auto-improvement
(ePost) Use when reviewing session performance, analyzing improvement trends, or understanding the metrics-capture-detection pipeline
npx skills add majiayu000/claude-skill-registry --skill auto-improvement --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.
# Auto-Improvement Skill ## Purpose Documents the automated feedback loop: metrics collection, lesson capture, and pattern detection across sessions. ## Architecture ``` SessionStart hook Stop hooks (sequential) │ │ write marker ──→ session-metrics.cjs ──→ lesson-capture.cjs current-session.json │ │ append JSONL evaluate thresholds sessions.jsonl │ significant? ──→ prompt knowledge-capture │ /review-improvements (on-demand detection) ``` ## Data Flow ### Storage Tiers | Tier | Location | Tracked | Retention | |------|----------|---------|-----------| | Raw metrics | `.epost-data/improvements/sessions.jsonl` | No (gitignored) | Auto-rotate at 1000 lines | | Session marker | `.epost-data/improvements/current-session.json` | No | Deleted on Stop | | Detection report | `.epost-data/improvements/latest-report.json` | No | Overwritten per run | | Significant learnings | `docs/` | Yes (git tracked) | Permanent | ### JSONL Schema Each line in `sessions.jsonl` is a JSON object: ```json { "sessionId": "string", "timestamp": "ISO-8601", "duration_ms": "number|null", "branch": "string", "git": { "filesChanged": 0, "insertions": 0, "deletions": 0 }, "tasks": { "total": 0, "completed": 0, "faile
- Purpose
- Architecture
- Data Flow
- Storage Tiers
- JSONL Schema
- Significance Thresholds
- Detection Engine
- Hooks
- Related Skills
What does the auto-improvement skill do?
(ePost) Use when reviewing session performance, analyzing improvement trends, or understanding the metrics-capture-detection pipeline
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill auto-improvement --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.