# Pre-ship checklist

The floor for every skill. New or substantially changed skills also go through the audit loop in audit.md.

## Discovery

- [ ] The description says what the skill does, when to use it, and lists trigger phrases, in third person.
- [ ] It names the platform where that matters.
- [ ] It separates this skill from its siblings.
- [ ] Tried on a new task it ought to catch, the skill really fires.

## Leanness

- [ ] SKILL.md is roughly one page and works as an index, far below the 500-line cap.
- [ ] Detail lives in bundled files exactly one level below SKILL.md.
- [ ] Every line passes the cut test.
- [ ] Anything deterministic ships as a script instead of prose the model must re-derive.

## Shape

- [ ] The layer is declared and the content matches it.
- [ ] Numbered procedures never appear in a reference skill.
- [ ] A workflow skill's steps are only the deterministic spine, and it ends in a verification gate.
- [ ] Conventions point at canonical files instead of pasting code that will go stale.

## Naming and wiring

- [ ] No platform prefix; noun for reference, verb phrase for workflow; not vague, not reserved.
- [ ] Registered in the `skills` array of `<plugin>/.claude-plugin/plugin.json`.
- [ ] Plugin version bumped in `.github/plugin/marketplace.json`.
- [ ] A row in the plugin's `index` skill route table.

## House rules

- [ ] Neither the skill nor its examples carry AI, Claude or Anthropic attribution.
- [ ] Each escape hatch says which skill takes over.

## Confidence gate

- [ ] New or substantially changed: the multi-architect audit ran, fixes were applied, and a fresh panel returned `clearsBar: true`.