Get the FREE Ultimate OpenClaw Setup Guide →
b

Prd

Scanned

@bjesuiter

npx machina-cli add skill @bjesuiter/prd --openclaw
Files (1)
SKILL.md
3.8 KB

PRD Skill

Create and manage Product Requirements Documents (PRDs) for feature planning.

What is a PRD?

A PRD (Product Requirements Document) is a structured specification that:

  1. Breaks a feature into small, independent user stories
  2. Defines verifiable acceptance criteria for each story
  3. Orders tasks by dependency (schema → backend → UI)

Quick Start

  1. Create/edit agents/prd.json in the project
  2. Define user stories with acceptance criteria
  3. Track progress by updating passes: falsetrue

prd.json Format

{
  "project": "MyApp",
  "branchName": "ralph/feature-name",
  "description": "Short description of the feature",
  "userStories": [
    {
      "id": "US-001",
      "title": "Add priority field to database",
      "description": "As a developer, I need to store task priority.",
      "acceptanceCriteria": [
        "Add priority column: 'high' | 'medium' | 'low'",
        "Generate and run migration",
        "Typecheck passes"
      ],
      "priority": 1,
      "passes": false,
      "notes": ""
    }
  ]
}

Field Descriptions

FieldDescription
projectProject name for context
branchNameGit branch for this feature (prefix with ralph/)
descriptionOne-line feature summary
userStoriesList of stories to complete
userStories[].idUnique identifier (US-001, US-002)
userStories[].titleShort descriptive title
userStories[].description"As a [user], I want [feature] so that [benefit]"
userStories[].acceptanceCriteriaVerifiable checklist items
userStories[].priorityExecution order (1 = first)
userStories[].passesCompletion status (falsetrue when done)
userStories[].notesRuntime notes added by agent

Story Sizing

Each story should be completable in one context window.

✅ Right-sized:

  • Add a database column and migration
  • Add a UI component to an existing page
  • Update a server action with new logic
  • Add a filter dropdown to a list

❌ Too large (split these):

  • "Build the entire dashboard" → Split into: schema, queries, UI, filters
  • "Add authentication" → Split into: schema, middleware, login UI, session

Story Ordering

Stories execute in priority order. Earlier stories must NOT depend on later ones.

Correct order:

  1. Schema/database changes (migrations)
  2. Server actions / backend logic
  3. UI components that use the backend
  4. Dashboard/summary views

Acceptance Criteria

Must be verifiable, not vague.

✅ Good:

  • "Add status column to tasks table with default 'pending'"
  • "Filter dropdown has options: All, Active, Completed"
  • "Typecheck passes"

❌ Bad:

  • "Works correctly"
  • "User can do X easily"

Always include: "Typecheck passes"

Progress Tracking

Update passes: true when a story is complete. Use notes field for runtime observations:

"notes": "Used IF NOT EXISTS for migrations"

Quick Reference

ActionCommand
Create PRDSave to agents/prd.json
Check status`cat prd.json
View incomplete`jq '.userStories[]

Resources

See references/ for detailed documentation:

  • agent-usage.md - How AI agents execute PRDs (Claude Code, OpenCode, etc.)
  • workflows.md - Sequential workflow patterns
  • output-patterns.md - Templates and examples

Source

git clone https://clawhub.ai/bjesuiter/prdView on GitHub

Overview

PRD Skill helps you create and manage Product Requirements Documents for structured feature planning. It breaks features into small, independent user stories with verifiable acceptance criteria and orders tasks by dependency (schema → backend → UI). This keeps teams aligned and supports planning for both AI agents and human developers.

How This Skill Works

Define the PRD in agents/prd.json, listing userStories with id, title, description, acceptanceCriteria, priority, passes, and notes. Each story should be small enough to complete in one context window and include explicit acceptance criteria and a clear priority. Progress is tracked by toggling passes to true and recording runtime notes.

When to Use It

  • Creating structured task lists with user stories and clear ownership
  • Specifying features with verifiable acceptance criteria
  • Planning feature implementation order (schema → backend → UI)
  • Coordinating AI agent and human developer workflows
  • Tracking progress and decisions with passes and notes

Quick Start

  1. Step 1: Create/edit agents/prd.json in the project
  2. Step 2: Define user stories with acceptance criteria
  3. Step 3: Track progress by updating passes: false → true

Best Practices

  • Break features into small, independent user stories
  • Define verifiable acceptance criteria for each story
  • Order tasks by dependency: schema, backend, UI
  • Always include Typecheck passes in acceptance criteria
  • Keep each story completable within one context window

Example Use Cases

  • Example: Add priority field to tasks with a migration and typecheck passes
  • Example: Create a UI component on an existing page and link to backend
  • Example: Update a server action to include new business logic with acceptance criteria
  • Example: Add a filter dropdown with options All, Active, Completed
  • Example: Plan a new feature by splitting into schema, backend, and UI tasks

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers