Important: This skill creates PRDs only—it does NOT begin implementation. </objective>
<quick_start>
- Ask 3-5 clarifying questions with lettered options (A, B, C, D)
- Generate structured PRD based on answers
- Save to
tasks/prd-[feature-name].md</quick_start>
- Problem/Goal: What problem does this solve? Who benefits?
- Core Functionality: What are the must-have features?
- Scope/Boundaries: What is explicitly NOT included?
- Success Criteria: How will we know this worked?
Each question should have 3-4 concrete options (A, B, C, D format) plus "Other" for custom input. </step>
<step name="2_generate_prd"> Create the PRD document with these sections:- Introduction/Overview – Brief feature description and problem statement
- Goals – Specific, measurable objectives
- User Stories – Each with title, description, and verifiable acceptance criteria
- Functional Requirements – Numbered explicitly (FR-1, FR-2, etc.)
- Non-Goals – Clear scope boundaries
- Design Considerations – UI/UX requirements (if applicable)
- Technical Considerations – Constraints and dependencies (if applicable)
- Success Metrics – Measurable outcomes
- Open Questions – Remaining clarifications needed </step>
Use kebab-case for feature name (e.g., prd-user-authentication.md).
</step>
Good: "Login button redirects to /dashboard on success" Bad: "Login works correctly" </principle>
<principle name="ui_stories"> Every UI-focused user story MUST include this acceptance criterion: `"Verify in browser using dev-browser skill"` </principle> <principle name="atomic_stories"> Each user story should be small enough to implement in one session. If a story feels too large, break it into smaller stories. </principle> </principles><prd_template>
# PRD: {{Feature Name}}
## 1. Introduction
{{Brief description of the feature and the problem it solves}}
## 2. Goals
- {{Goal 1: Specific, measurable objective}}
- {{Goal 2: Specific, measurable objective}}
## 3. User Stories
### US-1: {{Story Title}}
**As a** {{user type}}, **I want** {{feature}} **so that** {{benefit}}.
**Acceptance Criteria:**
- {{Specific, testable criterion}}
- {{Specific, testable criterion}}
- Verify in browser using dev-browser skill (for UI stories)
### US-2: {{Story Title}}
...
## 4. Functional Requirements
- **FR-1**: {{Explicit requirement}}
- **FR-2**: {{Explicit requirement}}
- **FR-3**: {{Explicit requirement}}
## 5. Non-Goals
- {{What this feature explicitly does NOT do}}
- {{Scope boundary}}
## 6. Design Considerations
{{UI/UX requirements, wireframe references, design patterns}}
## 7. Technical Considerations
{{Constraints, dependencies, integration points, performance requirements}}
## 8. Success Metrics
- {{Measurable outcome 1}}
- {{Measurable outcome 2}}
## 9. Open Questions
- [ ] {{Unresolved question needing clarification}}
</prd_template>
<examples> <example name="good_acceptance_criteria"> **Good:** - "Search results display within 2 seconds" - "Error message shows 'Invalid email format' for malformed input" - "Clicking 'Save' disables button and shows spinner until complete"Bad:
- "Search is fast"
- "Shows appropriate error messages"
- "Good UX on save" </example>
<success_criteria> PRD is complete when:
- 3-5 clarifying questions were asked and answered
- All 9 PRD sections are filled with concrete content
- User stories have verifiable acceptance criteria
- UI stories include browser verification criterion
- Functional requirements are numbered (FR-1, FR-2, etc.)
- Non-goals clearly define scope boundaries
- Document saved to
tasks/prd-[feature-name].md - No implementation has begun (PRD only) </success_criteria>