← ClaudeAtlas

definition-of-done-toolinglisted

Use when about to claim work is complete, shippable, or ready to release or tag a milestone — run a script that reads declared criteria and emits GO/NO-GO instead of asserting completion from memory; the author never self-certifies.
pedro-angel/agent-methodology · ★ 0 · AI & Automation · score 70
Install: claude install-skill pedro-angel/agent-methodology
# A Script Certifies Done, Not the Author's Memory A definition of done that lives as a checklist in someone's head, or a paragraph in a PR template, decays over a long session — steps get skipped under time pressure, and the person who wrote the code is the worst-positioned person to judge whether they finished it. Make completion a mechanical gate: a script reads a small declared list of criteria, runs every one marked required, and emits a single GO or NO-GO. The author's belief that they're done is a proposal; the script's exit code is the verdict. ## When to use Before claiming any non-trivial unit of work is complete, before cutting a release or tagging a milestone, and before a PR description says "ready for review" or "ready to merge." Red-flag thoughts that mean STOP and apply this skill: - "I've mentally checked everything off, we're good." (Mental checklists decay; a script doesn't.) - "Tests pass, that's the definition of done here." (Is that written down anywhere, or is it just what you remember today?) - "This criterion doesn't really apply, I'll just skip it." (Skipping is a silent deletion; the gate needs a visible `n/a`, not silence.) - "I'll edit the config so it passes." (You're editing the exam, not passing it.) - "Close enough — most of it's green." (One required NO-GO fails the whole gate, by design.) ## The rule 1. **Declare every completion criterion in a small config, one line per criterion, each marked `required` or `n/a`** — never left implic