self-improving-agent
低风险 · 93 评分：93/100
作者：pskoett | 审计时间：2026-02-05T09:18:25.242Z | 规则集：0.1.0
技能介绍
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'),…
✨
LEARNINGS.md — corrections, knowledge gaps, best practices ✨
ERRORS.md — command failures, exceptions ✨
FEATURE_REQUESTS.md — user-requested capabilities ✨ sessions_list — View active/recent sessions
✨ sessions_history — Read another session's transcript
✨ sessions_send — Send a learning to another session
✨ sessions_spawn — Spawn a sub-agent for background work
✨ Source: conversation | error | user_feedback
使用场景
1 See Also: LRN-20250110-001 (if related to existing entry)
2 Environment details if relevant
3 See Also: ERR-20250110-001 (if recurring)
4 Documents project-specific conventions
5 When working in an area with past learnings
6 API behavior differs from your understanding
安全审计
低风险 · 93
摘要
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
风险画像
关键风险 0 项
暂无 LLM 风险要点（LLM 未启用或无缓存）。
确定性发现（证据）
未检测到发现。