Best use case
create-prd is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Create a Product Requirements Document (PRD) for a product feature
Teams using create-prd should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/create-prd/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How create-prd Compares
| Feature / Agent | create-prd | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create a Product Requirements Document (PRD) for a product feature
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
Create a comprehensive Product Requirements Document (PRD) based on the feature description provided. ## Instructions: 1. Parse the arguments: - First argument: Feature description (required) - Second argument: Output path (optional, defaults to `PRD.md` in current directory) 2. Create a well-structured PRD that includes: - **Executive Summary**: Brief overview of the feature - **Problem Statement**: What problem does this solve? - **Objectives**: Clear, measurable goals - **User Stories**: Who are the users and what are their needs? - **Functional Requirements**: What the feature must do - **Non-Functional Requirements**: Performance, security, usability standards - **Success Metrics**: How will we measure success? - **Assumptions & Constraints**: Any limitations or dependencies - **Out of Scope**: What this PRD does NOT cover 3. Focus on: - User needs and business value (not technical implementation) - Clear, measurable objectives - Specific acceptance criteria - User personas and their journey 4. Use the TodoWrite tool to track PRD sections as you complete them ## Example usage: - `/create-prd "Add dark mode toggle to settings"` - `/create-prd "Implement user authentication with SSO" auth-PRD.md` Feature description: $ARGUMENTS ## References - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/instruction-comprehension.md — Fully parse the feature description before drafting; track all multi-part requirements - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/human-authorization.md — Confirm scope and output location before writing; PRD commits product direction - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/skills/intake-start/SKILL.md — Intake validation skill that feeds the requirements context a PRD builds on - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/skills/project-status/SKILL.md — Use to orient within the SDLC phase before generating PRD artifacts
Related Skills
voice-create
Generate custom voice profiles from natural language descriptions by mapping tone, formality, and domain to voice dimensions
soul-create
Generate a SOUL.md identity file from source material, interactive prompts, or an existing voice profile
provenance-create
Create a W3C PROV-compliant provenance record for an artifact
issue-create
Create a new ticket/issue with configurable backend (Gitea, GitHub, Jira, Linear, or local files)
devkit-create-skill
Enable interactive design mode
devkit-create-framework
Comma-separated phase names
devkit-create-extension
Create a new AIWG extension (framework expansion pack) with AI-guided setup
devkit-create-command
Create a new slash command with AI-guided behavior definition
devkit-create-agent
Create a new agent with AI-guided expertise definition following the Agent Design Bible
devkit-create-addon
Create a new AIWG addon with AI-guided setup
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.