name: skill-creator-improvement description: Improves skill-creator generated skills by updating SKILL.md Gotchas and verified examples with reusable learnings. Use after using a generated skill if the interaction revealed custom fields, service quirks, faster workflows, corrected commands, or safer usage patterns.
skill-creator improvement
Use this skill proactively after using a skill generated by @asnd/skill-creator when you discover reusable knowledge that would make future use faster or safer.
Safety boundary
Only edit skills tracked in ~/.skill-creator/lock.json or ${SKILL_CREATOR_HOME}/lock.json when that environment variable is set.
Before editing:
- Identify the generated skill directory you used.
- Read the lock file.
- Confirm the target skill path or
agent:scope:nameentry is present. - If the skill is not tracked, do not modify it. Tell the user it is outside skill-creator management.
What to improve
Add concise, verified learnings directly to the target skill's ## Gotchas section when real usage reveals:
- stable custom fields, IDs, project keys, registry names, or instance-specific mappings
- service quirks that caused failed or repeated discovery
- faster command chains that worked
- corrected command examples or safer flags
- output filters, pagination, or bounded-query patterns that reduce noise
Editing rules
- Keep
SKILL.mdconcise and hot-path useful. - Prefer short bullets in
## Gotchas. - Add only reusable knowledge verified by actual use.
- Do not add secrets, tokens, raw API responses, huge outputs, or one-off task details.
- Do not rewrite the whole skill unless necessary.
- Ask before changing destructive workflows, auth behavior, source URLs, install scope, or anything that could affect production data.
Workflow
- Read the target
SKILL.md. - Locate
## Gotchas; create it if missing. - Add or update the smallest useful bullet(s).
- Update verified examples or usage rules only when a command example changed and was smoke-tested.
- Briefly report what changed and why.
Gotchas
- The lock file is the source of truth for whether this skill may edit another skill.
- Important learnings belong in
SKILL.md, not only in references, because agents rarely read references unless prompted.