Next Forge logo

Next Forge

Organization
vercel
next-forge

Expert assistance for next-forge — a production-grade Turborepo template for Next.js SaaS apps. Triggers on questions about next-forge installation, setup, architecture, packages, customization, deployment, and development workflows.

Overview

Publishervercel
Repositoryvercel-plugin
Skill namenext-forge
Stars
286
Forks
56
Bundled files
4
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vercel on GitHub. Read the source before you install it.

Installation

Install the Next Forge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vercel/vercel-plugin.git /tmp/vercel-plugin
mkdir -p .claude/skills
cp -r /tmp/vercel-plugin/skills/next-forge/upstream .claude/skills/next-forge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Next Forge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Next Forge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Next Forge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

next-forge

next-forge is a production-grade Turborepo template for building Next.js SaaS applications. It provides a monorepo structure with multiple apps, shared packages, and integrations for authentication, database, payments, email, CMS, analytics, observability, security, and more.

Quick Start

Initialize a new project:

bash
npx next-forge@latest init

The CLI prompts for a project name and package manager (bun, npm, yarn, or pnpm). After installation:

  1. Set the DATABASE_URL in packages/database/.env pointing to a PostgreSQL database (Neon recommended).
  2. Run database migrations: bun run migrate
  3. Add any optional integration keys to the appropriate .env.local files.
  4. Start development: bun run dev

All integrations besides the database are optional. Missing environment variables gracefully disable features rather than causing errors.

Architecture Overview

The monorepo contains apps and packages. Apps are deployable applications. Packages are shared libraries imported as @repo/<package-name>.

Apps (in /apps/):

AppPortPurpose
app3000Main authenticated SaaS application
web3001Marketing website with CMS and SEO
api3002Serverless API for webhooks, cron jobs
email3003React Email preview server
docs3004Documentation site (Mintlify)
storybook6006Design system component workshop
studio3005Prisma Studio for database editing

Core Packages: auth, database, payments, email, cms, design-system, analytics, observability, security, storage, seo, feature-flags, internationalization, webhooks, cron, notifications, collaboration, ai, rate-limit, next-config, typescript-config.

For detailed structure, see references/architecture.md.

Key Concepts

Environment Variables

Environment variable files live alongside apps and packages:

  • apps/app/.env.local — Main app keys (Clerk, Stripe, etc.)
  • apps/web/.env.local — Marketing site keys
  • apps/api/.env.local — API keys
  • packages/database/.envDATABASE_URL (required)
  • packages/cms/.env.local — BaseHub token
  • packages/internationalization/.env.local — Languine project ID

Each package has a keys.ts file that validates environment variables with Zod via @t3-oss/env-nextjs. Type safety is enforced at build time.

Inter-App URLs

Local URLs are pre-configured:

  • NEXT_PUBLIC_APP_URL=http://localhost:3000
  • NEXT_PUBLIC_WEB_URL=http://localhost:3001
  • NEXT_PUBLIC_API_URL=http://localhost:3002
  • NEXT_PUBLIC_DOCS_URL=http://localhost:3004

Update these to production domains when deploying (e.g., app.yourdomain.com, www.yourdomain.com).

Server Components First

page.tsx and layout.tsx files are always server components. Client interactivity goes in separate files with 'use client'. Access databases, secrets, and server-only APIs directly in server components and server actions.

Graceful Degradation

All integrations beyond the database are optional. Clients use optional chaining (e.g., stripe?.prices.list(), resend?.emails.send()). If the corresponding environment variable is not set, the feature is silently disabled.

Common Tasks

Running Development

bash
bun run dev                  # All apps
bun dev --filter app         # Single app (port 3000)
bun dev --filter web         # Marketing site (port 3001)

Database Migrations

After changing packages/database/prisma/schema.prisma:

bash
bun run migrate

This runs Prisma format, generate, and db push in sequence.

Adding shadcn/ui Components

bash
npx shadcn@latest add [component] -c packages/design-system

Update existing components:

bash
bun run bump-ui

Adding a New Package

Create a new directory in /packages/ with a package.json using the @repo/<name> naming convention. Add it as a dependency in consuming apps.

Linting and Formatting

bash
bun run lint                 # Check code style (Ultracite/Biome)
bun run format               # Fix code style

Testing

bash
bun run test                 # Run tests across monorepo

Building

bash
bun run build                # Build all apps and packages
bun run analyze              # Bundle analysis

Deployment

Deploy to Vercel by creating separate projects for app, web, and api — each pointing to its respective root directory under /apps/. Add environment variables per project or use Vercel Team Environment Variables.

For detailed setup and customization instructions, see:

  • references/setup.md — Installation, prerequisites, environment variables, database and Stripe CLI setup
  • references/packages.md — Detailed documentation for every package
  • references/customization.md — Swapping providers, extending features, deployment configuration
  • references/architecture.md — Full monorepo structure, Turborepo pipeline, scripts

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Next Forge AI skill do?

Expert assistance for next-forge — a production-grade Turborepo template for Next.js SaaS apps. Triggers on questions about next-forge installation, setup, architecture, packages, customization, deployment, and development workflows.

Why use Next Forge on TypingMind?

Because you install it once and use it with any model. Next Forge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Next Forge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vercel/vercel-plugin/tree/main/skills/next-forge/upstream. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Next Forge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Next Forge?

As many as you like. As long as a model supports skills, you can use Next Forge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Next Forge AI skill free?

It is published on GitHub by vercel. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇