본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

context-clean-up

phenomenoner 제작

Coding Agents & IDEs
1.7kclawskills.sh가 보고한 다운로드 수
5스타
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Use when: you suspect OpenClaw prompt context is bloating (slow replies, high cost, repeated transcript noise)

설명

이 스킬이 하는 일

Audits prompt context to identify what is consuming the most space, then produces a ranked list of offenders and a reversible fix plan. No changes are applied automatically. Designed for situations where slow replies, rising costs, or noisy transcripts suggest context has grown too large.

Gives a prioritized, rollback-ready fix plan based on measured context metrics rather than guesswork.

사용 시점

  • Diagnosing slow AI replies caused by context bloat
  • Finding oversized tool output clogging session transcripts
  • Identifying cron automation noise accumulating across sessions
  • Spotting bloated bootstrap files like AGENTS.md or SKILL.md
  • Getting a safe trim plan before modifying any config files

예시 워크플로

입력

User asks: /context-clean-up

에이전트
  1. 1

    Determine workspace directory and OpenClaw state directory

  2. 2

    Run the audit script to collect context size metrics across sessions

  3. 3

    Rank offenders by category: tool output dumps, automation noise, bootstrap bloat, ambient skill surface

  4. 4

    Generate a phased fix plan with expected impact and rollback steps for each change

출력

Audit report listing top context offenders, lowest-risk fixes ordered by phase, and verification steps to confirm improvement after changes

설치

clawhub install phenomenoner/context-clean-up

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크