Create a product requirement document (PRD) for a new feature.

MITAuto-check passedProduct & Project Management

Install Create Prd

skills CLI
$ npx skills add platformplatform/PlatformPlatform --skill create-prd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install platformplatform/PlatformPlatform create-prd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/platformplatform/PlatformPlatform.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/create-prd .claude/skills/create-prd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
create-prd
GitHub stars
440
Token cost
~3k tokens
SKILL.md length
1,111 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Create a product requirement document (PRD) for a new feature.

  • Works in 6 steps: Initialize [PRODUCT_MANAGEMENT_TOOL] → Ask what [feature] to build → Research and understand the [feature] → …
  • The user wants to create a new feature
  • SKILL.md covers Mandatory Preparation, Workflow and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Create Prd is an agent skill from platformplatform/PlatformPlatform. Create a product requirement document (PRD) for a new feature. Use when the user wants to create a new feature, plan a feature, or write a PRD.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: A platform designed for building enterprise-grade, multi-tenant products using Azure, .NET, React, TypeScript, Infrastructure as Code, etc. The licence is MIT.

When your agent uses it

  • The user wants to create a new feature
  • Tasks that involve PRD writing

Example prompts

  • “/create-prd”

Requirements

  • Pre-approved tools (allowed-tools): *

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Initialize [PRODUCT_MANAGEMENT_TOOL]
  2. Ask what [feature] to build
  3. Research and understand the [feature]
  4. Interactive requirements wizard
  5. Draft the complete PRD and get approval
  6. Create [feature] and [tasks] in [PRODUCT_MANAGEMENT_TOOL]

What it can do on your machine

Read from SKILL.md and the folder at commit 269de1c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • *

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create Prd loads about 3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 1,111 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from platformplatform/PlatformPlatform at commit 269de1c, republished under its MIT licence (© platformplatform). 1,111 words, ~2,983 tokens.

Download SKILL.mdSave it as .claude/skills/create-prd/SKILL.md (or your agent's skills folder).
name
create-prd
description
Create a product requirement document (PRD) for a new feature. Use when the user wants to create a new feature, plan a feature, or write a PRD.
allowed-tools
*

Create PRD Workflow

Your job is to work with the user through an interactive wizard to create a high-level PRD using language that is easy to understand for non-technical people. The PRD defines a [feature] with all [tasks] to be created in [PRODUCT_MANAGEMENT_TOOL].

Team leads: execute this workflow directly. Do not delegate it.

Mandatory Preparation

  1. Read [PRODUCT_MANAGEMENT_TOOL]-specific guide at /.claude/reference/product-management/[PRODUCT_MANAGEMENT_TOOL].md to understand terminology, status mapping, ID format, and MCP configuration.

Workflow

Follow the steps below to create the PRD.

Step 1: Initialize [PRODUCT_MANAGEMENT_TOOL]

Follow initialization steps in /.claude/reference/product-management/[PRODUCT_MANAGEMENT_TOOL].md.

Step 2: Ask what [feature] to build

Use the AskUserQuestion tool to ask the user what [feature] they want to build:

AskUserQuestion with:
- question: "What feature would you like to build?"
- header: "Feature"
- multiSelect: false
- options:
  - label: "New feature", description: "Create a new feature"
  - label: "Enhancement", description: "Enhance existing functionality"

Users will typically use the custom text option to describe their [feature].

If the user's answer comes back empty:

  • Tell the user to enable Plan Mode and try again
  • STOP the workflow

If you receive a valid answer:

  • Use the text they entered as the [feature] description for research
Step 3: Research and understand the [feature]

Conduct deep research for a feasible solution that takes the existing codebase and [features] into consideration:

  • Understand the user's requirements and business context
  • Investigate the current state and implementation in the codebase:
    • Specify which self-contained system (e.g., main, account) the [feature] belongs to. Back-office features live under account/Core/Features/BackOffice/ and are served on the back-office host.
    • Respect the multi-tenant nature: design [features] to work for one tenant by default, unless otherwise specified
  • Use MCP tools (like context7 for library docs), Perplexity for online research, or web research for best practices and technologies
  • Read relevant code files and rule files to understand patterns and conventions
Step 4: Interactive requirements wizard

Now that you've done research, ask the user ALL required questions in ONE single AskUserQuestion call:

AskUserQuestion with 3 questions:

Question 1 - Feature name:
- question: "What is the name of this feature? (Use sentence case, e.g., 'User management' not 'User Management')"
- header: "Feature name"
- multiSelect: false
- options:
  - label: "Custom name", description: "Enter your feature name"

Question 2 - Self-contained system (put the most likely SCS first based on research):
- question: "Which self-contained system (SCS) should this feature belong to?"
- header: "SCS"
- multiSelect: false
- options:
  - label: "account", description: "Tenant and user management system (also hosts the back-office surface for support and system admin tools)"
  - label: "main", description: "Primary shell application where you build your product"
  - label: "[Suggested SCS based on research]", description: "Based on my analysis"

Question 3 - E2E tests:
- question: "Should this PRD include Playwright end-to-end tests?"
- header: "E2E Tests"
- multiSelect: false
- options:
  - label: "Yes", description: "Include E2E tests as a separate [task]"
  - label: "No", description: "Skip E2E tests for now"

Ask additional questions:

After the first 3 questions, ask additional relevant questions to gather comprehensive requirements. Use multiple AskUserQuestion calls (max 4 questions per call, max 4 options per question).

Ask as many questions as needed to understand:

  • User roles and permissions
  • Complexity level (simple CRUD, workflow-based, complex logic)
  • Integration points with existing features
  • Validation rules and constraints
  • Edge cases to consider
  • Data relationships and dependencies

The more questions you ask, the better the PRD.

Implementation approach:

AskUserQuestion with:
- question: "Should we create frontend mockups first for UI/UX exploration?"
- header: "Approach"
- multiSelect: false
- options:
  - label: "Yes", description: "Frontend mockups first to validate UI/UX before backend"
  - label: "No", description: "Backend-first approach (default)"
Step 5: Draft the complete PRD and get approval

Based on all the research and user answers, draft the complete PRD.

Create the PRD content following the example PRD structure:

  1. High-level PRD description:

    • Use sentence case for level-1 headers
    • Stay at a high level—no implementation details or code examples
    • Use correct domain terminology: multi-tenant, self-contained system, shared kernel, tenant, user, etc.
    • Specify which self-contained system(s) are in scope
    • Avoid repetition
  2. [Tasks] section structured based on wizard answers:

    Examples based on common patterns:

    Example 1 - Backend-first approach (default):

    • Backend implementation
    • Frontend implementation
    • E2E tests (if E2E tests selected)

    Example 2 - Frontend-first approach:

    • Frontend mockups/prototypes with static data
    • Backend implementation based on frontend contract
    • Integration (connect frontend to backend)
    • E2E tests (if E2E tests selected)

    Example 3 - Backend-only [feature]:

    • Backend implementation (API endpoints, commands, queries, migrations, tests)

    Example 4 - Large complex [feature]:

    • Backend core functionality
    • Frontend core UI
    • Backend advanced functionality
    • Frontend advanced features
    • E2E tests (if E2E tests selected)

    Note: These are examples only. Adapt the [task] structure to match the actual [feature] requirements, scope, and user answers. All work is sequential -- one [task] fully completed before the next starts.

  3. [Task] guidelines:

    • Each [task] should be a logical grouping (e.g., "all backend", "all frontend", "all e2e tests")
    • Keep [tasks] focused (one commit per [task])
    • Write a clear paragraph describing what each [task] delivers
    • Each [task] represents a complete vertical slice that can be implemented, reviewed, and committed independently
    • Repeat all relevant business rules in each task description (permissions, validations, constraints)
    • Engineers/reviewers only read the task description, not the feature overview
    • List [tasks] in implementation order (the order they should be implemented)
    • E2E tests should typically be the final [task]
    • Important: When using MCP-based [PRODUCT_MANAGEMENT_TOOL], create [tasks] in the same order they appear in the PRD—this defines the implementation sequence

Example of WRONG task description (missing business rules):

### 1. Backend for team management

This task implements team CRUD operations with API endpoints and tests.

- Create Team aggregate
- Create CreateTeam command
- Create API endpoints
- Create tests

Example of CORRECT task description (includes business rules):

### 1. Backend for team management

This task implements team CRUD operations with API endpoints and tests. Teams are managed by Tenant Owners and Admins only. Team names must be unique within a tenant.

- Create Team aggregate with name uniqueness validation
- Create CreateTeam command with Owner/Admin permission guard
- Create UpdateTeam command with Owner/Admin permission guard
- Create DeleteTeam command with Owner/Admin permission guard
- Create API endpoints for all operations
- Create tests covering permissions (403 for non-owners/admins), name uniqueness, tenant isolation
  1. Frontend task descriptions - use ASCII art fat marker sketches:

For frontend tasks, include ASCII art fat marker sketches showing UI layout and components:

### 2. Frontend for user management

This task implements the Users page UI. Users can only be managed by Tenant Owners or Admins.

┌─────────────────────────────────────────┐
│ Users                   [+ Invite user] │
├─────────────────────────────────────────┤
│ ┌─────────────────────────────────────┐ │
│ │ Email           Name         Role   │ │
│ ├─────────────────────────────────────┤ │
│ │ admin@...       John Doe     Owner  │ │
│ │ member@...      Jane Smith   Member │ │
│ └─────────────────────────────────────┘ │
└─────────────────────────────────────────┘

- Add Users navigation menu item
- Create Users page with table
- Create CreateUserDialog (validates email uniqueness)
- Show/hide [+ Invite user] button based on role (Owner/Admin only)
- Create UserDetailsSidePane
- Integrate all API operations

ASCII sketches help engineers visualize the UI before coding.

Show the complete PRD to the user - display the full content including all [tasks] with their descriptions.

Ask for approval: "Does this PRD look good?" (Yes/No)

  • If No: Ask what to change, update the PRD content, show again, repeat approval
  • If Yes: Continue to Step 6
Show full SKILL.md (348 more words)Show less
Step 6: Create [feature] and [tasks] in [PRODUCT_MANAGEMENT_TOOL]

Follow your [PRODUCT_MANAGEMENT_TOOL]-specific guide at /.claude/reference/product-management/[PRODUCT_MANAGEMENT_TOOL].md to understand how to create items based on the PRD.

Create:

  • [feature] with name=[feature name from Step 4 wizard], assign to "me"
  • [task] for each [task] in the PRD with:
    • Title: [task title] (sentence case)
    • Description: [task description paragraph] + [subtask bullets] (use bullets, NOT checkboxes)
    • Link to parent [feature]
    • Assign to "me"
  • Initialize all items in [Planned] status, in the current iteration/sprint

Each [task] description must include:

  1. A paragraph explaining what the task delivers
  2. Bullet points (NOT checkboxes) listing the subtasks for implementation guidance

After creating all [tasks], update each [feature]'s description in [PRODUCT_MANAGEMENT_TOOL] with the full PRD content for that [feature] -- the intro paragraph, overview section, and core changes section (everything above the "Tasks overview" heading). This ensures the PRD context is available to anyone viewing the [feature] in [PRODUCT_MANAGEMENT_TOOL].

Inform user: The [feature] and all [tasks] have been created in [PRODUCT_MANAGEMENT_TOOL]. Ask the user if they would like to start implementing the first task now.

Guidelines

✅ DO:

  • Follow the exact structure in the example PRD
  • Conduct deep research by reading code, consulting rule files, and using MCP tools
  • Specify the self-contained system for the [feature]
  • Respect multi-tenant design by default
  • Keep the PRD high level without code snippets
  • Ask comprehensive questions in Step 4 to gather all requirements
  • Show PRD for approval (Step 5) before creating anything
  • Use the AskUserQuestion tool for all wizard questions in Plan Mode

❌ DON'T:

  • Write PRDs as user stories—use the example structure
  • Include implementation details or code examples in the PRD
  • Skip research—always understand the problem first
  • Ignore rule files
  • Repeat information across sections
  • Write titles in Title Case—use sentence case
  • Create [feature] or [tasks] in [PRODUCT_MANAGEMENT_TOOL] before getting PRD approval in Step 5
  • Rename the file—must be prd.md
  • Save questions in the PRD file
  • Create [tasks] that split tests, implementation, and migrations across separate [tasks]—each [task] must be a complete vertical slice
  • Ask the user clarifying questions before Step 4

Do the research. Read code and rule files. Ask comprehensive questions. Create excellent PRDs.

© platformplatform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/create-prd of platformplatform/PlatformPlatform.

Open the folder on GitHubat commit 269de1c

Compare with similar skills

Create Prd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Create Prd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Prd this skillplatformplatform/PlatformPlatform440—~3kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed
  • To Issues

    ywwynm/EverythingDone

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    144 GitHub starsUsed in 12 repos~893 tokens
    Product & Project ManagementAuto-check passed

More from platformplatform/PlatformPlatform

All 18 skills in this repo
  • Rebuild Branch

    platformplatform/PlatformPlatform

    Rebuild a stale branch by cherry-picking each commit onto a fresh branch off main, using a ralph-loop to validate each commit (build, test, format, lint, optional e2e) before moving on.

    440 GitHub stars~2.1k tokensUpdated 13 days ago
    Auto-check: notes
  • Swc Plugin Compatibility

    platformplatform/PlatformPlatform

    Diagnose and fix Lingui SWC plugin compatibility errors with Next.js, Rspack, or other SWC runtimes.

    440 GitHub stars~873 tokensUpdated 13 days ago
    Auto-check passed
  • Aspire Restart

    platformplatform/PlatformPlatform

    Start or restart the .NET Aspire AppHost via the developer CLI.

    440 GitHub stars~415 tokensUpdated 13 days ago
    Auto-check passed
  • Commit

    platformplatform/PlatformPlatform

    Commit session changes to git. An agent skill from platformplatform/PlatformPlatform.

    440 GitHub stars~567 tokensUpdated 13 days ago
    Auto-check passed
  • E2E

    platformplatform/PlatformPlatform

    Run end-to-end Playwright tests via the developer CLI. An agent skill from platformplatform/PlatformPlatform.

    440 GitHub stars~542 tokensUpdated 13 days ago
    Auto-check passed
  • Enhanced Message Context

    platformplatform/PlatformPlatform

    Provide additional context for messages based on the codebase and the context of the message to improve the quality of the translations.

    440 GitHub stars~1.6k tokensUpdated 13 days ago
    Auto-check passed

Questions about Create Prd

What does Create Prd do?

Create a product requirement document (PRD) for a new feature. Create Prd is an agent skill from platformplatform/PlatformPlatform. Create a product requirement document (PRD) for a new feature.

When should I use Create Prd?

Create Prd fits situations like: the user wants to create a new feature; tasks that involve PRD writing.

How do I install Create Prd in Claude Code?

Run `npx skills add platformplatform/PlatformPlatform --skill create-prd -a claude-code`. Or copy the skill folder (.claude/skills/create-prd in platformplatform/PlatformPlatform) into .claude/skills/create-prd in your project. Claude Code loads it when a task matches its description.

How do I install Create Prd in Codex?

Run `npx skills add platformplatform/PlatformPlatform --skill create-prd -a codex`. Or copy the skill folder (.claude/skills/create-prd in platformplatform/PlatformPlatform) into .agents/skills/create-prd in your project. Codex loads it when a task matches its description.

Can I use Create Prd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add platformplatform/PlatformPlatform --skill create-prd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-prd, .gemini/skills/create-prd, .github/skills/create-prd and .opencode/skills/create-prd in your project.

What does Create Prd need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Prd is instructions for the agent only. Its frontmatter pre-approves these tools: *.

Does Create Prd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Create Prd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Create Prd use?

Create Prd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Create Prd use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Create Prd?

Skills that share tags, products or a category with Create Prd: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Prd?

platformplatform (a GitHub organization) maintains it in platformplatform/PlatformPlatform, which has 440 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on September 24, 2026.

Source: platformplatform/PlatformPlatform on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.