agentleFS
MorganOnGitHubMorganOnGitHub/tackle/skills/finishing-work/SKILL.md

finishing-work

Skill0 starsChanged 46 days agoMITView on GitHub

Use when implementation is complete and verified, and the work needs to be integrated, handed off, or cleaned up

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Work on a branch or in a worktree: follow the steps below.

    line 13
  2. Distinctive:

    Keep the branch as it is for later

    line 23
  3. Distinctive:

    Leave out options that don't fit.

    line 26
  4. Distinctive:

    Merge: update the base branch, merge, and re-run the tests on the merged result before deleting the feature branch.

    line 28
  5. Distinctive:

    Never force-push, rewrite shared history, or delete work without an explicit request.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Finishing Work

Close the loop: confirm the work holds up, tell the user what they're getting, and integrate it the way they want.

Scale it

  • Trivial / Small, in place: a short summary of what changed and how it was verified. Done.
  • Work on a branch or in a worktree: follow the steps below.

How

  1. Verify the whole change with the full test suite, plus build and lint if the project uses them. If something fails, report it and fix it before offering to integrate.
  2. Summarise: what was built, how it was verified, any deviations from the plan, and anything left unverified or deferred.
  3. Confirm the base branch the work split from (usually main or master; ask if unsure).
  4. Offer the integration options that apply, with a recommendation:

    • Merge into the base branch locally
    • Push and open a pull request
    • Keep the branch as it is for later
    • Discard the work

    Leave out options that don't fit. There's no PR without a remote, and no merge without git.

  5. Carry out the choice:
    • Merge: update the base branch, merge, and re-run the tests on the merged result before deleting the feature branch.
    • PR: push, then create the PR with a summary and a test plan. Follow the project's PR conventions.
    • Keep: report the branch name and workspace path.
    • Discard: list exactly what will be deleted (branch, commits, workspace) and get explicit confirmation first.
  6. Clean up worktrees or scratch copies once they're no longer needed. Keep them if the user may come back (Keep, or a PR under review).

Never force-push, rewrite shared history, or delete work without an explicit request.

Skip or shorten when

  • The user has already said how to integrate. Do that.
  • There's no git. Summarise, and point to any scratch copies.

Done means

The user knows what was delivered and how it was verified, the chosen integration is complete, and nothing is left dangling.

Next

None. The work is done.

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.