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.

skills.sh installs: 553
GitHub stars: 6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add galaxy-dawn/claude-scholar --skill results-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Results Analysis

Run strict, evidence-first experimental analysis for ML/AI research.

Use this skill to produce a strict analysis bundle:

analysis-report.md
stats-appendix.md
figure-catalog.md
figures/

When the user asks for review, audit, no-write, dry-run, or when inputs are incomplete, use read-only audit mode instead of producing files or figures. In that mode, output only valid/invalid statistics, blockers, claim candidates, and what evidence is missing. If invoked by /analyze-results, the command layer may write a blocker summary, but this skill should not create figures, reports, or polished conclusions from incomplete evidence.

Do not use this skill to draft a paper Results section or a full experiment wrap-up report. Those belong to ml-paper-writing or results-report.