self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) The agent realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
npx skills add majiayu000/claude-skill-registry --skill self-improving-agent-ederheisler-agent-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Self-Improvement Skill Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory. **Not for** general Q&A, coding tasks, or ad-hoc reasoning. Use only to log, review, and promote learnings/errors/feature requests. **Context discipline:** Do not open whole log files; append directly or read only a small slice around the target entry. ## Memory Index (progressive loading) | Purpose | Path | |---------|------| | Learnings log | .learnings/LEARNINGS.md | | Errors log | .learnings/ERRORS.md | | Feature requests | .learnings/FEATURE_REQUESTS.md | | Formats reference | references/formats.md | | Examples | references/examples.md | | Promotion guide | references/promotion.md | | Review workflow | references/review.md | Maintain this table when adding new reference files; keep descriptions short so only the needed file is opened. ## Progressive Loading Rules - Do not load whole log files by default. Append directly to the correct file; if you must inspect, read only the relevant entry or a small surrounding slice. - Use grep/search first to find matching IDs or keywords bef
- Memory Index (progressive loading)
- Progressive Loading Rules
- Quick Reference
- Setup
- Core Workflow
- 1. Log the Entry
- 2. Resolve When Fixed
- 3. Promote If Applicable
- Detection Triggers
- Priority Guidelines
- Recurring Pattern Detection
- Periodic Review
- Best Practices
- Reference Documentation
mkdir -p .learnings
What does the self-improvement skill do?
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) The agent realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill self-improving-agent-ederheisler-agent-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.