product-forge

parallel-run

Orchestrate parallel agent execution with git worktrees

parallel-prompt-generator

Generate agent-ready prompts from existing task specification files. Use when regenerating prompts after editing tasks, updating prompt templates, or preparing tasks for cpo execution.

parallel-integrate

Verify integration after parallel agent execution and generate report

parallel-execution

Execute multiple Claude Code agents in parallel using the cpo CLI tool. Use when running parallel tasks, monitoring execution, or understanding the execution workflow.

parallel-decompose

Decompose PRDs and Tech Specs into parallel-executable tasks with contracts, prompts, and dependency graphs. Use when breaking down a PRD for multi-agent execution.

parallel-agents

Use when parallelizing development, running multiple agents, splitting work across agents, coordinating parallel tasks, or decomposing PRDs for concurrent execution. Breaks work into independent agent workstreams.

network-inspection

Use when debugging API calls, checking network requests, inspecting HTTP traffic, finding failed requests, analyzing response data, or investigating API errors. Provides detailed request/response analysis.

list-qa-tests

List QA test procedures with status and priority

list-prds

List all PRDs with status, progress, and metadata

install-chrome-devtools-mcp

Install Chrome DevTools MCP server for debugging and network inspection in Claude Code

generate-tasks

Convert PRD to structured task list with automatic linking

forge-help

Show all available Product Forge agents, skills, and commands

enrich-qa-test

Review QA test and capture element screenshots to enrich documentation

discovery-session

Start interactive product discovery with expert guidance

design-system

Design system management for building and reusing UI components, tokens, and patterns. Use when working with component libraries, design tokens, style guides, or reusable UI patterns to ensure consistency and promote component reuse.

debug-orchestrator

Use when facing complex, multi-layered debugging issues that require coordinated investigation across different domains (frontend, backend, database, network, etc). Spawns specialized debug expert agents to handle specific aspects of the investigation.

ctx

Load PRD, FRD, Tech Spec, or RFC into context

create-qa-test

Create a new QA test procedure for a feature

create-prd

Interactive PRD creation wizard with comprehensive question flow

create-prd-feature

Create a feature-specific PRD (FRD) for individual features

create-persona

Create detailed user persona with guided questions

console-debugging

Use when debugging JavaScript errors, checking console warnings, analyzing browser logs, finding runtime errors, investigating console output, or troubleshooting browser issues. Provides console message analysis.

browser-debug

Capture browser console, network, and performance logs for debugging. Auto-loads when debugging browser issues, analyzing errors, or investigating page behavior. Provides systematic log capture workflow using Chrome DevTools MCP.

brainstorm-solution

Structured brainstorming for technical solutions

agent-tools

Reference for configuring tool permissions when launching Claude Code agents. Use when setting up --allowedTools flags, restricting file access, or configuring agent permissions.