agentleFS
scoobydont-666scoobydont-666/shared-claude-skills/skills/definition-of-done/SKILL.md

definition-of-done

Skill1 starsChanged 34 days agoMITView on GitHub

Evaluate implementation, test, review, release and deployment evidence before completion claims; distinguish a reviewable change from a verified deployment.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 4

    Distinctive

    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
  1. Distinctive:

    Tests: Run the full applicable required suite after the last relevant edit.

    line 10
  2. Distinctive:

    CI:: If enabled, inspect current candidate checks.

    line 11
  3. Distinctive:

    Operations: Check idempotence, observable failure, persistence and rollback where applicable.

    line 16
  4. Distinctive:

    Documentation: Keep installation, migration, limitations and ownership accurate.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 8 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

Definition of done

Bind every completion claim to its requested scope and exact candidate revision. Creating a PR, merging a PR, releasing an artifact and verifying deployment are separate outcomes.

  1. Scope: Map every acceptance criterion to observed behavior. Mark unimplemented, blocked or unverified work explicitly. No stub or unwired configuration may satisfy a behavior requirement.
  2. Tests: Run the full applicable required suite after the last relevant edit. Record commands, environment, collected counts and results. No unexplained skip, hidden failure, or zero-test success. Select checks according to risk and the repository's policy.
  3. CI: If enabled, inspect current candidate checks. Pending, unavailable, cancelled and failed checks are not green. Local results do not override a required CI gate. If no CI applies, document the applicable local verification and its limits.
  4. Security and failure: Validate trust boundaries, secret handling, authorization, errors and recovery for changed behavior. A checklist is not a security guarantee.
  5. Review: Satisfy the repository's required independent reviews on the actual candidate. Authors cannot count self-review as independent approval.
  6. Distribution: Inspect the consumed package, skill directory or hook configuration. Resolve every bundled dependency. Verify installation and an actual event/consumer path where that is the requested deliverable.
  7. Deployment, when requested: Bind the immutable artifact and configuration to each intended consumer. Check running revision and user-facing behavior. Source merge alone is not deployment evidence. Do not deploy without existing authorization.
  8. Operations: Check idempotence, observable failure, persistence and rollback where applicable. Elapsed quiet time alone is inconclusive; use deterministic tests as well as meaningful runtime observations.
  9. Documentation: Keep installation, migration, limitations and ownership accurate. Link the issue, PR and verification evidence.

Report IMPLEMENTED, REVIEW_PENDING, CI_PENDING, RELEASED, DEPLOYED, VERIFIED, PARTIAL or BLOCKED only when evidence supports that scope. Mark genuinely inapplicable items N/A with a reason. Continue useful authorized work while a separate gate is unavailable.

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.