AGENT SKILLS · ミッション装備
実際に使われている Agent Skills
公開リポジトリの検証済み Skills を比較し、機能、内容、導入状況、出典を確認してから追加できます。
- 掲載範囲
- 検証済み
- Skills
- 22,797
- リポジトリ
- 3512
- 最終同期
- 2026/11/01
yogsoth-aiconceptual-blending
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.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiconstruct-causal-model
Construct and validate an explicit causal model with measurable variables, mechanism edges, evidence links, feedback loops, interventions, counterevidence, and confidence.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiconstruct-validity-envelope
Synthesize multi-axis breakpoints into a multidimensional statement of where a claim/method remains valid.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aicoverage-white-space-search
Map known methods against problem/parameter space and generate candidates from uncovered and weakly covered intersections. Acquisition mechanism is runtime-selected.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aicross-examine
Probe responses for inconsistency, logic gaps, and unsupported claims.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidecompose-and-or-goal
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidefine-analysis-dimensions
Identify approximately independent dimensions/axes that span the relevant problem, design, or validity space and define their semantics.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidefine-evidence-protocol
Define research questions, evidence scope, queries/concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence for an acquisition task.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidefine-objective
Formalize objectives, constraints, and tradeoff preferences for optimization.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidesign-discriminating-prediction
Construct a prediction that yields different outcomes under competing hypotheses.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidesign-falsification-test
Specify a concrete observation, computation, intervention, counterexample, or measurement that would count against the sharpened claim, prioritizing cheap high-information tests.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidestructive-ideation
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.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidetect-breakpoint
Locate the point or region where performance/validity changes regime or the claim flips.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidetect-feedback-loop
Detect and characterize reinforcing/balancing feedback loops, participating variables, delays, and possible breakpoints.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidiscover-biological-analog
Identify biological systems that achieve the target function under comparable constraints, without assuming surface similarity.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidocument-counterclaim
Construct a counterclaim, identify its target claim, contradiction type, assumptions, and supporting evidence requirements.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aidowngrade-equivalence-claim
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.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aienumerate-combinations
Construct combinations across dimensions/values without prematurely judging them.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aienumerate-validator-assumptions
Enumerate assumptions embedded in a validator/test/sandbox, including data-generation, measurement, simulator, oracle, metric, initialization, and acceptance assumptions.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiestimate-effective-evidence-count
Estimate an effective number of independent evidence/reasoning paths after discounting dependence/correlation; report nominal N, dependence structure, and Neff.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aievaluate-necessity-sufficiency
Test whether a proposed cause/mechanism is necessary and/or sufficient under controlled counterfactual or intervention comparisons.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiexplore-dimensional-space
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.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiextract-constructive-movement
Convert an initially absurd/destructive provocation into concrete useful directions.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日
yogsoth-aiextract-core-conflict
Represent a core constraint conflict in an Evaporating-Cloud-like structure with explicit assumptions on every dependency.
- 1時間の導入数
- 1
- GitHub Stars
- 505
- 更新日
- 9月29日