Claude Skills by yogsoth-ai

Extrapolate research landscape timelines using trend analysis and milestone projection

Adapt transferred principle to target problem constraints. Produces concrete adapted solutions from abstract principles.

Patent filing volume time-series, technology lifecycle stage, and S-curve analysis

Progressively remove components from a system while verifying function preservation through redistribution.

Resolve technical and physical contradictions via TRIZ 40 inventive principles and separation methods.

Select inventive principles from the contradiction matrix and generate concrete solutions for identified contradictions.

Uncertainty cascade propagation — assign input distributions, sample via Monte Carlo, propagate through model, analyze output distribution, identify critical paths. Maps how input uncertainty flows to output uncertainty.

Propagate input uncertainties through the model via Monte Carlo sampling. Identifies which input uncertainties contribute most to output uncertainty.

List current Undesirable Effects (UDEs) — observable symptoms of system underperformance

Quality check on leaf nodes of the GoalTree. Verify each leaf is specific enough, actionable, and that the set of leaves fully covers the top goal. Flag issues for further decomposition.

Combine multi-axis perturbation data into a multi-dimensional validity description with boundary conditions and interaction effects.

Map multi-dimensional validity envelopes — define variation axes, perturb systematically, measure degradation, construct boundary surface.

Challenge construct validity — does benchmark measure claimed capability? — 3 benchmarks, 40 papers, 30 web searches

Enumerate 3-5 values per parameter including extremes

Maximize total portfolio value within constraints using Knapsack, Linear programming, Cost-benefit analysis, and NPV ranking methods.

SOP: 识别变量及其在假设中的角色

Sobol variance decomposition — compute first-order and total-order sensitivity indices to quantify each parameter's contribution to output variance.

Identify orthogonal axes along which a method's validity might vary. Ensures axes are independent, measurable, and span the relevant parameter space.

Synthesizes findings from a completed campaign into typed verdict reports. Produces DebateVerdict, RedTeamReport, FailureAnticipationReport, CounterfactualMap, or AdversarialStressReport depending on campaign. Also supports cross-campaign StressTestSummary.

Map 15 vital relations between concepts

Simplified crystallization strategy for users who have a general research direction (e.g., "I'm interested in LLM reasoning") but lack specificity. Simplifies actor profiling and landscape reconnaissance, then proceeds through direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals a general area but not a specific problem.

Classifies discovered weaknesses into severity tiers (fatal/major/minor/cosmetic) with structured justification and exploitability assessment.

Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Import of web-browsing/web-research skill. Must fetch full page via apify for every analyzed page.

Quick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone.

Compute criteria weights using a specified elicitation method (AHP, Swing, BWM, MACBETH, or Simos).

Determine criteria weights using AHP, Swing, BWM, MACBETH, or Simos methods.

SOP: 扰动权重检验 gap 排序稳定性，输出稳定性判定

Identify patent coverage gaps — feature cross-matrix blank areas revealing unprotected technology combinations. Budget: 150 patent families, 10 claim parses, 60 web searches.

Identify matrix regions not covered by existing methods

Identify unexplored viable regions in the morphological matrix where no existing methods operate.

Feature cross-matrix construction and blank area identification for patent opportunity mapping

Apply Rittel's 10 criteria to determine if the problem is tame, complex, or wicked, and adjust research strategy accordingly.

Score a problem against Rittel's 10 criteria to determine if it is tame, complex, or wicked.

Stress-test the winning candidate using Pre-mortem, Red Teaming, and Failure Mode Analysis to expose hidden weaknesses before commitment.

Construct extreme but plausible worst-case scenarios for stress testing

Design the worst possible solution. Deliberate failure engineering to reveal hidden constraints and inversion opportunities.

Design worst possible solution → extract insights → invert. Deliberate failure design as creative catalyst.

Generate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing.

Classic Zwicky box: parameter identification → value enumeration → matrix construction