prd
Verifiedby github · Updated Apr 16, 2026
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
See It In Action
Let me check what's already in the codebase first.
Got it — Flowdeck's activation rate is flat at 34%, the big drop-off is at the blank project board, and Jordan wants an AI assistant experiment shipped by end of July. A couple quick questions before I draft:
Got it — here are my two questions before drafting:
-
UX surface — Jordan mentioned "chatbot-style," but are you leaning toward a chat panel (slide-out drawer), an inline guided flow (replacing the current welcome/empty state), or starting with one and phasing in the other?
-
Success bar — The current activation rate is flat at 34%. What target makes this experiment a win? Something conservative like 40% (+6pt), ambitious like 45% (+11pt), or just any statistically significant lift?
Let me know and I'll generate the PRD right after.
SKILL.md
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.
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)
Before writing a single line of the PRD, you MUST interrogate the user to fill knowledge gaps. Do not assume context.
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 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.
Strict PRD Schema
You MUST follow this exact structure for the output:
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.
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.
DON'T (Avoid)
- Skip Discovery: Never write a PRD without asking at least 2 clarifying questions first.
- Hallucinate Constraints: If the user didn't specify a tech stack, ask or label it as
TBD.
Example: Intelligent Search System
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.
4. Evaluation
- Benchmark: Test with 50 common developer questions.
- Pass Rate: 90% must match expected citations.
FAQ
What does prd do?
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
When should I use prd?
Use it when you need a repeatable workflow that produces text response.
What does prd output?
In the evaluated run it produced text response.
How do I install or invoke prd?
Ask the agent to use this skill when the task matches its documented workflow.
Which agents does prd support?
Agent support is inferred from the source, but not explicitly declared.
What tools, channels, or permissions does prd need?
It uses no extra tools; channels commonly include text; permissions include no explicit permission scopes.
Is prd safe to install?
Static analysis marked this skill as low risk; review side effects and permissions before enabling it.
How is prd different from an MCP or plugin?
A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.
Does prd outperform not using a skill?
About prd
When to use prd
You need to turn a vague product idea into a concrete PRD. You are starting a new feature or product planning cycle. You need a shared requirements document with measurable success criteria and clear non-goals.
When prd is not the right choice
You need the agent to implement or deploy the product rather than document requirements. You already have finalized requirements and only need minor editing or formatting.
What it produces
Produces text response.