prd-implementation-prechecklisted

# PRD Implementation Precheck The Step 1 / Step 2 gate. Catches PRD / TDD ambiguity **before** OpenSpec is generated, so we don't have to retrofit later. ## Core mental model A PRD is implementation-ready when: - Every feature has a **defined boundary** (in/out of scope, both stated) - Every acceptance criterion has a **measurable test hook** - Every cross-team dependency has a **named owner** - Every metric has a **baseline + target + measurement method** - The scope is **broken into shippable stages**, each with its own DoD This skill scans for violations and emits a gap report. ## What this skill produces `PRD_PRECHECK_REPORT.md` with: - Blockers (must fix before proceeding) - Warnings (should fix; can proceed with explicit override) - Suggestions (informational) ## When NOT to use - Writing or expanding a PRD (use `prd`) - Compliance pre-check (use `compliance-precheck` Step 0) - Architecture review (use Plan agent / openspec-new-change) ## Active context bundle **Always load first** 1. This `SKILL.md` 2. The target PRD / TDD file 3. `reference/precheck-checklist.md` — 30+ canonical gaps 4. `reference/severity-rubric.md` ## Workflow 1. **Read** PRD / TDD top to bottom. 2. **Run checklist** — for each item, mark present / missing / vague. 3. **Stage breakdown audit** — does the PRD propose a stage 1 / 2 / 3 split? Each stage has its own DoD? 4. **Metric audit** — every KPI has baseline + target + measurement method? 5. **Dependency audit** — every "needs X from