yogsoth-ai · Agent Skills
72 Skills avec une documentation substantielle et des sources vérifiées. Ouvrez une fiche pour lire les instructions originales et vérifier le paquet et son installation.
aggregate-ranking
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
apply-separation-principle
Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
appreciative-reframe
Reframe a problem around functioning exceptions, existing strengths, positive deviance, and conditions under which desired behavior already occurs.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
assess-goal-feasibility
Cross-check goal branches against resources, obstacles, and timeline; label feasible/stretch/infeasible and propose OR alternatives.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
assess-question-quality
Audit a research question for scope and FINER-style quality; return targeted repairs.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
assess-removability
Estimate whether and at what cost a constraint can be removed or relaxed.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
assess-sensitivity
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.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
attach-evidence-to-relation
Attach supporting or contradicting evidence to a specific claim/relation with quality, directness, and independence metadata.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
audit-data-contamination
Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
audit-reporting-quality
Audit whether a research/evaluation artifact reports the information needed for interpretation and reproduction, using a domain-appropriate checklist.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
audit-study-validity
Audit a study against an appropriate methodological-quality and risk-of-bias rubric; return domain-level judgments, evidence, and overall confidence.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
audit-validator-independence
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.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
build-concept-fan
Expand a target goal into progressively broader concepts and alternative routes, then descend into new concrete approaches.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
build-current-reality-tree
Build a sufficient-cause Current Reality Tree linking undesirable effects to a small root set.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
build-failure-chain
Build multi-level cause - failure mode - effect chains and identify cascades/shared roots.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
categorize-evidence
Cluster an evidence corpus by theme, method, chronology, mechanism, or another declared schema.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
collect-independent-judgments
Collect judgments/rankings from multiple genuinely independent evaluators or perspectives before exposing any peer outputs, preserving ballots and rationale for later social-choice aggregation.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
compare-pair
Execute one pairwise comparison under a specified criterion/model and return winner, confidence, and reasons.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
conceptual-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.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
construct-causal-model
Construct and validate an explicit causal model with measurable variables, mechanism edges, evidence links, feedback loops, interventions, counterevidence, and confidence.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
construct-validity-envelope
Synthesize multi-axis breakpoints into a multidimensional statement of where a claim/method remains valid.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
coverage-white-space-search
Map known methods against problem/parameter space and generate candidates from uncovered and weakly covered intersections. Acquisition mechanism is runtime-selected.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
cross-examine
Probe responses for inconsistency, logic gaps, and unsupported claims.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
decompose-and-or-goal
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
- Installations / 1h
- 1
- GitHub Stars
- 505
- Mis à jour
- 29 sept.
