agentleFS
Sign inStart free
WST2002WST2002/claude-code-skills/skills/proof-of-done-lite/SKILL.md

proof-of-done-lite

Skill4 starsChanged 28 days agoMITView on GitHub

Use before saying work is done, fixed, or complete after changing code. Run the project's checks, show their results, and end with a short verification receipt.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    After your last code change, run the checks that prove it works: typecheck, lint, tests and build.

    line 11
  2. Very specific:

    Run each check plainly. Do not pipe it into tail, head or Select-Object, and do not add || true.

    line 13
  3. Distinctive:

    If a check fails, fix it and run it again.

    line 15
  4. Distinctive:

    If no check can run, end with one line that states why:

    line 22

≈ “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

Proof of Done (lite)

This is the instructions-only version. For enforcement that blocks the agent until checks pass, install the proof-of-done plugin from the claude-code-skills marketplace.

  1. After your last code change, run the checks that prove it works: typecheck, lint, tests and build.
  2. Run each check plainly. Do not pipe it into tail, head or Select-Object, and do not add || true. A hidden exit code is not proof.
  3. If a check fails, fix it and run it again. If you cannot fix it, say so plainly.

  4. End your message with a receipt:

    Verified:

    • npm run lint ✓
    • npm test ✓ (42 passed)

  5. If no check can run, end with one line that states why:

    Verification: skipped — <the specific reason>

Made by Wageesha Tripathi · LinkedIn · Email · More skills

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