Lewati ke konten
TakoAPI
Kembali ke skill

context-clean-up

oleh phenomenoner

Coding Agents & IDEs
1.7kUnduhan dilaporkan oleh clawskills.sh
5Bintang
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

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

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

INPUT

User asks: /context-clean-up

AGENT
  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

OUTPUT

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

Instalasi

clawhub install phenomenoner/context-clean-up

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan