prd

# /supergraph:prd Turn conversation into a machine-readable PRD. Gives `/supergraph:plan` a concrete spec to work from. Announce: "📋 /supergraph:prd — extracting requirements..." ## Steps ### 1. Read CONTEXT.md (if exists) ```bash head -60 CONTEXT.md 2>/dev/null || echo "No CONTEXT.md" ``` Use domain vocabulary from CONTEXT.md in the PRD — never invent new terms for existing concepts. ### 2. Extract requirements from conversation Gather from current conversation context: - What the user wants to accomplish - Any constraints or non-goals mentioned - Technical decisions already made - Edge cases or concerns raised Ask one clarifying question if a critical piece is missing. Do not ask multiple questions at once. ### 3. Write PRD ```markdown # PRD: [Feature/Fix Name] ## Problem [One paragraph: what is broken or missing, and why it matters] ## Solution [One paragraph: the approach — what will be built] ## User Stories - As a [role], I want [action] so that [outcome] - (2-5 stories max) ## Acceptance Criteria - [ ] [Observable, testable condition] - [ ] [Observable, testable condition] - (Each maps to a test in /supergraph:plan) ## Implementation Decisions - [Technology/pattern chosen and why] - [What was explicitly ruled out and why] ## Testing Decisions - [Unit: what gets unit tested] - [Integration: what needs integration tests] - [E2E: what needs Playwright coverage, if any] ## Out of Scope - [Explicitly not included in this work] ## Notes - [Domain terms: a...