By itzsaga
Full PRD workflow system with research, planning, and implementation capabilities
A portable plugin marketplace for Claude Code, featuring a comprehensive PRD (Product Requirements Document) workflow system.
This marketplace provides plugins that extend Claude Code with structured workflows, commands, and automation. The flagship plugin is prd-workflow, which offers a complete system for creating, planning, and implementing product requirements.
Ensure you have the required dependencies installed. See DEPENDENCIES.md for detailed installation instructions.
Required:
jq - JSON parsingyq - YAML parsingcheck-jsonschema - Schema validationOptional:
glow - Markdown renderingmacOS (Homebrew):
brew install jq yq
pip install check-jsonschema
Ubuntu/Debian:
apt install jq
snap install yq # or: pip install yq
pip install check-jsonschema
Arch Linux:
pacman -S jq yq
pip install check-jsonschema
Once Claude Code supports plugin marketplaces, you can install via:
/plugin marketplace add /path/to/jackbot-ai
/plugin install prd-workflow
Until then, you can manually symlink or copy the plugin contents to your Claude configuration.
A complete PRD workflow system with three main phases:
# Create a new PRD
/prd create my-feature
# Plan an existing PRD (research and task definition)
/prd plan my-feature
# Work on a planned PRD (implementation)
/prd work my-feature
# Check PRD status (scripts are relative to the skill directory)
scripts/list-prds.sh
scripts/task-status.sh my-feature
cc-prd/
├── .claude-plugin/
│ └── marketplace.json # Marketplace catalog
├── plugins/
│ └── prd-workflow/ # PRD workflow plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin configuration
│ ├── agents/ # Subagent definitions
│ ├── commands/ # Custom commands
│ ├── hooks/ # Validation hooks
│ ├── skills/ # Skill definitions
│ ├── specs/ # JSON schemas
│ └── scripts/ # Utility scripts
├── README.md
└── DEPENDENCIES.md
The prd-researcher agent uses Exa MCP tools for web research. To enable:
EXA_API_KEY environment variableWithout Exa, the research features will gracefully degrade with appropriate error messages.
Hooks automatically validate tasks.yaml and research.yaml files when edited. They require jq, yq, and check-jsonschema to be installed.
If dependencies are missing, hooks will log a warning but won't block operations.
PRDs are stored in .claude/prds/<prd-name>/:
.claude/prds/my-feature/
├── PRD.md # Main requirements document
├── tasks.yaml # Task definitions
├── research.yaml # Research questions (optional)
├── log.md # Implementation log
└── specs/ # Task specification files
└── task-name.md
Scripts are located in plugins/prd-workflow/skills/prd/scripts/ and are invoked relative to the skill directory.
| Script | Description |
|---|---|
scripts/list-prds.sh | List all PRDs with status |
scripts/task-status.sh <prd> | Get task counts by status |
scripts/get-task.sh <prd> <task> | Get full task details |
scripts/list-prd-draft-tasks.sh <prd> | List tasks needing specs |
scripts/list-defined-tasks.sh <prd> | List tasks ready to implement |
scripts/update-task-status.sh <prd> <task> <status> | Update task status |
scripts/research-status.sh <prd> | Get research completion status |
scripts/get-unanswered-research.sh <prd> | Get pending research questions |
Adapted from fullykubed/nixos-config - converted from NixOS-specific configuration to a portable plugin format.
MIT
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub itzsaga/cc-prd --plugin prd-workflow'MUST BE USED PROACTIVELY when user mentions: planning, PRD, product requirements document, project plan, roadmap, specification, requirements analysis, feature breakdown, technical spec, project estimation, milestone planning, or task decomposition. Use IMMEDIATELY when user says "create a PRD", "plan this feature", "document requirements", "break down this project", "estimate this work", "create a roadmap", "write specifications", or references planning/documentation needs. Expert Technical Project Manager that creates comprehensive PRDs with user stories, acceptance criteria, technical architecture, task breakdowns, and separate task assignment files for sub-agent delegation.'
Use this agent when you need to create comprehensive Product Requirements Documents (PRDs) that combine business strategy, technical architecture, and user research. Examples: <example>Context: The user needs to create a PRD for a new feature or product launch. user: "I need to create a PRD for our new user authentication system that will support SSO and multi-factor authentication" assistant: "I'll use the prd-specialist agent to create a comprehensive PRD that covers the strategic foundation, technical requirements, and implementation blueprint for your authentication system."</example> <example>Context: The user is planning a major product initiative and needs strategic documentation. user: "We're launching a mobile app for our e-commerce platform and need a detailed PRD to guide development" assistant: "Let me engage the prd-specialist agent to develop a thorough PRD that includes market analysis, user research integration, technical architecture, and implementation roadmap for your mobile app initiative."</example>
Product Management Agents and skills to speed up your workflows.
Interactive PRD (Product Requirements Document) builder with comprehensive interview-driven discovery, gap analysis, and taskmanager integration.
Autonomous development methodology: PRD interviews → agent execution → automated review
Skills for the claude autonomous agent system - Generate PRDs and convert them to prd.json format for autonomous execution