prd

Product Requirements Document (PRD)

Overview

Design comprehensive, production-grade Product Requirements Documents (PRDs) that bridge the gap between business vision and technical execution. This skill works for modern software systems, ensuring that requirements are clearly defined. This skill needs only conversation with the user and requires no tools; return the PRD in chat unless the user names another destination.

When to Use

Use this skill when:

• Starting a new product or feature development cycle
• Translating a vague idea into a concrete technical specification
• Defining requirements for AI-powered features
• Stakeholders need a unified "source of truth" for project scope
• User asks to "write a PRD", "document requirements", or "plan a feature"

---

Operational Workflow

Phase 1: Discovery (The Interview)

By default, before writing a single line of the PRD, interrogate the user to fill knowledge gaps. Do not assume context. If the user explicitly asks for an immediate draft or declines questions, proceed and label every unknown (constraints, metrics, stack) as TBD.

Ask about:

• The Core Problem: Why are we building this now?
• Success Metrics: How do we know it worked?
• Constraints: Budget, tech stack, or deadline?

Phase 2: Analysis & Scoping

Synthesize the user's input. Identify dependencies and hidden complexities.

• Map out the User Flow.
• Define Non-Goals to protect the timeline.

Phase 3: Technical Drafting

Generate the document using the Strict PRD Schema below.

---

PRD Quality Standards

Requirements Quality

Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".

# Vague (BAD)
- The search should be fast and return relevant results.
- The UI must look modern and be easy to use.

# Concrete (GOOD)
+ The search must return results within 200ms for a 10k record dataset.
+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
+ The UI must follow the documented design system of the project and achieve 100% Lighthouse Accessibility score.

---

Strict PRD Schema

Follow this structure for the output by default. If the user explicitly requests another structure, use it and keep unknowns labeled TBD:

1. Executive Summary

• Problem Statement: 1-2 sentences on the pain point.
• Proposed Solution: 1-2 sentences on the fix.
• Success Criteria: 3-5 measurable KPIs.

2. User Experience & Functionality

• User Personas: Who is this for?
• User Stories: As a [user], I want to [action] so that [benefit].
• Acceptance Criteria: Bulleted list of "Done" definitions for each story.
• Non-Goals: What are we NOT building?

3. AI System Requirements (If Applicable)

• Tool Requirements: What tools and APIs are needed?
• Evaluation Strategy: How to measure output quality and accuracy.

4. Technical Specifications

• Architecture Overview: Data flow and component interaction.
• Integration Points: APIs, DBs, and Auth.
• Security & Privacy: Data handling and compliance. Refer to sensitive details abstractly, not verbatim.

5. Risks & Roadmap

• Phased Rollout: MVP -> v1.1 -> v2.0.
• Technical Risks: Latency, cost, or dependency failures.

---

Implementation Guidelines

DO (Always)

• Define Testing: For AI systems, specify how to test and validate output quality.
• Iterate: Present a draft and ask for feedback on specific sections.
• Protect Sensitive Data: Keep secrets, keys, tokens and personal data out of the PRD; replace any the user pastes with a short placeholder note, and describe auth at the design level only.

DON'T (Avoid)

• Skip Discovery: Ask at least 2 clarifying questions before drafting, unless the user has already supplied complete context or explicitly asks for an immediate draft; then label unknowns as TBD.
• Hallucinate Constraints: If the user didn't specify a tech stack, ask or label it as TBD. Only name specific third party APIs, libraries or design systems the user supplied or confirmed; label others as TBD and note that they need vetting.

---

Example: Intelligent Search System (abbreviated)

1. Executive Summary

Problem: Users struggle to find specific documentation snippets in massive repositories. Solution: An intelligent search system that provides direct answers with source citations. Success:

• Reduce search time by 50%.
• Citation accuracy >= 95%.

2. User Stories

• Story: As a developer, I want to ask natural language questions so I don't have to guess keywords.
• AC:
  • Supports multi-turn clarification.
  • Returns code blocks with "Copy" button.

3. AI System Architecture

• Tools Required: codesearch, grep, webfetch. (illustrative PRD content only; drafting a PRD requires no tool invocation or network access)

4. Evaluation

• Benchmark: Test with 50 common developer questions.
• Pass Rate: 90% must match expected citations.