Claude Skills by yogsoth-ai

Strategy: 为同一现象构建多个竞争假设

SOP: 为同一现象生成机制上不同的竞争假设

Tactic: 多假设管理——生成竞争假设，设计区分性预测，构建结构化比较矩阵

Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.

Predict competitor progress, publications, and strategic moves

What will competitors do? — Competitive method progress prediction and time window analysis

Query the 39x39 TRIZ contradiction matrix to find recommended inventive principles for a given technical contradiction.

Systematically vary parameters along defined axes, recording performance at each point to identify degradation thresholds.

Compare results across multiple model variants — quantitative agreement metrics and qualitative conclusion stability.

Evaluate whether the ranking has stabilized by analyzing rating history and computing stability metrics.

Iterative convergence to a single answer through Classic Delphi, Modified Delphi, or Nominal Group Technique rounds.

Extract core conflict in Evaporating Cloud format (A-B-C-D-D')

Generate dialectical opposites for governing variables — coherent alternative worldviews where the opposite is true.

Construct the strongest possible counter-argument to the convergence decision using Dialectical Inquiry and Thesis-Antithesis-Synthesis methods.

Systematically generate counterexamples (monsters) to a given claim using diverse heuristic strategies.

Generate counterexamples (monsters), attempt monster-barring, incorporate surviving counterexamples as lemma refinements (Lakatos method).

Campaign: Counterfactual reasoning to identify load-bearing factors. Core question: If key factors were different, would the conclusion still hold? Methods: Pearl SCM Three-Step, Lewis Possible Worlds, Tetlock & Belkin, PNS/PS.

Construct precise, internally consistent counterfactual scenarios where specified factors are altered, then reason about the resulting conclusion.

Strategy: Legal adversarial structure — prosecution presents case, defense responds, evidence is cross-examined, judge delivers verdict. Emphasizes evidence quality and procedural rigor.

Systematic coverage evaluation pipeline — benchmark inventory, method-problem crossing, and intersection evaluation to map explored vs unexplored solution space.

Detect uncovered regions in the solution space, producing a prioritized gap list.

Map evaluation coverage, identify untested capability dimensions — 20 benchmarks, 30 papers, 50 web searches

Compute coverage completeness, redundancy, and gap severity scores from a coverage map.

Challenge the evaluation criteria themselves using Assumption-based Planning, Critical Systems Heuristics, and Boundary Critique to ensure the framework is sound.

Extract evaluation criteria from research goals and candidate alternatives.

Attack an advocate's case with multiple arguments rated by severity.

Strategy: Classic triangular debate — Critic attacks, Defender responds, Judge adjudicates. Based on Irving AI Safety via Debate with Toulmin argumentation structure.

Flyvbjerg critical case methodology: select most-likely and least-likely cases to maximize inferential power.

Identify the critical chain — longest path considering resource contention

CPM forward/backward pass with float calculation to identify the critical path

Identify which input uncertainties contribute most to output uncertainty and compute EVPI for research prioritization.

Identify the shortest execution path via CPM forward/backward pass, resource leveling, and buffer insertion

CCA: pairwise consistency checking to reduce solution space 90-99%

Orchestrates pairwise consistency evaluation and narrative construction to filter the morphological field

Verify gap existence across multiple databases (Semantic Scholar, Google Scholar, arXiv, domain-specific). Distinguishes database-specific gaps from universal gaps.

Cross-Domain Discovery Campaign — find transferable mechanisms from unrelated fields via bisociation, analogical transfer, random stimulus, and forced bridging

Synthesize all cross-domain findings into a structured idea report. Integrates outputs from all strategies and SOPs.

Probes defender responses for inconsistencies, logical gaps, and unsupported claims. Acts as follow-up interrogation after initial defense.

Multi-source cross-validation of gap authenticity — cross-database search, temporal sensitivity testing, false-gap filtering, stakeholder confirmation.

Fuse the GoalTree root node and user motivation into a single crystallized North Star statement. Format: '[verb] [specific goal], through [method/path], solving [what problem], ultimately [what impact]'. Quality checks: specific? ambitious? achievable?

Apply Ulrich's Critical Systems Heuristics 12 questions across 4 dimensions (motivation, control, expertise, legitimacy) comparing is vs ought.

Track evidence accumulation over time — cumulative meta-analysis protocol design. Budget: 40 studies, 40 effect sizes, 30 web searches.

Build TOC Current Reality Trees — connect Undesirable Effects via sufficient-cause logic to identify 1-3 root causes.

Scan a pairwise comparison matrix for preference cycles and compute transitivity metrics.

Design structured data extraction form for systematic meta-analysis data collection

Top-level orchestrator for the yogsoth-ai research ecosystem. Drives the full research lifecycle from direction crystallization through experiment design.

Designs debate structure based on artifact type — selects attack vectors, assigns perspectives, determines escalation ladder, and configures round parameters.

Generates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses.

Responds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms.

Evaluates debate exchanges, adjudicates argument quality, and produces round verdicts with confidence scores and reasoning.