agentleFS
ianklassenianklassen/ai-pm-system/skills/prd-writer/SKILL.md

prd-writer

Skill1 starsChanged 7 months agoMITView on GitHub

Use this skill when user asks to create, write, or draft a PRD (Product Requirements Document). Generates structured PRDs with governance framework, problem statements, business goals, use cases, and functional requirements.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use user-research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    user-research

    Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create comprehensive Product Requirements Documents following a structured PRD template format.

    line 8
  2. Distinctive:

    Use the problem statement framework:

    line 46
  3. Distinctive:

    P0: Must have for launch

    line 94
  4. Distinctive:

    Ask clarifying questions (one at a time):

    line 138
  5. Distinctive:

    Create PRD in sections, validating each:

    line 148
  6. Distinctive:

    Use cases and requirements

    line 152
  7. Very specific:

    Google Doc: Use create_document and write_document tools

    line 157
  8. Distinctive:

    Local Markdown: Write to project directory

    line 158
  9. Distinctive:

    Both: Create local source of truth + shareable Google Doc

    line 159
  10. Distinctive:

    Be specific: Avoid vague requirements; include measurable criteria

    line 163
  11. Distinctive:

    Prioritize ruthlessly: Not everything is P0

    line 165
  12. Distinctive:

    Keep it current: Update last modified date with each change

    line 168

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PRD Writer

Create comprehensive Product Requirements Documents following a structured PRD template format. This skill ensures consistent, well-structured PRDs that align with product development standards.

When to Use

  • User explicitly asks for a PRD
  • User wants to document product requirements
  • User needs to formalize a product idea into a structured document
  • User mentions "product requirements", "PRD", or "spec"

PRD Structure

1. Header Section

🚧 Draft | ✅ Approved | 🔄 In Review
LAST UPDATED: [Date]

[PRD Title]
[One-line description of initiative for quick context]

2. Governance Table (RACI)

ROLENAMESREVIEW STATUS
RESPONSIBLE (Drive decision process)PM (Primary Owner): [Name], Design: [Name], Eng: [Name]Not started
ACCOUNTABLE (Ultimate decision authority)[Name]Not started
CONSULTED (Contribute input)[Names]Not started
INFORMED[Names]Not started

3. Background & Current State

  • Current state experience with pain points
  • Industry data and competitive landscape
  • Link to recordings, Figma files, or other references

4. Problem Statements (Customer Problem Framework)

Use the problem statement framework:

Customer Problem:

I am… [narrow description of customer]
I am trying to… [desired outcome]
But… [problem or barrier]
Because… [root cause]
Which makes me feel… [emotion]

Business Problem:

I am… [business unit/team]
I am trying to… [business goal]
But… [challenge]
Because… [root cause]
Which makes me feel… [impact]

5. Ideal State

In a perfect world: [Vision of solved problem]
The biggest benefit to me is: [Primary value proposition]
Which makes me feel: [Emotional outcome]

6. Business Goals and Success Metrics

GOAL/METRICDESCRIPTIONTARGET
[Metric name][Brief description][Target value]

7. Key Features

High-level explanation of feature areas (3-6 features):

  • Feature 1: [Description]
  • Feature 2: [Description]
  • Feature 3: [Description]

8. Use Cases & Functional Requirements

IDPRIORITYPERSONAUSE CASEACCEPTANCE CRITERIA
1.1P0/P1/P2[Persona][As a user, I want...][Criteria for completion]

Priority levels:

  • P0: Must have for launch
  • P1: Important, should have
  • P2: Nice to have

9. Non-Functional Requirements

  • Performance Requirements: Latency, throughput, scalability
  • Security Requirements: Auth, encryption, compliance
  • Legal Requirements: Disclaimers, regulatory compliance
  • Internationalization: Language, locale support
  • Reliability: Uptime SLA, failover

10. Insights and Problem Validation

  • Market Research: SWOT analysis, competitive UI analysis
  • Customer Insights: Research findings, survey data, customer feedback, app reviews
  • Include supporting quotes when available

11. Milestones and Releases

MILESTONETARGET DATEDESCRIPTION
Alpha[Date][Scope]
Beta[Date][Scope]
GA[Date][Scope]

12. Open Questions and Decisions

TYPEDESCRIPTIONPERSON RESPONSIBLESTATUSDATE TO CLOSE
Question/Decision[Description][Name]Not started/Decided[Date]

13. Appendix

RELATED ARTIFACTSDESCRIPTIONLINKS
Related PRDConnected workstream PRDs[Link]
FigmaE2E journeys, wireframes, designs[Link]
ResearchResearch plans and insights[Link]

Workflow

Step 1: Gather Information

Ask clarifying questions (one at a time):

  1. What is the product/feature being defined?
  2. Who is the target user/persona?
  3. What problem does it solve?
  4. What are the key success metrics?
  5. What are the main features?
  6. Any constraints or dependencies?

Step 2: Draft PRD

Create PRD in sections, validating each:

  1. Header and governance
  2. Problem statements
  3. Goals and features
  4. Use cases and requirements
  5. Milestones and appendix

Step 3: Output Options

  • Google Doc: Use create_document and write_document tools
  • Local Markdown: Write to project directory
  • Both: Create local source of truth + shareable Google Doc

Best Practices

  • Be specific: Avoid vague requirements; include measurable criteria
  • Use personas: Reference specific user personas consistently
  • Prioritize ruthlessly: Not everything is P0
  • Include rationale: Explain "why" not just "what"
  • Link evidence: Reference research, data, and prior art
  • Keep it current: Update last modified date with each change

Agentic PRD Extensions

For AI-powered products, include additional sections:

  • Agent Classification: Type, autonomy level, interaction mode
  • AI Trust Profile: Data sensitivity, decision risk, reversibility
  • AI Leverage Points: Where AI adds unique value
  • Guardrails & Safety: Ethical bounds, fallbacks, human escalation
  • Eval Framework: How to measure AI performance

See references/agentic-prd-template.md for the full agentic PRD template.

Reference Templates

TemplateUse Case
references/prd-template.mdStandard PRD with governance, problem statements, requirements
references/agentic-prd-template.mdExtended template for AI/agent products with evals, guardrails, trust

Quick Reference

SectionPurposeKey Content
GovernanceWho decidesWho decides, approves, reviews
Problem StatementWhyCustomer and business pain points
Ideal StateVisionPerfect world outcome
Goals/MetricsSuccessMeasurable targets
Use CasesWhatFunctional requirements
NFRsHowPerformance, security, reliability
MilestonesWhenTimeline and phases

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.