agentleFS
stjarnstromstjarnstrom/spec-system/skills/finish/SKILL.md

finish

Skill0 starsChanged 45 days agoMITView on GitHub

Integrate finished work: verify it, then merge locally, push and open a pull request, or keep the branch — and clean up the worktree safely. Use when implementation is done and the branch needs to go somewhere, when the user says "wrap it up", "merge it", "open a PR", or at the end of spec-run.

  • Commits and pushes

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use status, bootstrap and 7 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.
  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 5 projects that use this

  • OpenAISkill

    bootstrap

    Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.

    Also in 3 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 6 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 3

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

    Verify, choose, integrate, clean up.

    line 11
  2. Distinctive:

    Capture where you are: before changing directory: the branch, the base branch (confirm it if unsure), the worktree path (git rev-parse …

    line 19
  3. Distinctive:

    Keep the branch as it is.

    line 27
  4. Very specific:

    Clean up: only what this workflow created: a worktree under .worktrees/ or one the harness's worktree tool made.

    line 47
  5. Very specific:

    No force-push, no reset --hard on a shared branch, no branch -D.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 18 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

Verify, choose, integrate, clean up.

Procedure

  1. Verify. The full suite, typecheck, lint, and — with a spec layer — node specs/registry.mjs check, all with output from this turn. Red stops here: integration waits for green, and the failure is reported.
  2. Capture where you are before changing directory: the branch, the base branch (confirm it if unsure), the worktree path (git rev-parse --show-toplevel), and the main checkout (git rev-parse --git-common-dir).
  3. Choose — or use the choice spec-run's readiness step recorded:

    1. Merge into the base branch locally.
    2. Push and open a pull request.
    3. Keep the branch as it is.

    Pushing and opening a PR act outside the repository: they need the user's yes, given now or at spec-run's readiness step. Discarding work happens only when the user asks for it by name, and after they confirm the exact branch.

  4. Integrate.
    • Merge: from the main checkout, update the base branch, then git merge --no-ff --no-commit <branch> and run the suite on the merged tree before committing. Green → commit the merge and clean up. Red → git merge --abort, keep the work branch, and report; nothing on the base branch changed.
    • Pull request: push the branch and open the PR (gh pr create). The body comes from the plan, not from reading the diff: what changed and why, the statement IDs now true and the tests proving them, the verification commands and their results, rulings made during the run, and anything parked. Keep the worktree until the PR merges.
    • Keep: report the branch and worktree path.
  5. Clean up only what this workflow created: a worktree under .worktrees/ or one the harness's worktree tool made. Remove it with git worktree remove. If git refuses because of untracked or modified files, show them and ask — never force it. Delete the merged branch with git branch -d, which refuses unmerged work.

Rules

  • No force-push, no reset --hard on a shared branch, no branch -D.
  • A rejected push is information: fetch, integrate, re-verify, push again.

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.