Claude Skills by yogsoth-ai

Systematically generate boundary inputs — boundary values, adversarial constructions, distribution shifts, rare combinations, scale extremes.

Systematically extract effect sizes and conditions from papers for meta-analytic synthesis

Determine effect size types and calculation methods for meta-analytic synthesis

Strategy for large-N sparse pairwise comparison using TrueSkill, active learning, and rank centrality to rank 100+ candidates from limited comparisons.

Build structured Evidence Gap Maps — define axes (intervention × outcome or method × domain), place gaps in cells, annotate with evidence density and quality.

Detect and validate emergent properties from combinations. Orchestrates emergent-property-identification → blend-elaboration.

Seek properties that emerge from combination (non-additive)

Identify non-additive properties from combinations

Generate technical solutions emulating biological strategies. Bridge from design principle to concrete implementation.

Synthesize all systematic enumeration outputs into a structured idea report with prioritized recommendations.

SOP: define complete experiment environment specification

Identify dominant thinking pattern and escape it via deliberate pattern-breaking.

Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection.

Compare implementation differences of same benchmark across papers

Model conflicts as Goldratt's Evaporating Cloud — expose hidden assumptions behind opposing needs to dissolve the conflict.

Strategy: 基于证据强度的 AHRQ PiCMe 评估——用文献证据质量驱动 gap 优先级

Assess evidence quality using GRADE/SOE framework. Rates certainty level and identifies downgrade reasons.

Systematic evidence map construction — search, classify, locate gaps, visualize. Combines concept-matrix-construction, gap-keyword-extraction, evidence-grading, and egm-construction SOPs.

Build evidence network graph for network meta-analysis — nodes, edges, geometry assessment

Searches for external evidence supporting or opposing specific claims. Returns structured evidence with source assessment and relevance scoring.

Plan the statistical synthesis approach — model selection, heterogeneity strategy, and reporting

Synthesize multi-source evidence into structured argumentation. Weaves findings from literature, web, and analysis into coherent evidence maps with explicit strength ratings.

Tactic: Evidence gathering, cross-examination, and quality judgment. External evidence is collected, presented, challenged, and scored for relevance and reliability.

Map evolution mechanisms to design operations. Translate selection, mutation, drift, radiation into design operators.

Use evolution mechanisms (selection, mutation, radiation) as design operators for generating and refining solution populations.

Leave the problem entirely and explore an unrelated domain. Produces excursion domain discoveries for later force-fitting.

Full 8-stage Gordon-Prince excursion process. Deliberate departure from the problem into unrelated domains, then force-fit discoveries back.

Orchestrate the excursion sequence — departure into unrelated domain, force-fit discoveries back to problem, launch springboard ideas.

Execute a Research Spec step by step, respecting context protocol, deviation limits, and backtrack rules. Supports multi-session recovery.

Monitor execution progress, detect anomalies, and report status

Synthesize complete execution report from all results, tests, and reproducibility data

SOP: generate executable experiment configuration files

Transform validated hypotheses into rigorous, executable experiment designs

Execute the plan by dispatching fresh subagents per task, monitoring status, and collecting results

SOP: 为异常现象生成候选解释列表

Understand the user's background comprehensively — technical stack, project experience, research experience, publications, research directions. Allows user to express interest beyond their resume. Execute once only, never re-run.

Structured data extraction from deep-read papers — produces comparison tables (method, dataset, metrics, results, limitations). Used by systematic-survey and deep-survey.

Generate boundary and extreme test values for a given parameter dimension to stress-test claims.

Bridge two unrelated thinking matrices via Koestler bisociation. Identify independent frames of reference and force collision to produce creative insight.

List all key factors, conditions, and assumptions that support or enable the artifact's conclusion.

Identify independent, dependent, and control variables for an experiment

Strategy: Systematic factor removal — remove factors one at a time and observe whether the conclusion remains stable, identifying which factors are load-bearing.

DOE thinking: identify factors, define levels, and explore combinations to systematically cover the design space.

Campaign: Forward-looking failure analysis combining pre-mortem rapid screening with systematic FMEA deep-dive. Core question: If this artifact fails, how will it fail? Methods: Klein Pre-Mortem 2007, AIAG-VDA FMEA 2019, IEC 60812.

Build cause-mode-effect chains tracing upstream root causes and downstream cascading effects for each failure mode.

Tactic: Trace upstream causes and downstream effects of each failure mode. Builds multi-level cause-mode-effect chains for systemic understanding.

Group observed failures by mechanism (not symptom), identify common triggers per cluster, estimate frequency and severity.

Generate targeted solutions for each identified failure mode, ensuring every failure has at least one proposed mitigation.

Systematically catalog failure modes — generate edge cases, observe failures, cluster by mechanism, identify triggers and frequency.

Extract structured failure mode list from raw scenarios or artifact analysis. Produces standardized failure mode records.