agentleFS
vtmocanuvtmocanu/skills/skills/done/SKILL.md

done

Skill2 starsChanged 5 days agoMITView on GitHub

Wraps up a working session. Checks git state in every directory the session touched, removes git artifacts the session created once they are safely unneeded, reviews unfinished work, and gives a plain verdict on whether the session can close, leaving its session-peers channels when it can. Use when the user invokes /done or asks whether the session is done or can be closed.

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use simplify, work and 4 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.
  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 5 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 3 projects that use this

  • OpenAISkill

    transcribe

    Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 9 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Git: run git status in the current repo and any other working directory we touched this session.

    line 16
  2. Distinctive:

    Cleanup, without asking: remove git artifacts this session created that are no longer needed (worktrees, local branches, temporary refs, …

    line 17
  3. Distinctive:

    Never force a removal past git's own safety checks, except deleting a branch whose work the preservation test above has proven.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 33 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

Done

Document Location

This document is located at: ~/stuff/gitrepos/gh/vtmocanu/skills/skills/done/SKILL.md (public repo: github.com/vtmocanu/skills)

Note: This is the source of truth. The installed copy at ~/.claude/skills/done/SKILL.md is derived from this file by the npx skills package manager; edit here, then run npx skills update to re-pull it. Never edit the installed copy.

Are we done here? Can we close this session? Decide and tell me, after checking:

  • Git: run git status in the current repo and any other working directory we touched this session. Report uncommitted, unstaged, untracked, and unpushed changes (where an upstream exists, git log --oneline @{u}..). If everything is committed and pushed, say so in one line.
  • Cleanup, without asking: remove git artifacts this session created that are no longer needed (worktrees, local branches, temporary refs, throwaway clones). Remove one only when all hold; otherwise leave it and report it:

    • this session created it, still owns it, and nothing uses it: not handed to another session, not backing a running check or review;
    • nothing in it is needed, ignored files included;
    • its current tip is preserved: it equals a merged PR's final head, or every commit is on the remote according to freshly fetched state (stale or deleted tracking refs do not count). A squash merge counts only by the final-head match, never by ancestry. A tools or review tree counts as never holding work only while it still sits at the commit it was created on.

    Never force a removal past git's own safety checks, except deleting a branch whose work the preservation test above has proven. Never touch the main worktree, stashes, remote branches, or anything another session or the user created. List what you removed.

  • Outstanding work: review this session for anything unfinished: partial edits, failed or skipped steps, open TODOs, loose ends.

Then give me a plain verdict: can we close the session, or is there something left to do?

If the verdict is that the session can close, then leave its session-peers channels. Run peers.py leave from the installed session-peers skill, ~/.agents/skills/session-peers/scripts/peers.py, else ~/.claude/skills/session-peers/scripts/peers.py; if neither exists, skip this step. leave takes the session out of every stored channel it is in and out of #general. Report its output and exit code. On a non-zero exit, name what was not left, do not retry, and do not change the verdict. Skip the step when anything is left to do or the session stays open.

Apart from that cleanup and the channel leave, do not commit, push, or change anything; report only.

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.