skill-evolve
Mine the CURRENT session for how the agent skills were actually used - friction hit, commands corrected, recipes discovered, docs found stale - distill only the SELECTIVE, generalizable improvements, apply them to the relevant SKILL.md / reference files in the skills repo, and ship via vd:ship. Conservative by design: high bar, evidence-backed, no scope creep. Use when the user says 'evolve the skills', 'skill-evolve', 'improve the skills from this session', 'capture what we learned into the skills', 'update the skills based on this session', or runs an end-of-session skill retro. Routes standing-behavior corrections to vd:rule-miner and project/task facts to memory - it only touches skill content.
Target: Design & content creation. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- skill-evolve
- The three buckets (route every candidate before doing anything)
- The selectivity gate
- Workflow
- Hard rules
- Scope & security
Close the loop between using skills and improving them: the friction you hit this session (a wrong command, a missing recipe, a stale doc) is the highest-signal feedback there is. Capture it selectively and ship it back into the skills repo - most sessions produce 0-2 real skill improvements, and a long list is a smell. Adjacent skills: vd:rule-miner (standing-behavior corrections → CLAUDE.md/AGENTS.md rules), vd:skill-management (lifecycle ops), vd:create-skill (new skill, evals first), memory (project/user facts). skill-evolve only edits the content of existing skills from this session's evidence. 1. Skill-content improvement - a SKILL.md / reference is wrong, incomplete, or missing a reusable recipe you just proved out → this skill. 2. Standing-behavior correction - "the agent keeps doing X wrong across tasks" → vd:rule-miner. Do not write rules here. 3. Project / task fact - a brand name, this repo's layout, a one-off config → memory, never into a skill (skills are shared/public). If a candidate doesn't clearly fit bucket 1, it does not belong in a skill. Keep a bucket-1 candidate only if all three hold: (a) General - it helps a future, unrelated session, not just this task. (b
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- vanducng/skills
- Source file
- skills/skill-evolve/SKILL.md
- Fixed revision
- c20411b8df8f821988c87689f6aefe142b6f9025
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: vanducng/skills · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-11T14:02:27.568Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.