Results Analysis

This is the skill you want when you have experiment logs and need to know what actually happened, not what you hoped happened. It enforces a strict analysis bundle with real figures, complete statistics, effect sizes, and explicit blockers when evidence is missing. The core discipline is separating what you can claim from what you want to claim. It won't write your Results section or polish manuscript prose. Instead it produces analysis-report.md, stats-appendix.md, a figure catalog, and actual generated figures when data exists. Every major figure must answer why it exists and what belief it changes. If your artifacts are incomplete or you're in read-only mode, it runs an audit and tells you exactly what's blocking a valid analysis.