Product Forge
A comprehensive Claude Code marketplace plugin for product development, PRD management, task tracking, and secure technical implementation. Features CPO/CTO/Marketing/UX/DPO/DevOps/Data Engineering/RAG-CAG expertise with specialized technical agents (Django, FastAPI, FastMCP, React/TypeScript, Celery, Playwright) that research current documentation before coding. Includes design system management, cloud infrastructure (AWS, GCP, Ansible), data transformation (dbt, SQLMesh), RAG/CAG architecture with multi-tenant security, MCP security with 5-layer defense, OAuth/OIDC, and privacy compliance (GDPR/CCPA).
Forge CLI Utilities
Product Forge includes a unified forge CLI tool for skill-related utilities:
YouTube Transcript Fetcher
Fetch YouTube video transcripts as readable text files:
# Install with YouTube support
uv tool install . --with youtube-transcript-api
# Fetch transcript
forge youtube "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
forge youtube "https://youtu.be/dQw4w9WgXcQ" --output transcripts/
forge youtube dQw4w9WgXcQ
Feedback Management
Manage Product Forge learnings and feedback:
# Initialize learnings directory
forge feedback init
# Show statistics
forge feedback stats
# List feedback items
forge feedback list
forge feedback list --project product-forge
forge feedback list --type improvement
# Save feedback (used by hooks)
cat feedback.json | forge feedback save
See FORGE_CLI_IMPLEMENTATION_SUMMARY.md for complete CLI documentation.
Features
Skills (Automatic Context Activation)
Skills automatically activate when Claude detects relevant context, providing expert guidance without explicit commands.
| Skill | Triggers | Description |
|---|
| PRD Management | prd, requirements | Automatic lifecycle management and organization |
| Task Orchestration | task, implement | Documentation-first execution with quality checks |
| Product Strategy | strategy, market | Chief Product Officer expertise with proven frameworks |
| Documentation Research | code, build, develop | Enforces online documentation research before implementation |
| MCP Security | mcp security, prompt injection, authorization | 5-layer defense architecture for multi-agent systems |
| Design System | design system, components, tokens | Build and reuse UI components, tokens, and patterns |
| Python Style | python, django, fastapi, celery | PEP standards, type hints, and modern Python patterns |
| TypeScript Style | typescript, react, node, eslint | Strict typing, ESLint, and modern TS/JS patterns |
| Privacy Compliance | gdpr, ccpa, privacy, data protection | GDPR, CCPA/CPRA, and regional compliance |
| AWS Cloud | aws, ec2, s3, lambda, iam | AWS services best practices and IAM security |
| GCP Cloud | gcp, gce, bigquery, cloud run | Google Cloud best practices and IAM security |
| Ansible | ansible, playbook, vault | Ansible automation for infrastructure |
| OAuth | oauth, oidc, jwt, pkce | OAuth 2.0 and OpenID Connect implementation |
| dbt | dbt, data transformation | dbt modeling, testing, and documentation |
| SQLMesh | sqlmesh, virtual environments | SQLMesh incremental models and CI/CD |
| RAG/CAG Architecture | rag, cag, vector database, embeddings | RAG/CAG patterns, chunking, multi-tenant security |
| Chunking Strategies | chunking, text splitting, semantic chunking | Document-type-specific chunking, RAPTOR, evaluation |
Commands (Explicit User Actions)
Commands you invoke when you need specific functionality.
| Command | Usage | Description |
|---|
/create-prd | /create-prd my-product | Interactive PRD creation wizard |
/create-prd-feature | /create-prd-feature auth | Create feature-specific PRD |
/generate-tasks | /generate-tasks prd.md | Convert PRD to task list |
/prd-status | /prd-status prd.md --set ACTIVE | Check/update PRD status |
/list-prds | /list-prds --status ACTIVE | List PRDs with metadata |
/task-list | /task-list --dir focus | List tasks with progress |
/task-focus | /task-focus TASK-001 | Focus on specific task |
/discovery-session | /discovery-session my-product | Start product discovery |
/create-persona | /create-persona developer | Create user persona |
/position-product | /position-product my-product | Define positioning |
/brainstorm-solution | /brainstorm-solution "problem" | Structured brainstorming |
/prd-progress | /prd-progress prd.md | Show implementation progress |
/prd-archive | /prd-archive prd.md | Archive completed PRDs |
/quick-start | /quick-start | Quick start guide |
Agents (Complex Multi-Step Tasks)
Agents handle autonomous, multi-step workflows.
Leadership Agents
