Prd Creation
Scannednpx machina-cli add skill a5c-ai/babysitter/prd-creation --openclawPRD Creation
Interactive PRD brainstorming and drafting with quality-gated refinement.
Agent
Product Planner - product-planner
Workflow
- Brainstorm ideas, users, and pain points
- Draft structured PRD with vision, user stories, success criteria
- Validate PRD quality (completeness, clarity, testability, consistency)
- Iteratively refine until quality threshold met
- Finalize and write to .claude/prds/<featureName>.md
Inputs
projectName- Project namefeatureName- Feature identifierprojectDescription- High-level descriptiontargetAudience- Target user description (optional)constraints- Known constraints (optional)
Outputs
- PRD with vision, user stories, acceptance criteria, scope, constraints
- Quality validation report with dimensional scores
- Brainstorm artifacts
Process Files
ccpm-prd-workflow.js- Standalone PRD workflowccpm-orchestrator.js- Phase 1 of full lifecycle
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/ccpm/skills/prd-creation/SKILL.mdView on GitHub Overview
PRD Creation provides an interactive workflow for brainstorming ideas, defining a product vision, and drafting a structured PRD with user stories and acceptance criteria. It validates quality across completeness, clarity, testability, and consistency, iterating until the threshold is met, then finalizes and writes the PRD to .claude/prds/<featureName>.md.
How This Skill Works
A Product Planner guides the process, collecting inputs, brainstorming ideas, users, and pain points, and drafting a PRD with vision, user stories, acceptance criteria, and scope. It then runs a quality validation pass (completeness, clarity, testability, consistency) and iterates until the quality threshold is met, before finalizing and saving the PRD to .claude/prds/<featureName>.md. The workflow leverages ccpm-prd-workflow.js and ccpm-orchestrator.js to orchestrate the lifecycle.
When to Use It
- Kick off a new feature and create a structured PRD from scratch
- Align cross-functional teams on vision, user stories, and success criteria
- Ensure a PRD is complete, clear, testable, and consistent before reviews
- Iteratively refine an in-progress PRD to meet quality thresholds
- Finalize and export the PRD to .claude/prds/<featureName>.md for handoff
Quick Start
- Step 1: Provide inputs (projectName, featureName, projectDescription, targetAudience, constraints)
- Step 2: Run the PRD workflow to brainstorm, draft the PRD, and define vision, user stories, and acceptance criteria
- Step 3: Review the quality validation report, iterate as needed, and finalize by saving to .claude/prds/<featureName>.md
Best Practices
- Capture projectName and featureName early to keep PRD scope clear
- Fill inputs like projectDescription, targetAudience, and constraints up front
- Structure the PRD with vision, user stories, acceptance criteria, and scope
- Make acceptance criteria testable and measurable
- Run a quality validation pass and save the final PRD to .claude/prds/<featureName>.md
Example Use Cases
- PRD for onboarding flow revamp in a mobile app with clear user stories and acceptance criteria
- PRD for API integration between two SaaS platforms with data contracts and success metrics
- PRD for a analytics dashboard overhaul focusing on new metrics and usability
- PRD for implementing a feature flag system with rollout criteria and constraints
- PRD for exporting reports feature with data sources, formats, and validation rules
