agentleFS
aroyburman-codesaroyburman-codes/pm-skills/skills/prd-writer/SKILL.md

prd-writer

Skill25 starsChanged 9 months agoMITView on GitHub

Generate structured Product Requirements Documents (PRDs) from a feature brief, idea, or problem statement. Covers problem definition, user stories, requirements, success metrics, and launch plan. Adapts to AI/ML product contexts.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use experiment-designer, user-research and 1 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.
  • Dokkabei97Skill

    experiment-designer

    Designs A/B tests and product experiments with hypothesis structuring, sample size calculation, duration estimation, and result interpretation. Unified framework for both product and marketing experiments.

    Also in 3 projects that use this

  • 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

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 1

    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:

    Write 3-5 user stories in the format:

    line 43

“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 Skill

Generate a complete, structured PRD from a feature idea, problem statement, or brief description.

When to Use

  • User needs to write a PRD for a new feature
  • User has an idea and wants it turned into a structured spec
  • User says /prd-writer followed by a feature description
  • Any time a product requirement needs to be documented

Framework: PRD Structure

1. Overview

  • Feature name: Clear, descriptive name
  • Author: [to be filled]
  • Date: Current date
  • Status: Draft / In Review / Approved
  • One-liner: What this feature does in one sentence

2. Problem Statement

  • What problem are we solving? Describe the user pain point or business need
  • Who has this problem? Primary user segment
  • How big is this problem? Estimated impact (users affected, frequency, severity)
  • Why solve it now? Urgency, strategic alignment, competitive pressure

3. Goals & Non-Goals

Goals:

  • 3-5 specific, measurable goals this feature should achieve
  • Each goal maps to a user need or business objective

Non-Goals:

  • Explicitly list what this feature will NOT do
  • Prevents scope creep and sets expectations

4. User Stories

Write 3-5 user stories in the format:

As a [user type], I want to [action] so that [benefit].

Include acceptance criteria for each:

  • Given [context], when [action], then [expected result]

5. Detailed Requirements

Functional Requirements:

IDRequirementPriority (P0/P1/P2)Notes
FR-1
FR-2

Non-Functional Requirements:

  • Performance: Latency, throughput, scalability targets
  • Security: Auth, data handling, compliance
  • Accessibility: WCAG level, screen reader support
  • Reliability: Uptime, error handling, graceful degradation

For AI/ML features, also include:

  • Model requirements: Accuracy, latency, cost per inference
  • Data requirements: Training data, eval data, data pipeline
  • Safety requirements: Content policy, guardrails, fallback behavior
  • Eval criteria: How model quality will be measured

6. UX & Design

  • User flow: Step-by-step walkthrough of the primary flow
  • Key screens/states: Describe the main UI states (loading, empty, error, success)
  • Edge cases: What happens when things go wrong?
  • Design references: Links to mockups/wireframes (placeholder)

7. Technical Approach

  • Architecture: High-level system design
  • Dependencies: APIs, services, teams needed
  • Data model: Key entities and relationships
  • Migration: Any data migration or backward compatibility concerns

8. Success Metrics

  • Primary metric: The one number that tells us this feature worked
  • Secondary metrics (3-4): Supporting indicators
  • Guardrail metrics (2-3): What must NOT regress
  • Measurement plan: How and when to measure

9. Launch Plan

  • Rollout strategy: Feature flag → internal → beta → GA
  • Launch criteria: What must be true before each stage
  • Rollback plan: How to revert if something goes wrong
  • Communication: Who needs to know and when

10. Open Questions

  • List unresolved questions that need stakeholder input
  • Include who should answer each question

Output Format

Generate as clean markdown, ready to paste into Notion, Confluence, Google Docs, or any doc tool. Use tables for requirements. Be specific and actionable — avoid vague language.

Research-First Workflow

  1. Research — Search for comparable features from competitors, best practices, and relevant technical approaches.
  2. Generate the complete PRD following the structure above.
  3. Flag open questions and assumptions that need validation.

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.