ReqForge

Prerequisites

Requirements depth: PM frameworks & Chain-of-Thought

Beyond the interview flow, product-spec-builder ships optional references (no extra Skills to install):

You do not need to type “think first” in every message — the Skill and session bootstrap apply the structure. See What's New → v1.25.0.

Installation & Usage

Forge is copy-to-use: no package publish, no npm install in your app project. You only need a supported AI coding assistant.

Step 2 — Install into your project

Option A — One-command install (recommended)

From your Forge clone (requires Node.js for ts-node):

```bash

Install into another project

pnpm forge-install claude-code --target /path/to/my-app

Install into current directory

pnpm forge-install cursor .

After installation — what appears in your project

my-app/
├── .claude/                    # or .cursor/ or .opencode/  ← adapter bundle
│   ├── CLAUDE.md               # control file (OpenCode: AGENTS.md)
│   ├── settings.json           # 10 hooks (Unix .sh); copy settings.windows.json on Windows
│   ├── skills/                 # 12 Skill definitions + commands/
│   ├── agents/                 # 10 Sub-agent definitions
│   ├── hooks/                  # .sh + .bat hook scripts
│   ├── loadouts/               # full | web-app | cli-tool | minimal
│   ├── feedback/               # evolution fuel (lessons learned)
│   ├── EVOLUTION.md            # evolution engine levels
│   └── rules/                  # Claude Code: .claude/rules/*.md; Cursor: .cursor/rules/*.mdc
├── Product-Spec.md             # after /product-spec-builder
├── DEV-PLAN.md                 # after /dev-planner
├── Design-Brief.md             # optional
├── changes/                    # optional — brownfield iterations (/change-manager)
│   └── archive/
├── memory/                     # auto-created on first /dev-builder
│   ├── project-memory.md
│   ├── decisions-log.md
│   └── task-history.md
└── <project-name>/ ...         # your application code (not flat in root)

Forge does not modify your package.json unless you ask the agent to add dependencies during development.

Quick Start Mode

Don't want the full interview? Just describe your project in one sentence:

You: "A habit tracker app with AI coaching"
Forge: ⚡ Quick Spec generated! Items marked [待确认] are my best guesses.

AI infers everything — product type, target users, core features, tech stack, layout. Uncertain items default to the simpler option and are marked for your review. Switch to deep-dive mode anytime with /product-spec-builder.

Merge upgrade (keeps your feedback/ and settings.local.json)

pnpm forge-install claude-code --target ../my-app --force

Step 3b — Loadouts (optional)

Adapters ship 4 loadout bundles under loadouts/ (full, web-app, cli-tool, minimal). Each JSON lists recommended skills, agents, and hooks for a project type.

Not sure which one? See loadout-scenarios.md — scenario → loadout → first Skill command.

• Default install ≈ full loadout (all hooks in settings.json).
• Trim hooks (contributors, from Forge clone): pnpm apply-loadout minimal claude-code merges a lighter hook set into adapter settings.json. Add --dry-run to preview.
• Loadouts are reference manifests — skills/agents are already copied; use loadouts to understand what each bundle includes.
• Brownfield (/change-manager): included in full and web-app only; cli-tool and minimal omit it — copy the skill from core/skills/change-manager/ or switch loadout if you need changes/ on a CLI project.

Workflow

1. Describe your idea — /product-spec-builder interviews you (or Quick Mode for one sentence). For fuzzy ideas, optional PM discovery (OST, assumptions) and CoT templates improve Spec quality before any code.
2. Generate spec — Outputs Product-Spec.md (may include optional JTBD, metrics, competitors, assumptions sections) → user confirms → .forge/spec-confirmed.json
3. Design brief (optional) — Invoke /design-brief-builder
4. Design mockups (optional) — Invoke /design-maker
5. Development plan — Invoke /dev-planner, outputs DEV-PLAN.md
6. Build — Invoke /dev-builder, works through each Task in each Phase
7. Memory auto-update — After each Task, project memory is updated automatically
8. Auto-review — code-reviewer parallel agent review + confidence aggregation
9. Auto-fix — Failed review triggers bug-fixer automatically
10. Commit & push — Review passes → auto commit + push
11. Phase verification — Cross-Task integration check + compile + functional test
12. Iterate — Request changes in conversation; auto-update Spec → Plan → code → review
13. Brownfield feature (optional, when Spec already exists) — /change-manager propose <name> → fill changes/<name>/ → apply (dev-planner/dev-builder scoped) → verify → archive
14. Release — Invoke /release-builder

Research & comparisons

External harnesses reviewed for positioning (not dependencies):

ReqForge maintainer docs (not third-party comparisons):

---