hypothesis-testing-engine

Quick Review

The skill addresses a valuable task (automated hypothesis testing) with a clear high-level description. However, the SKILL.md lacks concrete implementation details: no guidance on data source selection methods, statistical test selection logic, sample size calculation approaches, or handling of different hypothesis types (causal, correlational, descriptive). The 'Instructions' section provides general direction but would benefit from specifics like which statistical tests to apply when, how to operationalize vague claims, or criteria for determining confidence levels. The generic template sections ('Best Practices', 'Common Use Cases') appear boilerplate and don't provide hypothesis-testing-specific guidance. Novelty is moderate—while automating scientific method is valuable, a capable CLI agent could design basic research protocols given sufficient prompting. The skill would significantly improve with concrete workflows, decision trees for test selection, and examples showing how to handle ambiguous claims.