From fireauto
Logs user corrections like 'wrong' or 'no' as mistakes, updates CLAUDE.md rules, and auto-generates skills from repeated patterns after 3+ occurrences. Triggers on feedback or repetitions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fireauto:fireauto-self-learn-guideThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
---
다음 상황에서 이 가이드를 참고하세요:
사용자가 수정을 요청하면 즉시 실행하세요:
mistake-log MCP 도구로 기록하세요:
wiki-write MCP 도구로 gotchas.md를 업데이트하세요.
같은 실수 방지 규칙을 CLAUDE.md에 추가하세요.
⚠️ 실수 기록: {내용}. 다음부터 주의할게요.
같은 작업이 3회 이상 반복되면 실행하세요:
반복되는 작업에서 공통 패턴을 추출하세요.
skill-save MCP 도구로 DB에 저장하세요.
.claude/skills/에 스킬 파일을 생성하세요.
wiki-write MCP 도구로 skills-catalog.md를 업데이트하세요.
🔧 새 스킬 생성: {스킬명}
{스킬 설명}
반복 횟수 {N}회에서 자동 감지됐어요.
npx claudepluginhub imgompanda/fireauto --plugin fireautoDetects learning opportunities from user corrections, repeated instructions, tool failures, and tone escalation. Extracts improvement candidates and applies them to Claude's configuration after user approval via `/coach` commands.
Logs errors, user corrections, missing features, API failures, knowledge gaps, and best practices to .learnings/ markdown files. Promotes key insights to CLAUDE.md and AGENTS.md for AI agent self-improvement.
Extracts reusable rules from developer corrections during a coding session and persists them to CLAUDE.md or memory for future sessions.