All authors
Claude Skills by yogsoth-ai
github.com/yogsoth-ai1,223 skills7 installs1,449 views
- Update Pairwise RatingUpdate candidate latent ratings and uncertainty from sequential pairwise outcomes using an explicitly chosen Bradley-Terry/Elo/Glicko/TrueSkill-style update model.Votes: 0GitHub stars: 499
- Validate Axis IndependenceTest candidate dimensions pairwise for independence/redundancy; merge covarying axes and remove non-informative axes.Votes: 0GitHub stars: 499
- Validate Causal LinkAudit a causal relation for clarity, existence, sufficiency, and logical completeness using CLR-style checks.Votes: 0GitHub stars: 499
- Validate Goal TreeCheck leaf specificity, testability, coverage of the parent goal, logical completeness, and dependency consistency.Votes: 0GitHub stars: 499
- Validate Mitigation EffectRe-run the relevant failure/adversarial test after a mitigation and verify that risk actually decreases without unacceptable new failure modes.Votes: 0GitHub stars: 499
- Verify Evidence IndependenceSeek independent evidence channels sufficient to determine whether a finding/gap is source-specific. No database/provider is named.Votes: 0GitHub stars: 499
- Verify ReproducibilityAssess reproducibility across reruns/replications using the predeclared reproducibility target and suitable agreement/variance metrics.Votes: 0GitHub stars: 499
- Write Research SpecConvert a confirmed North Star, ResearchBrief, and user constraints into an executable multi-stage Research Spec.Votes: 0GitHub stars: 499
- Analogical DiscoveryAbstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.Votes: 0GitHub stars: 499
- Portfolio OptimizationFormalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.Votes: 0GitHub stars: 499
- Sensitivity AnalysisQuantify which parameters, assumptions, interactions, or uncertainties dominate the conclusion; select Morris/Sobol/perturbation/Monte-Carlo as modes.Votes: 0GitHub stars: 499
- Validate Research GapTest whether an apparent gap is real, persistent, and not an evidence-acquisition artifact. Tool choice is left to the host AI.Votes: 0GitHub stars: 499
- Gap NormalizationSOP: 统一不同来源的 gap 格式为标准 GapRecordVotes: 0GitHub stars: 417
- Gap Pairwise JudgmentSOP: 对两个 gap 进行逐标准相对优先级判断，输出偏好结果Votes: 0GitHub stars: 417
- Gap Synthesis StrategyCompile all gap analysis products into a coherent final report with evidence gap maps, research agenda, and concept matrices.Votes: 0GitHub stars: 417
- Gap SynthesisCompile all gap analysis intermediate products into a coherent final report with executive summary, detailed findings, and research agenda.Votes: 0GitHub stars: 417
- Gap Typology ClassificationClassify gaps using Miles 7-type taxonomy (theoretical, methodological, empirical, population, practical, knowledge void, evidence gap).Votes: 0GitHub stars: 417
- Gap ValidationValidate gap authenticity via cross-database verification, temporal sensitivity testing, and false-gap filtering. Ensures gaps are genuine absences, not search artifacts.Votes: 0GitHub stars: 417
- Gate Criteria DefinitionDefine gate criteria and pass thresholds for a specific stage in the Stage-Gate process.Votes: 0GitHub stars: 417
- Gate JudgmentEvaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence.Votes: 0GitHub stars: 417
- General Morphological AnalysisRitchey GMA: complete iterative morphological processVotes: 0GitHub stars: 417
- Generate Candidate FieldsPropose 3-8 candidate research fields based on the full ActorProfile. When user wants to explore beyond their current stack, use other ActorProfile signals (intentionality, boundary) to determine exploration space. Free exploration within the boundary.Votes: 0GitHub stars: 417
- Generate Research BriefAggregate all accumulated context from the crystallization process into a structured ResearchBrief document. This is the final output artifact alongside the North Star — a comprehensive requirement context document for downstream research strategies.Votes: 0GitHub stars: 417
- Generic Space ExtractionExtract shared abstract structure from two input spacesVotes: 0GitHub stars: 417
- Goal DecompositionStructure the user's chosen direction into a formal goal tree using KAOS-style AND/OR decomposition. Validate feasibility against ActorProfile and ObstacleReport. Use after obstacle-analysis confirms the direction is viable.Votes: 0GitHub stars: 417
- Governing Variable SurfacingApply Argyris framework to identify governing variables — the unstated rules driving behavior in a research field.Votes: 0GitHub stars: 417
- Green Hat SessionStructured creative thinking in Six Hats Green Hat mode — pure creative output with judgment suspended.Votes: 0GitHub stars: 417
- Groupthink MitigationStrategy: 10th Man Rule and Liberating Structures — institutionalized dissent to prevent premature consensus and expose suppressed objections.Votes: 0GitHub stars: 417
- Headroom EstimationEstimate theoretical/practical ceiling vs current SOTA gapVotes: 0GitHub stars: 417
- Heterogeneity InvestigationExplain why different studies reach different conclusions — heterogeneity investigation protocol. Budget: 30 studies, 30 effect sizes, 50 web searches.Votes: 0GitHub stars: 417
- Heterogeneity Source AnalysisIdentify and classify sources of between-study heterogeneity (clinical, methodological, statistical)Votes: 0GitHub stars: 417
- Hmw FormulationGenerate "How Might We" questions at different scope levels (narrow, medium, broad). Ensures each is actionable without being prescriptive.Votes: 0GitHub stars: 417
- Hot StartMinimal crystallization strategy for users who already have a specific research topic or problem (e.g., "I want to improve CoT faithfulness in LLMs") and need structuring into a formal North Star. Heavily simplifies or skips exploration tactics, focusing on obstacle analysis, goal decomposition, and synthesis. Use when the user's first message reveals a specific, actionable research direction.Votes: 0GitHub stars: 417
- Hypothesis Comparison MatrixSOP: 构建竞争假设的多维度对比矩阵Votes: 0GitHub stars: 417
- Hypothesis FormulationCampaign: 将 insight 和 gap 转化为结构化的可测试假设Votes: 0GitHub stars: 417
- Hypothesis OperationalizationStrategy: 将 working hypothesis 精确化为可测试形式Votes: 0GitHub stars: 417
- Hypothesis SynthesisSOP: 综合所有中间产物，产出最终结构化假设集Votes: 0GitHub stars: 417
- Idea SynthesisSynthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions.Votes: 0GitHub stars: 417
- Identify ObstaclesEnumerate obstacles that block a target goal/direction, with type, evidence, and blocking relation.Votes: 0GitHub stars: 417
- Impact ScoringSOP: 评估研究 gap 的潜在影响力，识别受益方并输出影响力评分Votes: 0GitHub stars: 417
- Implementation PlanningPlan execution path, produce executable plan, dispatch subagents, collect and analyze resultsVotes: 0GitHub stars: 417
- Implementer DispatchDispatch execution subagent — select model by complexity, construct prompt with full task contextVotes: 0GitHub stars: 417
- Importance ScoringSOP: 评估研究 gap 的学术与实践重要性，输出 1-5 分及依据Votes: 0GitHub stars: 417
- Inclusion Criteria DesignDefine inclusion/exclusion criteria for systematic study selection in meta-analysisVotes: 0GitHub stars: 417
- Inconsistency LocalizationIdentify which specific comparison pairs are most responsible for preference cycles and inconsistencies.Votes: 0GitHub stars: 417
- Inductive Hypothesis GenerationStrategy: 从数据/观察归纳提炼假设Votes: 0GitHub stars: 417
- Input Space ConstructionBuild input spaces for two source conceptsVotes: 0GitHub stars: 417
- InsightInsight Campaign — deep root-cause analysis of why research gaps persist. 5 strategies (root-cause-drilling, stakeholder-mapping, tension-mining, question-reformulation, assumption-audit), 4 tactics, 13 subagent SOPs.Votes: 0GitHub stars: 417
- Interaction DetectionDetect and characterize significant parameter interactions from Sobol decomposition results.Votes: 0GitHub stars: 417
- Intermediate Objective DesignDesign intermediate objectives to overcome each identified obstacleVotes: 0GitHub stars: 417