{"skill":{"slug":"learning-loop","displayName":"Learning Loop","summary":"Structured self-improvement system for AI agents with confidence decay, cross-agent sharing, and anomaly detection. Use when: (1) After debugging sessions to...","tags":{"latest":"1.4.0"},"stats":{"comments":0,"downloads":40,"installsAllTime":3,"installsCurrent":3,"stars":0,"versions":1},"createdAt":1771445119234,"updatedAt":1778491578254},"latestVersion":{"version":"1.4.0","createdAt":1771445119234,"changelog":"learning-loop 1.4.0 introduces confidence decay, error tracking, and structured cross-agent sharing.\n\n- Added exponential confidence decay for rules, flagging stale rules for review.\n- Implemented cross-agent rule sharing with portable JSON exports, metadata, and trust/conflict checks.\n- Introduced parse-errors.jsonl for tracking JSON parsing errors.\n- Expanded automation scripts for daily/weekly extraction, pattern detection, self-audit, and metric updates.\n- Updated documentation with clear usage instructions, anti-patterns, boot sequence wiring, and safety nets for context compaction.","license":null},"metadata":{"os":null,"systems":null},"owner":{"handle":"yoder-bawt","userId":"publishers:yoder-bawt","displayName":"yoder-bawt","image":"https://avatars.githubusercontent.com/u/259239279?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1778491578254}}