Automated summary
Produces a Product Requirements Document through an interactive session run by a Product Manager agent, either for the whole project or for a specific feature.
Strengths
- Guided questioning session before any writing happens
- Pulls in existing project context (brief.md, prd.md, tech-stack.md, CLAUDE.md)
- Outputs a structured PRD: user stories with acceptance criteria, functional and non-functional requirements, MoSCoW prioritization, risks and success metrics
- Cleanly separates the project PRD (memory-bank/prd.md) from per-feature PRDs (memory-bank/features/{name}/prd.md)
Limitations
- Relies on a custom "product-manager" subagent being available in the environment
- Assumes a memory-bank/ folder already exists to benefit from prior context
- PRD quality depends heavily on the user's answers during the iterative session
Use it when you need to formalize scope, user stories and requirements for a product or feature before development starts.
Avoid it for API or architecture reference docs, or when no product-manager subagent is configured.
Security analysis
SafeThe skill only reads project context files (brief.md, prd.md, tech-stack.md, CLAUDE.md) and writes a PRD markdown file into memory-bank/. The single shell command is a scoped `mkdir -p {output_dir}` for the documentation directory, and the Task tool spawns a product-manager subagent to conduct an interactive requirements interview. No network calls, no credential access, no destructive or obfuscated operations.
No concerns found
How this analysis is madeExamples
/prd We're building a habit-tracking app for freelancers. Help me define the MVP scope and requirements./prd --feature=dark-mode Add a dark mode theme across the app, then write the PRD.Define requirements for our team invitation flow and create the PRD when we're done.name: prd description: Create a Product Requirements Document. Interactive session to define features, requirements, and scope. triggers:
- "/prd"
- "create prd"
- "créer un prd"
- "define requirements"
- "définir les besoins"
- "write the prd"
- "rédiger le prd" tools: Read, Write, Grep, Glob, Task context: fork args:
- name: feature description: Feature name for feature-specific PRD (creates in features/{name}/) required: false
PRD Skill
Interactive session to create a Product Requirements Document.
Usage
/prd # Main project PRD → memory-bank/prd.md
/prd --feature=dark-mode # Feature PRD → memory-bank/features/dark-mode/prd.md
Behavior
- Determine output location based on
--featureparameter - Spawn the Product Manager agent to conduct the requirements session
- Agent reads existing context (brief.md) and asks clarifying questions
- User and agent iterate until user says "generate", "create the prd", or similar
- Create the PRD at the appropriate location
Instructions
When this skill is invoked:
-
Parse arguments:
- If
--feature=Xprovided, setfeature_name = X - Otherwise,
feature_name = null(main project PRD)
- If
-
Determine paths:
If feature_name: output_dir = memory-bank/features/{feature_name}/ output_file = memory-bank/features/{feature_name}/prd.md Else: output_dir = memory-bank/ output_file = memory-bank/prd.md -
Check for existing context:
Read memory-bank/brief.md if it exists Read memory-bank/prd.md if it exists (for feature PRDs, understand main product) Read memory-bank/tech-stack.md if it exists Read CLAUDE.md if it exists -
Create output directory if needed:
mkdir -p {output_dir} -
Spawn the Product Manager agent: Use the Task tool with
subagent_type: "product-manager"(custom agent).Prompt for the agent:
You are creating a PRD for: {feature_name or "the main product"} Existing context: - Brief: {summary of brief.md if exists} - Main PRD: {summary if feature PRD and main prd.md exists} - Tech Stack: {summary if exists} Your goal: 1. Understand the scope (MVP vs future) 2. Define user stories with acceptance criteria 3. Document functional and non-functional requirements 4. Prioritize using MoSCoW 5. When ready, create {output_file} Start by confirming your understanding of what we're building, then ask about the main user flows. User's initial input: {user's message if any} -
Let the agent run the interactive session
-
Output: PRD file at determined location
Output Location
# Main project
memory-bank/
└── prd.md
# Feature-specific
memory-bank/
└── features/
└── {feature-name}/
└── prd.md
PRD Template
The agent should create a PRD following this structure:
# PRD: {Feature/Product Name}
## Overview
{One paragraph summary}
## Goals
- Primary: {main objective}
- Secondary: {supporting objectives}
## Non-Goals (Out of Scope)
- {Explicit exclusions}
## User Stories
### Core User Flows
1. **{Flow Name}**
- As a {user}, I want to {action} so that {benefit}
- Acceptance Criteria:
- [ ] {criterion 1}
- [ ] {criterion 2}
### Secondary Flows
{Same format}
## Functional Requirements
### {Feature Area 1}
| ID | Requirement | Priority | Notes |
|----|-------------|----------|-------|
| FR-1 | {requirement} | Must | {notes} |
| FR-2 | {requirement} | Should | {notes} |
## Non-Functional Requirements
| Category | Requirement | Target |
|----------|-------------|--------|
| Performance | Page load time | < 2s |
| Security | Authentication | {method} |
## Dependencies
- {External services, other features}
## Risks & Mitigations
| Risk | Impact | Mitigation |
|------|--------|------------|
| {risk} | H/M/L | {mitigation} |
## Success Metrics
- {Metric}: {target}
## Open Questions
- {Questions for tech team}
Next Step
After creating the PRD, suggest:
"PRD saved to
{output_file}. Next:
/tech-stackto define the technical stack- Or
/implementation-planif stack is already decided"
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-a-product-requirements-document-prd-mrwakc7q/download' --output '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md.part' && mv '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md.part' '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md' && test -s '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/prd' && cp -R '.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q' '.claude/skills/prd'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/create-a-product-requirements-document-prd-mrwakc7q'openskills read 'create-a-product-requirements-document-prd-mrwakc7q'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/create-a-product-requirements-document-prd-mrwakc7q/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.