Sponsor Suno AI Music arrow_forward
Slash Command

Project Scaffold

Generate complete fullstack project structure with all boilerplate

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Project Scaffold is

Project Scaffold is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Project Scaffold gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Project Scaffold

Claude Code

  1. Download project-scaffold.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/packages/fullstack-starter-pack/commands/project-scaffold.md, shared under the repository's MIT license. Read the full file on GitHub.

Generates a complete fullstack project structure with frontend, backend, database, authentication, testing, and deployment configuration.

What This Command Does

Generated Project:

  • Frontend (React + TypeScript + Vite)
  • Backend (Express or FastAPI)
  • Database (PostgreSQL + Prisma/SQLAlchemy)
  • Authentication (JWT + OAuth)
  • Testing (Jest/Pytest + E2E)
  • CI/CD (GitHub Actions)
  • Docker setup
  • Documentation

Output: Production-ready fullstack application

Time: 5-10 minutes

Usage

# Generate fullstack project
/project-scaffold "Task Management App"

# Shortcut
/ps "E-commerce Platform" --stack react,express,postgresql

# With specific features
/ps "Blog Platform" --features auth,admin,payments,analytics

Generated Structure

my-app/
├── client/                    # Frontend (React + TypeScript + Vite)
│   ├── src/
│   │   ├── components/       # React components
│   │   ├── pages/            # Page components
│   │   ├── hooks/            # Custom hooks
│   │   ├── services/         # API services
│   │   ├── context/          # Context providers
│   │   ├── utils/            # Utilities
│   │   ├── types/            # TypeScript types
│   │   ├── App.tsx
│   │   └── main.tsx
│   ├── public/
│   ├── index.html
│   ├── package.json
│   ├── vite.config.ts
│   ├── tsconfig.json
│   └── tailwind.config.js
…

Example: Task Management App

Frontend (client/src/pages/Dashboard.tsx):

import { useState, useEffect } from 'react'
import { TaskList } from '../components/TaskList'
import { CreateTaskForm } from '../components/CreateTaskForm'
import { useAuth } from '../context/AuthContext'
import { taskService } from '../services/api'

export function Dashboard() {
  const { user } = useAuth()
  const [tasks, setTasks] = useState([])
  const [loading, setLoading] = useState(true)

  useEffect(() => {
    loadTasks()
  }, [])

  async function loadTasks() {
    try {
      const data = await taskService.getAll()
…

Backend (server/src/controllers/task.controller.ts):

import { Request, Response } from 'express'
import { TaskService } from '../services/task.service'

const taskService = new TaskService()

export class TaskController {
  async getAll(req: Request, res: Response) {
    const tasks = await taskService.findAll(req.user!.userId)
    res.json({ data: tasks })
  }

  async create(req: Request, res: Response) {
    const task = await taskService.create(req.user!.userId, req.body)
    res.status(201).json({ data: task })
  }

  async toggle(req: Request, res: Response) {
    const task = await taskService.toggle(req.params.id, req.user!.userId)
…

Quick Start

1. Install dependencies:

# Install all dependencies (client + server)
npm install

# Or individually
cd client && npm install
cd server && npm install

2. Setup environment:

cp .env.example .env
# Edit .env with your configuration

3. Setup database:

cd server
npx prisma migrate dev
npx prisma generate

4. Start development:

# Start all services (client, server, database)
docker-compose up

# Or start individually
npm run dev:client   # Frontend on http://localhost:5173
npm run dev:server   # Backend on http://localhost:3000

5. Run tests:

npm run test         # All tests
npm run test:client  # Frontend tests
npm run test:server  # Backend tests

Stack Options

Frontend:

  • React + TypeScript + Vite (default)
  • Next.js 14 (App Router)
  • Vue 3 + TypeScript

Backend:

  • Express + TypeScript (default)
  • FastAPI + Python
  • NestJS

Database:

  • PostgreSQL + Prisma (default)
  • MongoDB + Mongoose
  • MySQL + TypeORM

Styling:

  • Tailwind CSS (default)
  • CSS Modules
  • Styled Components

Included Features

Authentication:

  • JWT authentication
  • OAuth (Google, GitHub)
  • Email verification
  • Password reset

Testing:

  • Frontend: Jest + React Testing Library + Cypress
  • Backend: Jest + Supertest
  • E2E: Playwright

CI/CD:

  • GitHub Actions workflows
  • Automated testing
  • Docker build and push
  • Deployment to cloud platforms

Development:

  • Hot reload (frontend + backend)
  • Docker development environment
  • Database migrations
  • Seed data

Production:

  • Optimized Docker images
  • Health checks
  • Logging and monitoring
  • Environment-based config

Customization

Add Features:

# Add payment processing
/ps --add-feature payments --provider stripe

# Add file uploads
/ps --add-feature uploads --storage s3

# Add email service
/ps --add-feature email --provider sendgrid

# Add admin dashboard
/ps --add-feature admin

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Project Scaffold?

Project Scaffold is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Generate complete fullstack project structure with all boilerplate

How do I install Project Scaffold in Claude Code?

Download project-scaffold.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Project Scaffold in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Project Scaffold safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.