
Claude Skills by yogsoth-ai
github.com/yogsoth-aiProofs and Refutations method: generate counterexamples, attempt monster-barring, incorporate surviving counterexamples as lemma refinements.
Broad, shallow exploration of candidate research fields. Understand what's out there before narrowing. Use when the user needs to discover which fields are available to them — especially in cold-start and warm-start scenarios.
Patent landscape full-scan — maps technology domain via assignee ranking, IPC/CPC classification, filing trends. Budget: 200 patent families, 0 claim parses, 80 web searches.
Evaluate each candidate research field on maturity, competition, entry barrier, and publication opportunity. Synthesizes broad-web-search results into a structured FieldPanorama. Must consider both niche approaches AND direct frontal competition in hot fields.
de Bono lateral escape sequence — identify dominant idea, generate provocations (escape/reversal/exaggeration/distortion), follow consequences to extract new framings. Breaks paradigm lock-in.
Synthesize all lateral thinking intermediate outputs into a structured idea report.
Lateral Thinking Campaign — escape logical thinking tracks via PO/movement, random entry, concept fan, challenge, and six hats (de Bono)
Analyze leaderboard score distributions, compression, selective reporting
Systematically collect performance data from platforms and papers
Determine patent legal status — active, expired, pending, lapsed, or revoked
Determine appropriate levels for each experimental factor
Apply life's principles as design constraints. Orchestrates ecosystem-pattern-extraction → evolution-mechanism-transfer → abstraction-to-design.
Quick landscape scan — discover papers on a topic without full-text reading
Deep literature research — raw full text reading and targeted PDF queries for rigorous analysis
Medium-depth literature search — read AI-summarized reports for every paper analyzed
Autonomous Literature Survey Campaign — 5 research paradigms (scoping, systematic, deep, narrative, snowball) with quantitative budget enforcement. Selects and executes the right survey paradigm based on research intent.
Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion.
Build n-dimensional morphological matrix
Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning methods.
Assess current readiness of candidates using TRL 9-level, NASSS 7-dimension, and Innovation Readiness Level frameworks.
SOP: 从理论中提取因果机制链
Produce final meta-analysis protocol document assembling all planning outputs into PRISMA-compliant protocol
Cross-Study Statistical Synthesis Campaign — 5 strategies for systematic collection and methodological planning of multi-study evidence synthesis. Covers pairwise, network, cumulative meta-analysis, heterogeneity investigation, and bias detection. Stops at protocol design (no computation).
Identify all relevant methods via literature, leaderboards, citation chains
Comprehensively identify all relevant methods for a task — 50 methods, 60 web searches budget
Build method×problem cross-reference matrix showing which methods have been applied to which problems.
Cross method×problem matrix, find unexplored intersections where known methods have not been applied to known problems.
Analyze how the choice of MCDA method affects final rankings and identify method-sensitive alternatives.
Decompose composite metrics into constituent signals, analyze polarity and ceiling effects
Define experiment metrics and significance standards
Tactic: Generate candidate changes, detect flip-points where conclusion reverses, measure fragility as distance to nearest flip.
Design prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasure specifications.
Strategy: Design prevention, detection, and response measures for high-priority failure modes. Produces actionable countermeasures validated via re-scoring.
Proposes concrete mitigation strategies for identified weaknesses. Generates prevention, detection, and response measures with feasibility assessment.
Tactic: Run mini-FMEA on proposed mitigations to verify they do not introduce new failure modes. Prevents mitigation-induced risks.
Attempt to exclude a counterexample as illegitimate by tightening definitions or preconditions (Lakatos monster-barring).
Design and execute Monte Carlo sampling strategy for uncertainty propagation through a model.
Morphological Exploration Campaign — systematic dimension-combination enumeration to discover unexplored solution spaces via Zwicky box, CCA, and GMA
What are all possible combinations? — Zwicky Box construction with CCA consistency filtering for systematic scenario enumeration
Synthesize all morphological exploration outputs
Morris method screening — compute elementary effects to quickly identify important vs unimportant parameters.
Extract constructive directions from provocations via 4 movement types (moment-to-moment, principle, focus difference, positive aspects).
Extract constructive directions from PO provocations using 4 movement types (moment-to-moment, principle, focus difference, positive aspects).
Strategy: 多维度加权评分排序——将 gap 分解为独立子问题后重组为优先级列表
Score gaps on multiple dimensions (importance, feasibility, novelty, urgency, impact) using weighted multi-criteria decision analysis.
Assess readiness across multiple dimensions, synthesize into radar visualization, and identify bottleneck dimensions.
Collect independent rankings from multiple judges, aggregate using social choice methods, and identify disagreement hotspots.
Simultaneous concept collision at multiple abstraction levels
Apply 2-3 MCDA methods to the same candidates, compare rankings, and identify method-sensitive options.
Wimsatt-style multi-method cross-validation — enumerate assumptions, generate alternative models, compare results, flag divergences.