Usage Guide

The foundation. One command makes your AI understand your entire project.

forge-core runs a 7-gate architecture audit that auto-detects your stack, layers, conventions, and patterns. It generates project-specific dev-skills and 50+ quality guardrails that your AI follows in every session. The universal Hub classifies your intent, walks the dependency graph, and routes to the right pipeline - so you never need to memorize commands or worry about missing prerequisites.

Describe features in business language. AI builds from spec, not guesswork.

forge-product bridges the gap between what you want and what AI builds. Describe a feature in plain language - it generates user flows, user stories with acceptance criteria, and UX specifications. These artifacts feed directly into the development pipeline, so your AI codes from verified requirements instead of hallucinated assumptions.

Tests that trace back to requirements. Not AI guesswork.

forge-qa generates tests from acceptance criteria, not from AI assumptions. It supports 10 testing modes and maintains a 4-level traceability matrix: acceptance criteria → unit tests, use cases → E2E tests, UX criteria → visual tests, and LLM-as-Judge for AI output quality. Every test proves a requirement - no orphan tests, no missing coverage.

Your backlog lives in your tracker. Now your AI reads it too.

forge-tracker connects your existing task management tool to the AI development pipeline. Pick a task from GitHub Issues, Linear, ClickUp, Notion, or Jira - your AI gets the full context (description, acceptance criteria, labels, priority) and starts working. When done, it syncs status and links the PR back to the task. No more copy-pasting issue descriptions into prompts.

Your AI prompts are code. Manage them like code.

forge-prompts brings software engineering rigor to prompt management. It inventories every LLM prompt in your project, audits them against provider-specific best practices, and tracks quality over time. Three frameworks (CO-STAR, RISEN, TIDD-EC) guide structured prompt design. A dedicated subagent handles prompt writing and refactoring - so your prompts evolve as your product grows.

Run 3 agents in parallel. Zero merge conflicts.

forge-autopilot orchestrates autonomous AI teammates like Kubernetes orchestrates containers. Give it a list of features - it triages them, detects potential conflicts (shared models, overlapping files), groups non-conflicting features into parallel waves, and deploys agents to isolated worktrees. Each agent follows your full pipeline (guardrails, tests, quality gates). When a wave completes, it auto-merges and starts the next wave.

Isolated branches with zero port conflicts. Automatic cleanup.

forge-worktree manages the git worktree lifecycle for parallel development. Each worktree gets its own directory, Docker port offsets, and environment configuration - no more port conflicts between branches. Three templates cover common setups: Docker backend (with port isolation), Frontend (with dev server offsets), and Generic. Worktrees are auto-provisioned by forge-autopilot or created manually.

Validate before you build. Research before you commit.

forge-discovery structures the messy early phase of product development. Instead of jumping to code, it guides you through ideation, competitive research, problem validation, and user interview planning. The output feeds directly into forge-product - so by the time you design features, you have validated assumptions, not guesses.

From validated problem to sellable product. Strategy, not guesswork.

forge-marketing turns your validated product insights into marketing strategy. It generates positioning, pricing recommendations, go-to-market plans, and content calendars - all grounded in your product data, not generic templates. When forge-discovery and forge-product are installed, it reads their artifacts automatically for context-aware recommendations.

Consistent voice across every screen, email, and notification.

forge-copy manages production copy as a first-class concern. Define your brand voice once - it generates and reviews UI microcopy, email templates, notification text, and error messages against your voice guidelines. When forge-product or forge-marketing are installed, it uses their positioning and user research for copy that speaks your customer's language.

Technical SEO your AI actually understands. Not a checklist - a strategy.

forge-seo combines technical SEO auditing with keyword research and schema markup generation. It scans your pages for issues (missing meta tags, broken structured data, performance bottlenecks), researches keywords aligned with your product positioning, and generates JSON-LD schema markup. When forge-analytics is installed, it correlates SEO metrics with user behavior data.

Measurement-first. Plan what to track before you ship.

forge-analytics flips the usual approach: instead of adding tracking after launch, you define a measurement plan during development. It generates event schemas, tracking plans, and dashboard specifications before a single line of tracking code is written. Your team knows exactly what data you'll have on day one.

From signup to aha moment. Design the path, not just the page.

forge-onboarding designs activation flows that convert signups into engaged users. It maps the journey from first login to the "aha moment" - the point where users experience core value. Generates step-by-step onboarding flows, empty state designs, tooltip sequences, and progress indicators. When forge-product is installed, it uses user flows and personas to tailor the onboarding path.

Retain, refer, expand. Three levers, one module.

forge-growth structures the three core growth levers: retention (reduce churn), referral (organic acquisition), and expansion (upsell and cross-sell). It generates churn prevention strategies with cancel flow designs, referral program frameworks, and expansion revenue playbooks. When forge-analytics is installed, it grounds recommendations in actual user behavior data.

Statistically valid experiments. Not "we changed the button color."

forge-ab brings statistical rigor to product experimentation. It structures experiments from hypothesis to analysis: defines success metrics, calculates required sample sizes, designs variants, and provides analysis frameworks. No more running tests without enough traffic, or declaring winners based on gut feeling. When forge-analytics is installed, it uses your event schemas for metric definitions.

Feedback & Bug Reports

Found a bug? Have a suggestion? Use the built-in feedback command — it sends structured reports directly to the Forge team.