agentleFS
Sign inStart free
MelvynxMelvynx/ai-maxxing-skills/skills/brain/cleanup/SKILL.md

cleanup

Skill32 starsChanged 24 days agoMITView on GitHub

Tidy the user's brain. Finds finished, forgotten or empty projects, duplicates, misplaced folders, loose files and old scratch, proposes what to archive, merge or move, and does only what the user approves. Use when the user types /cleanup, says "fais le ménage", "range mon brain", "archive les vieux projets" or the brain feels messy.

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 10 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, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 61 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do only what they picked.

    line 17
  2. Very specific:

    When the user says a flagged project is still alive, set its updated: to today and leave it.

    line 23
  3. Distinctive:

    Fix the links: Search the brain (and the global rules) for each old path you moved and update it.

    line 24
  4. Very specific:

    Save: Commit with git add -A and cleanup: <what was archived, merged or moved>, and push when the brain has a GitHub copy.

    line 25

“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

Keep the brain small, so every session finds the right project fast. The brain is the folder named in the ## Brain section of ~/.claude/CLAUDE.md (default ~/brain): read its AGENTS.md first (layout, hubs, hygiene). Talk to the user in their language, without jargon. Never move, merge or trash anything before the user says yes, and never delete permanently: archive what has value, trash only scratch.

  1. Scan. Run python3 <brain>/.agents/skills/cleanup/scripts/review.py <brain>. It reads every projects/**/About.md (status, updated:, open Roadmap.md boxes), takes the last modification date from git (git log -1 --format=%cs -- <folder>) and from the newest file on disk (whichever is later wins), writes <brain>/.tmp/cleanup-review.html and opens it. The page lists all projects, oldest first, each with a recommendation (Keep, Archive, Trash, Merge into..., Move to...) the user can change, plus a "Copy prompt" button that builds the instruction to paste back here. When python3 is missing, collect the same facts yourself and skip the page. Then look for the candidates below that the page does not cover (merge, move, fix, tidy).
    • Archive: status done still in projects/; nothing changed for 60 days or more; paused for 30 days or more with no open task; a project whose About.md is still mostly "To fill" and never moved.
    • Merge: two projects about the same thing, or a sub-project that duplicates its hub.
    • Move: a project that belongs to a hub but sits at the projects/ root, or in the wrong hub.
    • Fix: a project folder with no About.md, an About.md with no status.
    • Tidy: loose files or folders at the brain root that AGENTS.md does not list, empty folders anywhere, .tmp/ files older than 7 days, *-final*, *-v2* and report files that duplicate an About.md, notes in notes/ideas/ and notes/todos/ older than 90 days.
  2. Propose. Tell the user the page is open: they choose per project, click "Copy prompt" and paste it here. A pasted prompt that starts with "/cleanup : applique mes choix" is their yes (read the "Note générale" and the comment after each -> as instructions, for example a merge target): skip the question below and go to step 3 with exactly their choices. Without a pasted prompt, also show one short numbered list grouped by Archive, Merge, Move, Fix and Tidy, each line with the project and the reason in a few words ("lumail/old-landing: nothing since 14 May"). Recommend a choice and ask in one message: "all", the numbers, or "none". When nothing needs doing, say the brain is clean and stop.
  3. Do only what they picked.
    • Archive: fold the final outcome into About.md (what was done, where the deliverables are), set status: done and updated: to today, trash scratch files, keep deliverables, and move the folder to archives/<folder-name>/ intact.
    • Merge: fold the facts of one About.md and Roadmap.md into the other (one fact, one place), move its files over, and archive the empty one.
    • Move: move the folder into the right hub.
    • Fix: write the missing About.md from what the folder holds, with "To fill" where you would have to guess.
    • Tidy: file each loose file into the project it belongs to, trash empty folders and old scratch, turn an old idea the user still wants into a project with the create-project skill, and trash the rest.
    • When the user says a flagged project is still alive, set its updated: to today and leave it.
  4. Fix the links. Search the brain (and the global rules) for each old path you moved and update it.
  5. Save. Commit with git add -A and cleanup: <what was archived, merged or moved>, and push when the brain has a GitHub copy.
  6. Report. Tell the user in 3 to 5 lines what moved where, how many projects are active now, and that /cleanup once a month keeps it this way.

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