All authors
Claude Skills by yogsoth-ai
github.com/yogsoth-ai1,223 skills7 installs1,449 views
- Adversarial Stress TestingCampaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.Votes: 0GitHub stars: 417
- Advocate ConstructionConstruct the strongest possible case for a rejected candidate or counter-position.Votes: 0GitHub stars: 417
- Aggregation MethodAggregate multiple ranking ballots into a consensus ranking using a specified social choice method.Votes: 0GitHub stars: 417
- Ahp WeightingSOP: 使用 AHP 层次分析法确定评分维度权重，输出权重向量Votes: 0GitHub stars: 417
- Ahrq Picme AssessmentSOP: 使用 AHRQ PiCMe 框架对研究 gap 进行 6 维度系统评估Votes: 0GitHub stars: 417
- Ahrq Reason ClassificationClassify gap root causes using AHRQ 4-reason framework (insufficient info, biased info, inconsistent info, not yet integrated).Votes: 0GitHub stars: 417
- Alternative AnalysisStrategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing — generate competing explanations and scenarios to challenge the dominant narrative.Votes: 0GitHub stars: 417
- Alternative FuturesGenerate 2-4 divergent scenarios from the same evidence base, each representing a plausible alternative to the artifact's conclusions.Votes: 0GitHub stars: 417
- Alternative Model GenerationGenerate alternative model formulations by relaxing, replacing, or generalizing specific assumptions.Votes: 0GitHub stars: 417
- Alternative ScoringScore each candidate alternative against all criteria to produce a score matrix.Votes: 0GitHub stars: 417
- Alternatives GenerationGenerate alternatives for every known approach — ensure no approach goes unchallenged.Votes: 0GitHub stars: 417
- Analogical TransferSystematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.Votes: 0GitHub stars: 417
- Analogy ChainChain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.Votes: 0GitHub stars: 417
- Analogy ExtractionExtract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.Votes: 0GitHub stars: 417
- Analogy Quality AssessmentAssess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.Votes: 0GitHub stars: 417
- And Or DecomposeKAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).Votes: 0GitHub stars: 417
- Anomaly CharacterizationSOP: 描述和分类无法被现有理论解释的异常现象Votes: 0GitHub stars: 417
- Anomaly Driven AbductionTactic: 归纳/溯因路径——描述异常现象，生成候选解释，按可信度排序Votes: 0GitHub stars: 417
- Answering Sequence DesignSOP: 设计子问题的最优回答顺序Votes: 0GitHub stars: 417
- Anti BenchmarkChallenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.Votes: 0GitHub stars: 417
- Appreciative DiscoverySearch for positive deviants and extract transferable principles using Appreciative Inquiry.Votes: 0GitHub stars: 417
- Appreciative ReframingFind positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.Votes: 0GitHub stars: 417
- Appropriateness BoundingEstablish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.Votes: 0GitHub stars: 417
- Argument CrystallizationDistill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods.Votes: 0GitHub stars: 417
- Argument ExtractionExtract and steel-man the core arguments supporting a given opinion cluster.Votes: 0GitHub stars: 417
- Artifact DetectionDetect annotation artifacts and shortcuts in benchmarksVotes: 0GitHub stars: 417
- Ask ConstraintsUnderstand hard boundaries on the user's research — target venues, methodology preferences, areas to avoid, advisor/team requirements. Not limited to ML/AI — works for any research domain.Votes: 0GitHub stars: 417
- Ask Decomposition ValidationPresent the GoalTree to the user for confirmation. Ask about reasonableness, missing elements, and priority ordering among sub-goals.Votes: 0GitHub stars: 417
- Ask IntentionalityDeep WHY probing inspired by i* Intentionality modeling. Understand the user's motivation, success definition, risk tolerance, innovation preference, independence preference, time urgency, and learning willingness. The most important SOP in actor-profiling — understanding WHY drives everything downstream.Votes: 0GitHub stars: 417
- Ask Obstacle AcceptancePresent obstacles with their severity assessments and proposed mitigations to the user. Ask whether they can accept these obstacles. If unacceptable after 2 rounds, return to present-candidates.Votes: 0GitHub stars: 417
- Assess Obstacle SeverityRate each identified obstacle's difficulty — overcomability, time cost, workaround existence. May optionally use search tools to validate assessments.Votes: 0GitHub stars: 417
- Assignee NormalizationStandardize assignee names and identify corporate group affiliations across patent officesVotes: 0GitHub stars: 417
- Assumption AuditSurface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.Votes: 0GitHub stars: 417
- Assumption Cascade TracerBuild assumption dependency graphs and trace cascade failures when root assumptions are invalidated.Votes: 0GitHub stars: 417
- Assumption CascadeTactic: Surface assumptions, sort by dependency, attack root assumptions first, then trace cascade failures through the dependency graph.Votes: 0GitHub stars: 417
- Assumption ChallengingChallenge each assumption's validity — shared cross-repo SOPVotes: 0GitHub stars: 417
- Assumption ConstraintWhich assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptionsVotes: 0GitHub stars: 417
- Assumption CriticalityMeasure how much conclusions change when each assumption is negated. Ranks assumptions by their impact on the final result.Votes: 0GitHub stars: 417
- Assumption DestructionAssumption Destruction Campaign — open new solution spaces by negating, reversing, and challenging fundamental assumptions.Votes: 0GitHub stars: 417
- Assumption ExcavationSystematic extraction, challenge, and sensitivity analysis of assumptions underlying a decision to identify load-bearing beliefs.Votes: 0GitHub stars: 417
- Assumption NegationClassic reductio ad absurdum: negate the core claim, derive logical consequences, seek contradiction or absurdity.Votes: 0GitHub stars: 417
- Assumption Stress TestSurface load-bearing assumptions, classify vulnerability, challenge or perturb them, and re-check causal logic.Votes: 0GitHub stars: 417
- Attack Resilience ScoringCompute overall resilience score (0.0-1.0) based on attack results, coverage, and vulnerability severity distribution.Votes: 0GitHub stars: 417
- Attack Vector GenerationGenerate specific attack strategies for a given threat surface, producing concrete probes that can be executed.Votes: 0GitHub stars: 417
- Axiom NegationIdentify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.Votes: 0GitHub stars: 417
- Ballot CollectionGather independent ranking ballots from multiple judges or perspectives for a given candidate set.Votes: 0GitHub stars: 417
- Baseline EstablishmentSOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.Votes: 0GitHub stars: 417
- Baseline SelectionSelect appropriate baselines for experimental comparisonVotes: 0GitHub stars: 417
- Baseline SynthesisProduce final structured baseline report integrating all analysis resultsVotes: 0GitHub stars: 417
- Benchmark ArchaeologyEvaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.Votes: 0GitHub stars: 417