Browse reusable Agent Skills, each with a clear purpose and practical guidance.
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.
Tactic for reasoning about what would happen if variables were different — supports causal identification and intervention analysis.
Construct precise, internally consistent counterfactual scenarios where specified factors are altered, then reason about the resulting conclusion.
Map evaluation coverage, identify untested capability dimensions — 20 benchmarks, 30 papers, 50 web searches
Catalog all known solutions/methods in a domain with performance, applicability, and limitations.
Identify factors and their levels for a problem, then design an experiment matrix for systematic exploration.
Systematically catalog all failure modes in a domain or method, producing a classified failure taxonomy.
Abstract-level paper scanning for broad coverage. Import of literature-engine/literature-overview skill. Abstract-level only — no methodology conclusions from abstracts.
Deep paper analysis with full text reading. Import of literature-engine/literature-research skill. Full text access — required for quoting results, verifying claims, extracting detailed methodology.
Mid-depth paper analysis via AI-generated summaries. Import of literature-engine/literature-search skill. Reads AI summary — sufficient for methodology understanding but not for quoting specific results.