agentleFS
Sign inStart free
elfrostelfrost/ai-patchlab/.agents/skills/cleanup/SKILL.md

cleanup

Skill1 starsChanged 30 days agoMITView on GitHub

Identify dead code, unused files, and clutter via import-graph tracing from entry points. Writes a report and asks before deleting anything.

  • Reads credentials

71 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chips, react-query-best-practices and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • udecodeSkill

    chips

    Run the project's suggested-task ledger, the chips. /chips alone brings this session's open tasks up to date: it applies what the ledger helper says, settles stale and split tasks, cards what can start and reports the board, and /chips all also takes the ship-list tasks and the ones no live session owns, and merges duplicate tasks across the board. Use for /chips, /chips offer, start or drop, \"what chips are open\", \"suggest a task for X\", \"update the chips\", \"clean up the chips\", \"which chips are stale\", \"is this chip still worth doing\", \"merge duplicate chips\", at the last hand-back of a run that offered a task, and whenever pstack would file a tracked issue, a follow-up, a reflect Backlog item or an out-of-band PR.

    Also in 3 projects that use this

  • bibektimilsina00Skill

    react-query-best-practices

    Audit and fix React Query usage in apps/web — enforce query key factories, signal forwarding, staleTime, and proper mutation patterns. Use when reviewing or fixing server-state code.

    Also in 3 projects that use this

  • bibektimilsina00Skill

    you-might-not-need-a-callback

    Analyze and fix useCallback anti-patterns in your code

    Also in 3 projects that use this

  • Scylla23Skill

    redo

    Re-run the last routed task one model tier up (haiku → sonnet → opus → fable). User-invoked escalation when the previous result missed. Pass --dry-run to preview without running.

    Also in 3 projects that use this

  • Aetheria-Labs1Skill

    plan-page

    Plan one storefront page from strategy through final copy, section order, proof, offers, template direction, responsive layout, and production asset requirements. Stops at an approved execution-ready specification.

    Also in 3 projects that use this

  • SocialKit-APISkill

    video-transcripts

    Extract transcripts from social videos through SocialKit across YouTube, TikTok, Instagram, Facebook, X/Twitter, LinkedIn, and direct video file URLs. Use when the user asks to transcribe, get captions or subtitles, pull the spoken text, or read what a video says, including one video or many at once. Returns full text plus timestamped segments. Not for posting, private accounts, or unrelated website scraping.

    Also in 3 projects that use this

  • +3 more from bibektimilsina00

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 61 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md to understand the project

    line 9
  2. Distinctive:

    NEVER delete without confirmation

    line 53
  3. Distinctive:

    Write the report BEFORE deleting anything

    line 54
  4. Distinctive:

    If unsure, mark ASK USER

    line 55

“Common” is measured: kept by at least 6 in 10 of the 61 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cleanup

Phase 1: Find entry points

  1. Read CLAUDE.md to understand the project
  2. Identify all entry points:
    • if __name__ == "__main__" in .py files
    • Scripts referenced in CLAUDE.md / README
    • Anything in Makefile, docker-compose, scripts/

Phase 2: Build the dependency graph

For each entry point, trace imports recursively. Mark every reachable file ALIVE. Mark unreachable ones DEAD.

Phase 3: Classify dead files

For each DEAD file, categorize:

  • Orphan script — has __main__, never called by main flow (could be a utility)
  • Abandoned module — imported before, no longer is
  • Duplicate / superseded — does the same as an alive file
  • Config / data file — used at runtime but not imported (templates, configs)
  • Test file — may still be relevant even outside main path

Phase 4: Other clutter

  • Empty __init__.py that serves nothing
  • .pyc / __pycache__ directories
  • Old output / log / temp files
  • Backup files (*_v2.py, *_old.py, *_backup.py)
  • Stale TODO / notes files

Phase 5: Report

Write CLEANUP_REPORT.md with:

  • Summary counts (alive / dead / clutter)
  • Entry points list
  • Alive files table (file -> imported by)
  • Dead files table (file -> type -> reason -> recommendation: DELETE / ARCHIVE / ASK USER)
  • Clutter items
  • Recommended actions (Safe / Moderate / Aggressive levels)

Phase 6: Confirm + act

Ask the user: "Quel niveau de cleanup tu veux?

  1. Safe only — clutter évident
  2. Moderate — clutter + dead code évident
  3. Aggressive — tout le dead code, projet lean
  4. Laisse-moi reviser le rapport d'abord"

Apply only what is approved. Move ambiguous items to archive/ instead of deleting.

Rules

  • NEVER delete without confirmation
  • Write the report BEFORE deleting anything
  • If unsure, mark ASK USER
  • Config / .env / data files are NOT dead even if not imported
  • Suggest a git commit before deletion to keep recovery easy

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free