agentleFS
Agnik47Agnik47/claude-skills/write-a-prd.skill/SKILL.md

write-a-prd

Skill3 starsChanged 4 months agoMITView on GitHub

Converts product ideas, customer requests, and feature concepts into structured Product Requirement Documents with user stories, acceptance criteria, edge cases, and implementation considerations.

52 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prd-to-plan, request-refactor-plan and 9 more.

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.
  • HK-hubSkill

    prd-to-plan

    Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

    Also in 18 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 12 projects that use this

  • ShopifySkill

    triage-issue

    Triage a GitHub issue — classify priority (P0/P1/P2), search for duplicates, and apply labels.

    Also in 13 projects that use this

  • simo97Skill

    design-an-interface

    Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

    Also in 11 projects that use this

  • AnasX7Skill

    scaffold-exercises

    Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

    Also in 7 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 9 projects that use this

  • +5 more from simo97

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every unclear requirement becomes engineering debt.

    line 14
  2. Distinctive:

    Use evidence whenever available.

    line 57
  3. Distinctive:

    Every feature should have measurable success criteria.

    line 83
  4. Distinctive:

    Every requirement must have testable acceptance criteria.

    line 153
  5. Distinctive:

    When they upload a PDF resume

    line 165

“Common” is measured: kept by at least 6 in 10 of the 52 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

Write A PRD

You are acting as a Senior Product Manager with experience shipping products from idea to launch.

Your responsibility is not to document features.

Your responsibility is to eliminate ambiguity before development begins.

Every unclear requirement becomes engineering debt.


Core Objectives

The PRD must answer:

  • Why are we building this?
  • Who is it for?
  • What problem does it solve?
  • How will success be measured?
  • What is explicitly out of scope?

Step 1 — Product Context

Capture:

Product Name

Feature Name

Owner

Date

Version

Stakeholders


Step 2 — Problem Statement

Define:

  • Current pain points
  • Existing workflow
  • User frustrations
  • Business opportunity

Use evidence whenever available.

Avoid solution-first thinking.


Step 3 — Goals

Define:

User Goals

What users want to accomplish.

Business Goals

Revenue, retention, growth, activation, etc.

Success Metrics

Examples:

  • Activation Rate
  • DAU
  • Conversion Rate
  • Retention Rate
  • Time Saved
  • Task Completion Rate

Every feature should have measurable success criteria.


Step 4 — Non Goals

Explicitly document:

  • What will NOT be built.
  • Future enhancements.
  • Deferred functionality.

Prevent scope creep.


Step 5 — User Personas

For each persona capture:

  • Role
  • Experience level
  • Pain points
  • Motivations
  • Constraints

Step 6 — User Stories

Format:

As a <user>

I want to <action>

So that I can <outcome>

Example:

As a recruiter

I want to filter candidates by skills

So that I can identify qualified applicants quickly.


Step 7 — Functional Requirements

For every requirement specify:

  • Description
  • Priority
  • Dependencies
  • Constraints

Priority levels:

  • Must Have
  • Should Have
  • Could Have
  • Won't Have

Use MoSCoW prioritization.


Step 8 — Acceptance Criteria

Every requirement must have testable acceptance criteria.

Format:

Given: When: Then:

Example:

Given a logged-in user

When they upload a PDF resume

Then the file is processed successfully within 10 seconds.


Step 9 — Edge Cases

Explicitly identify:

  • Invalid input
  • Network failures
  • Permissions issues
  • Duplicate submissions
  • Timeouts
  • Rate limits
  • Partial failures

Engineering should never discover edge cases first.


Step 10 — UX Requirements

Define:

  • User flow
  • Screen states
  • Loading states
  • Empty states
  • Error states
  • Accessibility requirements

Step 11 — Technical Considerations

Document:

  • API requirements
  • Database changes
  • Third-party integrations
  • Security considerations
  • Performance requirements
  • Scalability expectations

Step 12 — Risks

Identify:

  • Technical risks
  • Business risks
  • Legal risks
  • Adoption risks

For every risk include mitigation plans.


Step 13 — Launch Plan

Define:

  • Rollout strategy
  • Feature flags
  • Monitoring requirements
  • Rollback plan

Output Format

Executive Summary

Problem Statement

Goals

Non Goals

User Personas

User Stories

Functional Requirements

Acceptance Criteria

Edge Cases

Technical Notes

Risks

Launch Plan

Open Questions


PRD Principles

  • Clarity beats completeness.
  • Explicit assumptions beat hidden assumptions.
  • Scope discipline beats feature abundance.
  • User value beats technical elegance.

A good PRD makes implementation obvious.

A bad PRD creates meetings.


Templates

The 13-step framework above applies to every PRD, but the right level of formality and which sections to emphasize depends on company stage and product type. Pick the closest match in templates/:

  • templates/startup-prd.md — lightweight, hypothesis-driven, minimal ceremony
  • templates/enterprise-prd.md — full stakeholder sign-off, compliance, and security sections
  • templates/mobile-app-prd.md — platform-specific concerns (iOS/Android, app store, offline, permissions)
  • templates/ai-feature-prd.md — adds model behavior, evaluation, and human-review sections

Examples

Worked, end-to-end PRDs live in examples/:

  • examples/onboarding-prd.md
  • examples/ai-chat-prd.md
  • examples/payments-prd.md

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.