is invalidated.
## Input contract
```yaml
required: [assumption, dependency_graph, downstream_claims]
optional: [failure_evidence, intervention]
constraints: [each cascade edge must identify dependency and failure mechanism]
```
## Procedure
1. Identify the assumption and immediate dependents.
2. Propagate invalidation through claims, methods, and conclusions.
3. Distinguish local from cascading failure and record recovery points.
trace-causal-chain
When your agent uses it
Trace ordered causal chains including intermediate nodes, branches, and loops with explicit because/mechanism links.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
315 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,534 bytes
Read SKILL.md
# trace-causal-chain
## Purpose
Trace ordered causal chains with intermediate nodes, branches, loops, mechanisms, and boundary conditions.
## Input contract
```yaml
required: [causal_question, evidence_set, chain_granularity]
optional: [candidate_graph, time_order, loop_policy]
constraints: [every edge has a because/mechanism statement]
```
## Procedure
1. Identify start and endpoint variables from the question.
2. Expand intermediate mediators and mechanism links.
3. Mark branches, feedback loops, temporal order, and unsupported edges.
4. Return complete chains with evidence and boundary conditions.trace-citation-neighborhood
When your agent uses it
Expand an evidence set through backward/forward citation chaining and terminate using explicit relevance/saturation criteria, independent of the retrieval tool used.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
374 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,967 bytesSKILL.mdcore1,967 bytesSKILL.mdcore1,967 bytesSKILL.mdcore1,967 bytes
Read SKILL.md
# trace-citation-neighborhood
## Purpose
Expand an evidence set through backward and forward citation chaining, then stop using explicit relevance and saturation criteria.
## Input contract
```yaml
required: [seed_sources, citation_edges, relevance_rules]
optional: [backward_depth, forward_depth, source_quality, criticality_schema]
constraints: [citation direction, source identity, independence, and stopping evidence must be retained]
```
trace-patent-family
When your agent uses it
Trace priority, family membership, forward/backward citations, and continuation relationships until relevant family structure stabilizes.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,574 bytesSKILL.mdcore1,574 bytes
Read SKILL.md
# trace-patent-family
## Purpose
Trace priority, family membership, forward/backward citations, and continuation relationships until relevant family structure stabilizes.
## Input contract
```yaml
required: [patent_records, priority_links, family_identifiers]
optional: [citation_edges, continuation_records, jurisdiction_scope]
constraints: [family relation, jurisdiction, date, and source provenance must be explicit]
```
transform-component
When your agent uses it
Apply an explicit structural/function operator such as remove, substitute, combine, divide, redirect, redistribute, or reverse.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
330 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,663 bytes
Read SKILL.md
# transform-component
## Purpose
Apply one explicit structural or functional operator to a named component and record the resulting variant.
## Input contract
```yaml
required: [component, operator, system_context]
optional: [target_function, constraints, parent_design]
constraints: [operator must be one of remove, substitute, combine, divide, redirect, redistribute, reverse]
```
## Procedure
1. Identify the component's current function, interfaces, and dependencies.
2. Apply the named operator: remove; substitute; combine; divide; redirect; redistribute; or reverse.
3. Record changed functions, dependencies, constraints, and the resulting variant.
4. Return compatibility checks to the calling tactic.type-relation
When your agent uses it
Classify relations among entities using an explicit relation ontology and state evidence/assumptions for the type.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
337 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,677 bytes
Read SKILL.md
# type-relation
## Purpose
Classify relations among entities with an explicit relation ontology and evidence for the chosen type.
## Input contract
```yaml
required: [entity_pair, relation_ontology, evidence_register]
optional: [candidate_relation_types, scope_ledger, prior_edges]
constraints: [relation type, direction, scope, and evidence are explicit]
```
## Procedure
1. Verify that both entities are in scope and normalize their identifiers.
2. Enumerate candidate relation types and test each against its defining conditions.
3. Select the best-supported type or record ambiguity, then state direction and evidence.
4. Emit the typed relation, rejected types, and follow-up evidence needed to resolve uncertainty.update-confidence-from-evidence
When your agent uses it
Update confidence in a concept, relation, claim, or model component from new supporting/contradicting evidence with explicit rationale.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,684 bytesSKILL.mdcore1,684 bytes
Read SKILL.md
# update-confidence-from-evidence
## Purpose
Update confidence in a concept, relation, claim, or model component from new supporting or contradicting evidence.
## Input contract
```yaml
required: [target_record, prior_confidence, new_evidence, update_rule]
optional: [support_weights, contradiction_weights, confidence_floor]
constraints: [each update cites evidence direction, provenance, weight rule, and prior state]
```
## Procedure
1. Verify target identity and freeze the prior confidence and evidence ledger.
2. Classify each new item as supporting, contradicting, or non-informative under the declared rule.
3. Apply the update rule, record the weight and direction, and cap the result to the permitted confidence range.
4. Emit the updated confidence, evidence trace, and unresolved conflicts.update-cumulative-evidence
When your agent uses it
Update a cumulative evidence estimate/order as new studies or evidence blocks arrive and detect when inference changes materially over time.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
329 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,722 bytes
Read SKILL.md
# update-cumulative-evidence
## Purpose
Update a cumulative evidence estimate or ordering as new studies or evidence blocks arrive and detect material inference change over time.
## Input contract
```yaml
required: [prior_estimate, new_evidence_block, estimand]
optional: [prior_data, heterogeneity_model, time_field, sensitivity_plan]
constraints: [new evidence must be linked to the same estimand or an explicit comparability change]
```
update-pairwise-rating
When your agent uses it
Update candidate latent ratings and uncertainty from sequential pairwise outcomes using an explicitly chosen Bradley-Terry/Elo/Glicko/TrueSkill-style update model.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
327 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,584 bytes
Read SKILL.md
# update-pairwise-rating
## Purpose
Update latent candidate ratings and uncertainty from a pairwise outcome using an explicitly chosen rating model.
## Input contract
```yaml
required: [prior_ratings, pairwise_outcome, rating_model, update_parameters]
optional: [rating_history, draw_policy, uncertainty_floor]
constraints: [model, outcome direction, confidence, and parameter values are recorded]
```
## Procedure
1. Validate the pairwise outcome and retrieve the two prior rating states.
2. Apply the declared Bradley-Terry, Elo, Glicko, TrueSkill, or equivalent update equations.
3. Update both ratings and uncertainty, preserving the pre-update state and the reason for the magnitude.
4. Emit the updated ratings, uncertainty change, and consistency flags for downstream audit.validate-axis-independence
When your agent uses it
Test candidate dimensions pairwise for independence/redundancy; merge covarying axes and remove non-informative axes.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
323 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,598 bytes
Read SKILL.md
# validate-axis-independence
## Purpose
Test candidate dimensions pairwise for redundancy or dependence, merging covarying axes and removing non-informative axes.
## Input contract
```yaml
required: [candidate_axes, observations_or_measurements, independence_rule]
optional: [domain_constraints, sample_plan, prior_axis_map]
constraints: [each pair has a declared test, dependence criterion, and evidence basis]
```
## Procedure
1. Normalize axis definitions, units, ranges, and observed cases before comparison.
2. Test each axis pair for dependence, redundancy, or deterministic derivation under the declared rule.
3. Merge or remove axes only when the evidence crosses the stated criterion; preserve the rationale and affected mappings.
4. Emit the validated axis set, pairwise test matrix, and unresolved dependence cases.validate-causal-link
When your agent uses it
Audit a causal relation for clarity, existence, sufficiency, and logical completeness using CLR-style checks.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
413 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore2,050 bytesSKILL.mdcore2,050 bytesSKILL.mdcore2,050 bytes
Read SKILL.md
# validate-causal-link
## Purpose
Audit a causal relation for clarity, existence, sufficiency, and logical completeness using CLR-style checks.
## Input contract
```yaml
required: [causal_relation, source_evidence, boundary_conditions]
optional: [causal_graph, alternative_explanations, clr_checklist]
constraints: [the relation has explicit cause and effect; distinguish clarity, existence, sufficiency, and logical completeness]
```
validate-goal-tree
When your agent uses it
Check leaf specificity, testability, coverage of the parent goal, logical completeness, and dependency consistency.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
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
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,675 bytesSKILL.mdcore1,675 bytesSKILL.mdcore1,675 bytes
Read SKILL.md
# validate-goal-tree
## Purpose
Check leaf specificity, testability, coverage of the parent goal, logical completeness, and dependency consistency.
## Input contract
```yaml
required: [goal_dag, top_goal, validation_criteria]
optional: [actor_profile, constraints, feasibility_annotations]
constraints: [each validation judgment cites the affected node and criterion]
```
validate-mitigation-effect
When your agent uses it
Re-run the relevant failure/adversarial test after a mitigation and verify that risk actually decreases without unacceptable new failure modes.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
245 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,234 bytes
Read SKILL.md
# validate-mitigation-effect
## Purpose
Re-run the relevant failure or adversarial test after mitigation and verify actual risk reduction without unacceptable new failures.
## Input contract
```yaml
required: [failure_mode, baseline_risk, mitigation, validation_test]
optional: [new_failure_conditions, residual_risk_scale]
constraints: [baseline and post-mitigation tests must be comparable]
```
## Procedure
1. Reproduce the baseline failure or risk measurement.
2. Apply the mitigation and re-run the relevant test.
3. Compare residual risk and inspect new failure modes.
## Output contractvalidate-research-gap
When your agent uses it
Test whether an apparent gap is real, persistent, and not an evidence-acquisition artifact, keeping every candidate rejected as closed on record. Tool choice is left to the host AI.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
564 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Execution protocol
- Output contract
- Thresholds and quality gates
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
- Context checkpoint / Delta notes
Files
SKILL.mdcore2,764 bytesSKILL.mdcore2,764 bytesSKILL.mdcore2,764 bytesSKILL.mdcore2,764 bytesSKILL.mdcore2,764 bytesSKILL.mdcore2,764 bytes
Read SKILL.md
# validate-research-gap
## Purpose
Test whether an apparent research gap is real, persistent, and not an evidence-acquisition artifact, and keep the candidates rejected along the way auditable.
## Input contract
```yaml
required: [gap_claim, evidence_set, search_scope]
optional: [independent_sources, time_slices, candidate_gap_types]
constraints: [absence claims require an explicit scope and retrieval record]
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `verify-evidence-independence` to check source independence.
2. You MUST load skill `filter-false-gap` to separate open, touched-but-not-closed, and false gaps.verify-evidence-independence
When your agent uses it
Seek independent evidence channels sufficient to determine whether a finding/gap is source-specific. No database/provider is named.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Parameterization
- Failure and counterexamples
- Provenance map
- Preserved source criteria ledger
Files
SKILL.mdcore1,805 bytesSKILL.mdcore1,805 bytesSKILL.mdcore1,805 bytes
Read SKILL.md
# verify-evidence-independence
## Purpose
Determine whether a finding is supported by independent evidence channels rather than one source lineage.
## Input contract
```yaml
required: [finding, evidence_records, independence_definition]
optional: [source_lineage, search_scope, stopping_rule]
constraints: [independence claims require explicit lineage and channel distinctions]
```
## Procedure
1. Group records by source, method, dataset, and citation lineage.
2. Identify channels that are independent under the supplied definition.
3. Compare direction, effect, and contradiction across channels.
4. Return support status, dependence risks, and remaining search needs.verify-reproducibility
When your agent uses it
Assess reproducibility across reruns/replications using the predeclared reproducibility target and suitable agreement/variance metrics.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
328 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input contract
- Procedure
- Output contract
- Quality gates
- Failure and counterexamples
- Provenance map
Files
SKILL.mdcore1,614 bytesSKILL.mdcore1,614 bytesSKILL.mdcore1,614 bytes
Read SKILL.md
# verify-reproducibility
## Purpose
Assess reproducibility across reruns/replications using the predeclared reproducibility target and suitable agreement/variance metrics.
## Input contract
```yaml
required: [reproducibility_target, rerun_results, replication_results]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]
```
write-research-spec
When your agent uses it
Convert a confirmed North Star, ResearchBrief, and user constraints into an executable multi-stage Research Spec.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
765 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input Contract
- Execution Protocol
- Spec Contract
- Output Contract
- Completion Criteria
- Failure and Backtrack
- Boundary
Files
SKILL.mdcore3,684 bytes
Read SKILL.md
# write-research-spec
## Purpose
Convert a confirmed North Star, ResearchBrief, and user constraints into an executable multi-stage Research Spec. The spec is a plan projection over checkpoint events, not a second persistent artifact.
## Input Contract
```yaml
required: [confirmed_north_star, research_brief, user_constraints]
optional: [existing_context, preferred_depth, candidate_tactics]
constraints:
- North Star must be user-confirmed
- every stage needs objective, inputs, focus, tactic selection, completion gate, backtrack condition, and execution stepsSkills included
- abstract-structure
- adjudicate-exchange
- adjust-abstraction-scope
- adversarial-deliberation
- aggregate-ranking
- analogical-discovery
- analyze-constraints-readiness
- analyze-experiment-results
- analyze-future-scenarios
- analyze-heterogeneity
- analyze-intervention
- analyze-leaderboard-dynamics
- analyze-patent-citation-network
- analyze-scaling-regime
- analyze-temporal-trajectory
- apply-perturbation
- apply-question-framework
- apply-separation-principle
- apply-stage-gate
- apply-veto-filter
- appreciative-reframe
- assess-construct-validity
- assess-evidence-saturation
- assess-goal-feasibility
- assess-patent-claim-scope
- assess-patent-legal-status
- assess-prior-art-and-claims
- assess-problem-wickedness
- assess-publication-bias
- assess-question-quality
- assess-ranking-consistency
- assess-readiness-dimension
- assess-removability
- assess-sensitivity
- assess-system-boundary
- assumption-stress-test
- atomize-claim
- atomize-concept
- attach-evidence-to-relation
- audit-benchmark-validity
- audit-convergence-independence
- audit-data-contamination
- audit-explanatory-compression
- audit-reporting-quality
- audit-structural-equivalence
- audit-structure-consistency
- audit-study-validity
- audit-validator-independence
- biologize-problem
- biomimetic-transfer
- build-concept-fan
- build-current-reality-tree
- build-domain-ontology
- build-failure-chain
- build-noncircularity-matrix
- calibrate-adversarial-confidence
- calibrate-probability-forecast
- canonicalize-entity
- categorize-evidence
- challenge-assumption
- characterize-anomaly
- check-dominance
- classify-assumption-vulnerability
- classify-constraint
- classify-falsification-verdict
- classify-research-gap
- classify-simplicity-evidence
- classify-stakeholder-salience
- collect-independent-judgments
- compare-evaluation-protocols
- compare-hypotheses
- compare-pair
- conceptual-blending
- construct-argument-map
- construct-causal-model
- construct-counterfactual
- construct-critique
- construct-defense
- construct-design-matrix
- construct-evidence-network
- construct-hierarchy
- construct-input-spaces
- construct-perspective-set
- construct-scenario
- construct-validity-envelope
- counterfactual-causal-analysis
- coverage-white-space-search
- cross-examine
- crystallize-north-star
- dare
- decompose-and-or-goal
- decompose-components
- decompose-evaluation-metric
- decompose-global-sensitivity
- decompose-ishikawa
- decompose-research-goal
- decompose-research-question
- define-analysis-dimensions
- define-criteria
- define-evidence-protocol
- define-objective
- derive-consequences
- design-data-extraction
- design-discriminating-prediction
- design-experiment
- design-falsification-test
- design-mitigation
- design-randomness-protocol
- design-study-inclusion
- destructive-ideation
- detect-breakpoint
- detect-contradiction
- detect-coverage-gap
- detect-feedback-loop
- detect-pass-by-construction
- detect-performance-discrepancy
- discover-biological-analog
- document-counterclaim
- downgrade-equivalence-claim
- drill-five-whys
- drill-root-causes
- elicit-weights
- enumerate-combinations
- enumerate-dimension-values
- enumerate-failure-modes
- enumerate-validator-assumptions
- establish-empirical-baseline
- estimate-effective-evidence-count
- estimate-performance-headroom
- estimate-sample-size
- evaluate-compatibility
- evaluate-falsifiability
- evaluate-necessity-sufficiency
- evaluate-optionality
- evaluate-scenario-impact
- evaluate-scenario-robustness
- evolve-solution-population
- execute-probe
- execute-research-spec
- explore-dimensional-space
- extract-biological-strategy
- extract-causal-structure
- extract-concepts
- extract-constructive-movement
- extract-core-conflict
- extract-empirical-regularity
- extract-evaluation-protocol
- extract-evidence-record
- extract-generic-space
- extract-structural-mapping
- falsifiability-audit
- falsification-first-audit
- filter-false-gap
- fmea-risk-analysis
- formulate-hypotheses
- formulate-meta-analysis-scope
- formulate-research-question
- formulate-top-goal
- generate-alternative-model
- generate-attack-vector
- generate-candidate-directions
- generate-competing-hypotheses
- generate-counterexample
- generate-provocation
- generate-subquestions
- identify-bottleneck
- identify-critical-chain
- identify-dominant-frame
- identify-inventive-contradiction
- identify-load-bearing-factors
- identify-obstacles
- identify-scenario-drivers
- identify-shared-priors
- identify-theory
- identify-variables
- instantiate-transfer
- inventory-reference-items
- list-undesirable-effects
- map-ablation-components
- map-analogy
- map-coverage-space
- map-dependencies
- map-disagreement
- map-patent-white-space
- map-productive-polarity
- map-research-landscape
- map-stakeholder-jobs
- map-stakeholder-system
- map-threat-surface
- map-validity-envelope
- measure-portfolio-diversity
- mine-patent-landscape
- mutate-solution-population
- navigate-patent-classification
- negate-claim
- normalize-comparison-scale
- normalize-gap
- operationalize-construct
- optimize-design-under-budget
- optimize-pareto-frontier
- pairwise-ranking
- parse-patent-claim
- plan-effect-size
- portfolio-optimization
- predict-competitive-move
- probe-benchmark-artifact
- problem-reframing
- project-future-reality
- propagate-uncertainty
- quantify-information-value
- quantify-resource-gap
- rank-candidates
- reductio-counterexample-analysis
- refine-claim
- represent-mechanism-edge
- research-catalog
- resolve-inventive-contradiction
- robustness-analysis
- rotate-perspective
- run-convergence-round
- scope-domain
- score-fmea-risk
- score-object
- screen-evidence-multistage
- search-minimal-flip
- select-critical-case
- select-experimental-baseline
- select-from-frontier
- select-inventive-principle
- select-next-pair
- select-seed-evidence
- select-solution-variants
- select-statistical-method
- sensitivity-analysis
- sequence-work
- set-threshold
- sharpen-falsifiable-claim
- simulate-emergent-properties
- specify-boundaries
- specify-execution-environment
- specify-metrics
- specify-relationship
- specify-reproducibility-protocol
- statistical-testing
- structural-transformation
- structured-consensus
- structured-red-team
- surface-assumptions
- synthesize-field-panorama
- synthesize-idea
- synthesize-literature-evidence
- synthesize-meta-analytic-evidence
- test-risky-prediction
- test-structure-preservation
- trace-assumption-cascade
- trace-causal-chain
- trace-citation-neighborhood
- trace-patent-family
- transform-component
- type-relation
- update-confidence-from-evidence
- update-cumulative-evidence
- update-pairwise-rating
- validate-axis-independence
- validate-causal-link
- validate-goal-tree
- validate-mitigation-effect
- validate-research-gap
- verify-evidence-independence
- verify-reproducibility
- write-research-spec
Repository facts
- License
- Apache-2.0
- Created
- Feb 10, 2026
- Last pushed
- Oct 23, 2026
- Forks
- 42
- Open issues
- 1
- Project activity
- Active
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 381 notes
skills/abstract-structure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-structure/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adjust-abstraction-scope/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adversarial-deliberation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adversarial-deliberation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adversarial-deliberation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adversarial-deliberation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/adversarial-deliberation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/aggregate-ranking/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/analogical-discovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/abstract-structure/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/abstract-structure/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/abstract-structure/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/abstract-structure/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/abstract-structure/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/abstract-structure/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.
