self-improvement
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal with Recurrence-Count at least 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use self-healing instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.
Pinned to revision 8a71d7098d7c, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/self-improvement/SKILL.md
- skills/self-improvement/assets/ERRORS.md
- skills/self-improvement/assets/FEATURE_REQUESTS.md
- skills/self-improvement/assets/LEARNINGS.md
- skills/self-improvement/assets/SKILL-TEMPLATE.md
- skills/self-improvement/hooks/openclaw/HOOK.md
- skills/self-improvement/hooks/openclaw/handler.ts
- skills/self-improvement/references/examples.md
- skills/self-improvement/references/hooks-setup.md
- skills/self-improvement/references/openclaw-integration.md
- skills/self-improvement/scripts/activator.sh
- skills/self-improvement/scripts/error-detector.sh
- skills/self-improvement/scripts/extract-skill.sh
Every link opens the file at its source, pinned to the revision this page describes.