skill-doctor

Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits — scores recent local Claude Code / Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report.

• SKILL.md6,252 bytes
• assets/report.example.json2,132 bytes
• assets/session_scores.example.json1,675 bytes
• assets/suggestions.example.json1,197 bytes
• references/session_mining_privacy.md5,082 bytes
• references/skill_edit_governance.md5,895 bytes
• references/transcript_scoring_canon.md4,804 bytes
• scorers/code-quality.md4,781 bytes
• scorers/efficiency.md3,340 bytes
• scripts/collect_sessions.py33,284 bytes
• scripts/render_report.py11,737 bytes
• scripts/score_aggregator.py15,734 bytes