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

housekeeping

Skill1 starsChanged 31 days agoMITView on GitHub

Sync shared project docs after implementation work and clean temporary artifacts. Use when the user asks for housekeeping, doc sync, cleanup after a feature, or wants ROADMAP, DECISIONS, AGENTS, README, and CLAUDE updated to match the codebase.

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the post-implementation sync pass that keeps project state documents accurate.

    line 8
  2. Very specific:

    Read ROADMAP.md, recent git history, and the changed files.

    line 11
  3. Very specific:

    Update ROADMAP.md statuses with the current date where appropriate.

    line 12
  4. Distinctive:

    Update AGENTS.md when structure, commands, dependencies, or gotchas changed.

    line 13
  5. Distinctive:

    If CLAUDE.md exists, update the matching sections there too.

    line 14
  6. Distinctive:

    Update README.md if setup, usage, or dependencies changed.

    line 15
  7. Very specific:

    Update DECISIONS.md if new architectural decisions were made.

    line 16
  8. Distinctive:

    Remove obvious temporary artifacts such as:

    line 17
  9. Distinctive:

    If the housekeeping ran after a non-trivial implementation, append this self-healing reminder to the output (do NOT execute):

    line 23
  10. Distinctive:

    Keep documentation edits minimal and concrete.

    line 33
  11. Distinctive:

    Never delete source files as part of cleanup.

    line 34
  12. Distinctive:

    If a deletion is ambiguous, ask before removing it.

    line 35
  13. Very specific:

    NEVER run the retrospective skill from inside housekeeping — it must be a fresh context.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 10 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

Housekeeping

Run the post-implementation sync pass that keeps project state documents accurate.

Workflow

  1. Read ROADMAP.md, recent git history, and the changed files.
  2. Update ROADMAP.md statuses with the current date where appropriate.
  3. Update AGENTS.md when structure, commands, dependencies, or gotchas changed.
  4. If CLAUDE.md exists, update the matching sections there too.
  5. Update README.md if setup, usage, or dependencies changed.
  6. Update DECISIONS.md if new architectural decisions were made.
  7. Remove obvious temporary artifacts such as:
    • *.pyc
    • __pycache__/
    • *.proposed
    • scratch files created during the task
  8. Show the resulting git state.
  9. If the housekeeping ran after a non-trivial implementation, append this self-healing reminder to the output (do NOT execute):
    Self-healing pending — recommend running in a SEPARATE session:
  retrospective last

Catches AI-layer drift the implementer can't see from inside its own context.
Skip if the implementation was trivial.

Rules

  • Keep documentation edits minimal and concrete.
  • Never delete source files as part of cleanup.
  • If a deletion is ambiguous, ask before removing it.
  • NEVER run the retrospective skill from inside housekeeping — it must be a fresh context.

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