Claude Skills by yogsoth-ai

Catalog all failure modes in a domain, classify them systematically, and generate targeted solutions for each failure type.

Detect false gaps — search failures, already-solved gaps, and inherently unanswerable questions masquerading as research gaps.

Tactic: 假设质量保证——检验可证伪性，修复不合格假设，完成操作化与边界条件规范

SOP: 检验假设是否满足可证伪性标准

Wish-fulfillment thinking — ignore physical laws for ideal solution. Use unconstrained imagination to reveal what the problem truly needs.

Unconstrained wish-fulfillment ideation. Ignore all physical laws to imagine the ideal solution, then identify realization directions.

Feasibility Assessment Campaign — evaluate whether selected candidates can actually be implemented using TRL, NASSS, Stage-Gate, TRIZ, TOC, and parametric estimation methods.

Cross-reference the GoalTree against ActorProfile (capabilities), ObstacleReport (known barriers), and timeline (deadline feasibility). Identify infeasible paths and suggest OR alternatives.

Strategy: 在资源约束下重塑研究问题 — pragmatic 调整保持核心价值

SOP: 评估研究 gap 的可攻击性，识别瓶颈并输出可行性评分

Synthesize all assessments into a feasibility matrix, recommendation, and risk summary.

Create anonymized feedback report summarizing group judgment distribution for a given round.

Self-review the North Star + ResearchBrief for completeness, consistency, and clarity before presenting to user. If issues found, return to specific tactic/SOP for targeted fix. If passes, present final output to user for confirmation.

Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report.

SOP: FINER 5 项标准逐项检验研究问题质量

Iterative "Why?" questioning (5+ levels) to drill from surface phenomenon to actionable root cause. Each level verified against evidence.

Find the minimal change magnitude along a dimension that causes the conclusion to flip from true to false.

Force-fit excursion discoveries back to the original problem. Deliberately create connections between unrelated findings and the challenge.

Force connections between unrelated technologies. Deliberately construct bridges where none naturally exist to discover novel integration possibilities.

Force connection between two unrelated concepts. Deliberately construct bridging paths where no natural connection exists.

Express the user's chosen research direction as a formal goal statement in the format: 'Achieve [what], such that [effect], under [constraints]'. Confirm with user before proceeding to decomposition.

Split concepts into smaller units and recombine them differently to produce novel structures.

Identify which specific assumption changes cause conclusion divergence. Rates fragility severity and plausibility of alternatives.

Compute a fragility index from flip-point distances and degradation scores, summarizing how robust the conclusion is.

Strategy: 选择 RQ 框架（PICO/SPIDER/SPICE/ECLIPSE）并系统应用

SOP: 根据研究类型匹配最适合的 RQ 框架

Tactic: 选择最适合的 RQ 框架并系统应用

Produce a complete ordering of all candidates using PROMETHEE I/II, ELECTRE III, or MAVT methods.

FMEA Step 3: Decompose artifact into function tree — identify what each component is supposed to do before analyzing how it can fail.

TRIZ function analysis: function-level recombination and redistribution

Build substance-field functional model of a system, annotating useful, harmful, insufficient, and excessive interactions.

Redistribute functions across different components

Remove components while preserving function via TRIZ trimming methodology. Simplify systems by redistributing functions.

Map technical functions to biological functions, find organisms solving equivalent problems. Deep functional matching across domains.

Build biological system functional model. Map energy, matter, and information flows.

Project solution effects using Future Reality Tree logic

Aggregate probability judgments across perspectives using Real-Time Delphi or prediction market mechanisms.

Gap Analysis Campaign — identify, classify, validate, and prioritize research gaps via systematic evidence mapping. 5 strategies (gap-identification, gap-classification, gap-validation, gap-prioritization, gap-synthesis), 3 tactics, 12 subagent SOPs.

Classify identified gaps using Miles 7-type taxonomy and AHRQ 4-reason framework. Determines gap type (theoretical, methodological, empirical, etc.) and root cause of gap existence.

Generate solutions targeting specific coverage gaps — detect gaps, generate failure-driven solutions, and design factor-level experiments.

Extract gap-indicating sentences and phrases from papers/reviews. Identifies linguistic markers of research gaps (e.g., "remains unclear", "has not been explored", "limited understanding").

Competitor perspective — design strategies to defeat this solution, then use attack vectors to improve it.

Decompose system into functional components, identify dependencies, and surface trimming candidates.

Component-level surgical operations (subtract/multiply/divide/unify/redirect) from Systematic Inventive Thinking (SIT).

Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions from the symbolic tension.

Normalize results by compute budget (Pareto analysis)

Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space

Expand concept fan from purpose through concepts to directions to ideas (de Bono Concept Fan).

Expand from purpose to concepts to directions to ideas (de Bono Concept Fan)

Build concept levels from purpose through concepts to ideas, with escape and fractionation at each level.