Agent skill

generate-prd

Generates Product Requirements Documents for new features through guided discovery. Use when starting a new feature, creating specifications, or when user needs help defining requirements with clarifying questions.

Stars 16
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/cfircoo/claude-code-toolkit/tree/main/skills/generate-prd

SKILL.md

Important: This skill creates PRDs only—it does NOT begin implementation.

<quick_start>

  1. Ask 3-5 clarifying questions with lettered options (A, B, C, D)
  2. Generate structured PRD based on answers
  3. Save to tasks/prd-[feature-name].md </quick_start>
  • Problem/Goal: What problem does this solve? Who benefits?
  • Core Functionality: What are the must-have features?
  • Scope/Boundaries: What is explicitly NOT included?
  • Success Criteria: How will we know this worked?

Each question should have 3-4 concrete options (A, B, C, D format) plus "Other" for custom input.

  1. Introduction/Overview – Brief feature description and problem statement
  2. Goals – Specific, measurable objectives
  3. User Stories – Each with title, description, and verifiable acceptance criteria
  4. Functional Requirements – Numbered explicitly (FR-1, FR-2, etc.)
  5. Non-Goals – Clear scope boundaries
  6. Design Considerations – UI/UX requirements (if applicable)
  7. Technical Considerations – Constraints and dependencies (if applicable)
  8. Success Metrics – Measurable outcomes
  9. Open Questions – Remaining clarifications needed

Use kebab-case for feature name (e.g., prd-user-authentication.md).

Good: "Login button redirects to /dashboard on success" Bad: "Login works correctly"

<prd_template>

markdown
# PRD: {{Feature Name}}

## 1. Introduction

{{Brief description of the feature and the problem it solves}}

## 2. Goals

- {{Goal 1: Specific, measurable objective}}
- {{Goal 2: Specific, measurable objective}}

## 3. User Stories

### US-1: {{Story Title}}
**As a** {{user type}}, **I want** {{feature}} **so that** {{benefit}}.

**Acceptance Criteria:**
- {{Specific, testable criterion}}
- {{Specific, testable criterion}}
- Verify in browser using dev-browser skill (for UI stories)

### US-2: {{Story Title}}
...

## 4. Functional Requirements

- **FR-1**: {{Explicit requirement}}
- **FR-2**: {{Explicit requirement}}
- **FR-3**: {{Explicit requirement}}

## 5. Non-Goals

- {{What this feature explicitly does NOT do}}
- {{Scope boundary}}

## 6. Design Considerations

{{UI/UX requirements, wireframe references, design patterns}}

## 7. Technical Considerations

{{Constraints, dependencies, integration points, performance requirements}}

## 8. Success Metrics

- {{Measurable outcome 1}}
- {{Measurable outcome 2}}

## 9. Open Questions

- [ ] {{Unresolved question needing clarification}}

</prd_template>

Bad:

  • "Search is fast"
  • "Shows appropriate error messages"
  • "Good UX on save"

<success_criteria> PRD is complete when:

  • 3-5 clarifying questions were asked and answered
  • All 9 PRD sections are filled with concrete content
  • User stories have verifiable acceptance criteria
  • UI stories include browser verification criterion
  • Functional requirements are numbered (FR-1, FR-2, etc.)
  • Non-goals clearly define scope boundaries
  • Document saved to tasks/prd-[feature-name].md
  • No implementation has begun (PRD only) </success_criteria>

Expand your agent's capabilities with these related and highly-rated skills.

cfircoo/claude-code-toolkit

sqlalchemy-postgres

Expert guidance for SQLAlchemy 2.0 + Pydantic + PostgreSQL. Use when setting up database layers, defining models, creating migrations, or any database-related work. Automatically activated for DB tasks.

16 1
Explore
cfircoo/claude-code-toolkit

ralph-convert-prd

Converts Product Requirements Documents into prd.json format for the Ralph autonomous agent system. Use when preparing PRDs for Ralph execution, breaking down features into atomic user stories, or when the user mentions Ralph, prd.json, or autonomous agent workflows.

16 1
Explore
cfircoo/claude-code-toolkit

ralph-orchestrator

Orchestrates the full Ralph autonomous agent pipeline from requirements gathering to execution. Use when building new features, platforms, or complex tasks that need structured development through spec-interview, PRD generation, and autonomous implementation.

16 1
Explore
cfircoo/claude-code-toolkit

generate-images

Generate and edit images using Nano Banana (Google Gemini image generation). Use whenever Claude Code needs to create new images, edit existing images, generate icons, diagrams, mockups, or any visual content.

16 1
Explore
cfircoo/claude-code-toolkit

create-subagents

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

16 1
Explore
cfircoo/claude-code-toolkit

manage-slash-commands

Expert guidance for creating and managing Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration. This skill should be used when the user asks to "create a slash command", "add a command", "manage commands", "build a command", or mentions slash commands, custom commands, or command configuration.

16 1
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results