Claude Skills by yogsoth-ai

This document serves as an index of usage guides under `docs/use-skill/`. It is intended to help readers quickly find concrete examples of how to use specific skills in this repository for practical tasks, such as reading a single research paper.

Quick web scanning for field landscape understanding. Strict import of web-browsing/web-search skill. Hard constraint: brave_web_search count=10 per call, at least 150 total search results before completing.

SOP: 统一不同来源的 gap 格式为标准 GapRecord

SOP: 对两个 gap 进行逐标准相对优先级判断，输出偏好结果

Score and rank validated gaps on importance, feasibility, novelty, and urgency. Multi-criteria decision analysis with stakeholder confirmation.

Compile all gap analysis products into a coherent final report with evidence gap maps, research agenda, and concept matrices.

Compile all gap analysis intermediate products into a coherent final report with executive summary, detailed findings, and research agenda.

Classify gaps using Miles 7-type taxonomy (theoretical, methodological, empirical, population, practical, knowledge void, evidence gap).

Validate gap authenticity via cross-database verification, temporal sensitivity testing, and false-gap filtering. Ensures gaps are genuine absences, not search artifacts.

Define gate criteria and pass thresholds for a specific stage in the Stage-Gate process.

Evaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence.

Ritchey GMA: complete iterative morphological process

Propose 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.

Aggregate 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.

Extract shared abstract structure from two input spaces

Structure 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.

Apply Argyris framework to identify governing variables — the unstated rules driving behavior in a research field.

Structured creative thinking in Six Hats Green Hat mode — pure creative output with judgment suspended.

Strategy: 10th Man Rule and Liberating Structures — institutionalized dissent to prevent premature consensus and expose suppressed objections.

Estimate theoretical/practical ceiling vs current SOTA gap

Explain why different studies reach different conclusions — heterogeneity investigation protocol. Budget: 30 studies, 30 effect sizes, 50 web searches.

Identify and classify sources of between-study heterogeneity (clinical, methodological, statistical)

Generate "How Might We" questions at different scope levels (narrow, medium, broad). Ensures each is actionable without being prescriptive.

Minimal 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.

SOP: 构建竞争假设的多维度对比矩阵

Campaign: 将 insight 和 gap 转化为结构化的可测试假设

Strategy: 将 working hypothesis 精确化为可测试形式

SOP: 综合所有中间产物，产出最终结构化假设集

Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions.

Enumerate barriers to pursuing the chosen research direction — knowledge barriers, resource barriers, capability barriers, competition barriers. May optionally use search tools to discover obstacles the user hasn't mentioned.

SOP: 评估研究 gap 的潜在影响力，识别受益方并输出影响力评分

Plan execution path, produce executable plan, dispatch subagents, collect and analyze results

Dispatch execution subagent — select model by complexity, construct prompt with full task context

SOP: 评估研究 gap 的学术与实践重要性，输出 1-5 分及依据

Define inclusion/exclusion criteria for systematic study selection in meta-analysis

Identify which specific comparison pairs are most responsible for preference cycles and inconsistencies.

Strategy: 从数据/观察归纳提炼假设

Build input spaces for two source concepts

Insight 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.

Detect and characterize significant parameter interactions from Sobol decomposition results.

Design intermediate objectives to overcome each identified obstacle

Evaluate exploration status of each cell in a method×problem matrix, annotating as explored, partial, or unexplored.

Extract constructive insights from worst solutions. Transform failure analysis into innovation directions.

Reverse statements → extract insights → build constructive alternatives. Systematic inversion pipeline from negation to innovation.

Decompose problems into 6M categories (Methodology, Data, Theory, Measurement, Researchers, Environment) via fishbone diagram analysis.

Execute one full Delphi round — collect judgments, distribute anonymous feedback, measure consensus, decide whether to continue.

Map stakeholder Jobs-to-be-Done — functional, emotional, and social jobs for each affected party. Identifies unserved jobs as opportunity signals.

Render an impartial verdict on advocate case vs critic attacks with explicit reasoning.

Collect independent judgments from all perspectives on a given question.

Military ACT: systematically enumerate all assumptions, classify by type, and evaluate evidence strength supporting each.