agentleFS
Sign inStart free
brain-marchinebrain-marchine/verify-done-skills/skills/verify-done/SKILL.md

verify-done

Skill0 starsChanged 4 months agoMITView on GitHub

Fail-closed verification before accepting Done/Fixed/做完了. Use when the user or agent claims a task is finished, fixed, complete, verified, or ready to merge — including UI fixes, bug fixes, overflow, layout, tests passing, or "I'm done". Also trigger for 做完了、修好了、验收、验证完成、可以合并. Runs bundled check scripts and refuses verbal Done until PASS.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ship, debug and 1 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.
  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 4 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 3 projects that use this

  • BlockSkill

    plan

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

    Also in 3 projects that use this

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. domengabrovsek/agent-config★ 22same name
    2. domengabrovsek/claude★ 22same name
    3. AbdurRafay2004/handoff★ 4same name
    4. Roberdan/roberdan-os★ 2same name
    5. alexgrebeshok-coder/dirigent-skills★ 0same name
    6. DefaultPerson/iron-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    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. Distinctive:

    Prefer running the bundled script over inventing your own checklist.

    line 27
  2. Very specific:

    If the script path is unclear, locate SKILL.md for this skill and run scripts/check.mjs next to it.

    line 28

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

Agent said Done. Reality must agree.

You MUST run verification before saying the work is finished. Verbal "Done / Fixed / 做完了" without a PASS from the scripts below is Fake Done — forbidden.

When this skill applies

  • User or you claim: Done, Fixed, complete, finished, verified, LGTM, ready to merge
  • Chinese: 做完了、修好了、弄好了、验收通过、可以提交
  • Any UI / layout / overflow / bugfix claim

Hard rules

  1. Do not say Done / Fixed / 做完了 until the check script exits 0 (PASS).
  2. On FAIL (exit 1): show evidence, keep fixing, re-run the script.
  3. Prefer running the bundled script over inventing your own checklist.
  4. If the script path is unclear, locate SKILL.md for this skill and run scripts/check.mjs next to it.

Procedure

1. Locate this skill

Common install paths:

  • Project Cursor: .cursor/skills/verify-done/
  • Project Claude: .claude/skills/verify-done/
  • User Cursor: ~/.cursor/skills/verify-done/
  • User Claude: ~/.claude/skills/verify-done/

2. Run the check (from the user's project root)

node "<path-to-verify-done>/scripts/check.mjs" --cwd . --claim "<exact claim text>"

Windows PowerShell example:

node "$PWD\.cursor\skills\verify-done\scripts\check.mjs" --cwd . --claim "Fixed the inventory overflow"

Optional demo URL check (when a local page should prove a UI fix):

node "<path-to-verify-done>/scripts/check.mjs" --cwd . --claim "Fixed overflow" --url http://127.0.0.1:4173

3. Report in chat (required template)

## verify-done: FAIL | PASS
- Claim: ...
- Checks: git_diff | fake_tests | npm_test | url_probe (list which ran)
- Evidence: (paste key lines from script stdout)
- Next: (if FAIL, concrete fix steps; if PASS, you may say Done)

4. Only after PASS

You may say the work is done. Summarize what passed.

What the script checks

CheckBehavior
git_diffClaimed a fix but no file changes → FAIL
fake_testsVacuous tests (expect(true).toBe(true), empty bodies, it.todo) → FAIL
npm_testIf package.json has test script, runs it (skip if missing)
url_probeIf --url given, FAIL when page still contains overflow-bug / LAYOUT BROKEN

Details: references/fake-done.md

Anti-patterns (do not do)

  • "Tests are green in my head" without running the script
  • Editing the script to force PASS
  • Saying Done because the user sounded impatient
  • Skipping verify on "tiny" UI claims — those are Fake Done hotspots

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