From cm
Repairs or extends CodyMaster skills via three-mode loop (FIX, DERIVED, CAPTURED) after cm-skill-health identifies issues, grounded in repo tooling.
npx claudepluginhub tody-agent/codymaster --plugin cmThis skill uses the workspace's default tool permissions.
Use this skill after `cm-skill-health` identifies a degraded or broken skill, or when `cm advisory handoff --for cm-skill-evolution` produces a structured recovery note.
Evolves existing skills by refining content in-place or creating advanced variants. Assesses gaps, applies changes, updates version metadata, syncs registry/cross-references. Use for outdated steps, feedback gaps, complexity upgrades.
Improves existing Claude Code skills by fixing under/over-triggering, refining instructions, adding sub-skills, and evolving architecture based on feedback.
Optimizes a single existing Claude Code skill through task-based workflow: analyze structure, gather context, research best practices, identify/apply improvements, validate/review. For 'improve skill' or similar.
Share bugs, ideas, or general feedback.
Use this skill after cm-skill-health identifies a degraded or broken skill, or when cm advisory handoff --for cm-skill-evolution produces a structured recovery note.
Use when the skill should exist already but is inaccurate, broken, or partially missing.
Checklist:
Use when the original promise was too ambitious, but the repo has enough primitives to ship a truthful MVP.
Checklist:
Use when the main value is operational learning rather than a new code path.
Checklist:
cm retro --project . --tool skill --note "...".cm/CONTINUITY.mdcm advisory handoff --for cm-skill-evolutionnpm run validate:skillsnpm run check:skillsFIXDERIVEDCAPTURED## Skill Evolution
- Skill: cm-...
- Mode: FIX | DERIVED | CAPTURED
- Change: ...
- Verification: ...
- Learning captured: yes | no
Preferred advisory input:
## Advisory Handoff
- Consumer: cm-skill-evolution
- Skill: cm-...
- Recovery path: FIX | DERIVED | CAPTURED | NONE
- Confidence: 0.xx
- Source analysis: EA-...
- Task: ...
- Status: completed | partial | failed
- Evidence: ...
- Selected skills: ...
- Target skills: ...
- Quality weight: 0.xx
- Next step: ...