prdCreate and manage Product Requirements Documents (PRDs). Use when: (1) Creating structured task lists with user stories, (2) Specifying features with acceptance criteria, (3) Planning feature implementation for AI agents or human developers.
Install via ClawdBot CLI:
clawdbot install bjesuiter/prdCreate and manage Product Requirements Documents (PRDs) for feature planning.
A PRD (Product Requirements Document) is a structured specification that:
agents/prd.json in the projectpasses: false → true{
"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 | Description |
|-------|-------------|
| project | Project name for context |
| branchName | Git branch for this feature (prefix with ralph/) |
| description | One-line feature summary |
| userStories | List of stories to complete |
| userStories[].id | Unique identifier (US-001, US-002) |
| userStories[].title | Short descriptive title |
| userStories[].description | "As a [user], I want [feature] so that [benefit]" |
| userStories[].acceptanceCriteria | Verifiable checklist items |
| userStories[].priority | Execution order (1 = first) |
| userStories[].passes | Completion status (false → true when done) |
| userStories[].notes | Runtime notes added by agent |
Each story should be completable in one context window.
Stories execute in priority order. Earlier stories must NOT depend on later ones.
Correct order:
Must be verifiable, not vague.
status column to tasks table with default 'pending'"Always include: "Typecheck passes"
Update passes: true when a story is complete. Use notes field for runtime observations:
"notes": "Used IF NOT EXISTS for migrations"
| Action | Command |
|--------|---------|
| Create PRD | Save to agents/prd.json |
| Check status | cat prd.json | jq '.userStories[] | {id, passes}' |
| View incomplete | jq '.userStories[] | select(.passes == false)' prd.json |
See references/ for detailed documentation:
agent-usage.md - How AI agents execute PRDs (Claude Code, OpenCode, etc.)workflows.md - Sequential workflow patternsoutput-patterns.md - Templates and examplesGenerated Mar 1, 2026
A software-as-a-service company uses the PRD skill to plan and track the implementation of a new analytics dashboard feature. It breaks the work into user stories for database schema updates, backend API endpoints, and frontend components, ensuring each story fits within an AI agent's context window for efficient execution.
An e-commerce business employs the PRD skill to add a product recommendation engine. The PRD outlines user stories for data model changes, algorithm integration, and UI updates, with acceptance criteria like 'Typecheck passes' to verify each step before moving to the next priority task.
A mobile app development team uses the PRD skill to manage a feature for in-app notifications. Stories are ordered by dependency, starting with backend schema modifications, followed by push notification services, and ending with UI implementation, tracking progress via the passes field.
A healthcare software provider applies the PRD skill to integrate patient data from multiple sources. The PRD structures tasks into user stories for database migrations, API development, and compliance checks, with clear acceptance criteria to ensure regulatory requirements are met.
An edtech company utilizes the PRD skill to launch a new collaborative tool feature. It defines user stories for backend logic, user interface components, and testing, using the notes field to document runtime observations and maintain a clear execution order.
Companies offer the PRD skill as part of a premium subscription for project management tools, generating recurring revenue by helping teams streamline feature development with structured documentation and AI-assisted task tracking.
Agencies provide consulting services using the PRD skill to assist clients in product planning and development, charging per project or hourly rates for expertise in creating and managing PRDs to improve workflow efficiency.
Developers integrate the PRD skill into a freemium development platform, offering basic PRD creation for free and charging for advanced features like analytics, team collaboration, or integration with other AI agents.
💬 Integration Tip
Integrate the PRD skill by saving prd.json in the agents directory and using it with AI agents like Claude Code to automate task execution based on the structured user stories and acceptance criteria.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection