skill-self-update
SolidReads a skill's feedback.log, decides whether accumulated feedback justifies a change, applies a surgical edit to that skill's SKILL.md, archives the processed feedback, and commits the change to git with a clearly-marked automated message. Designed to run headless (`claude -p`) on a schedule — see docs/living-skills.md for the Task Scheduler setup. Triggers: /skill-self-update <skill-dir>, "обнови скилл по фидбеку", "прочитай feedback.log и обнови SKILL.md". НЕ для: ручного улучшения скилла без накопленного фидбека (→ /self-improve skill <path>), одноразового аудита реестра скиллов (→ /skill-audit).
Install
Quality Score: 78/100
Skill Content
Details
- Author
- sergeeey
- Repository
- sergeeey/Claude-cod-top-2026
- Created
- 4 months ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
skill-updater
Fold the current session's learnings back into the robium skills, on demand. Harvests gotchas from the conversation and any unabsorbed learnings/ files, confirms the list, then edits the robium source checkout: fixes wrong/stale guidance, widens missed trigger surfaces, adds figured-out-from-scratch knowledge, prunes noise, and promotes ✓-verified examples. Use when: a work session surfaced gotchas, frictions, or better methods worth keeping; 'skill-updater', 'update my skills', 'absorb these learnings', 'fold these gotchas into the skills', end of an app-building session with the robium plugin. Runs ONLY on explicit user request — agents surface candidate learnings and offer, never invoke this themselves. Developer workflow — requires a local robium checkout. Not for: authoring a new skill from scratch (skill-author) or building apps (architect).
update-skill
Maintain an existing skill by batching real usage feedback, reflecting on the patterns, and landing one focused edit instead of reactive monkey-patches. Use when the user wants to improve, tune, fix, or update a skill they already wrote, points at feedback for a skill (a notepad, GitHub comments, Slack threads), says a skill is drifting or misbehaving, or wants to set up a weekly self-improvement loop for their skills.
update-skill
Thorough on-demand refresh of one skill in a skills repository: researches usage/upstream/docs in parallel, gates twice for approval, bumps version, updates CHANGELOG, runs the repo's validation, then commits and watches CI. Install the pond MCP (https://pond.cascade.fyi/) for the prior-session usage angle; without it that angle is skipped. Use to update, refresh, or check the freshness of a specific skill.