Project Scaffolding logo

Project Scaffolding

Community
hmohamed01
project-scaffolding

IDE-grade project scaffolding wizard for creating new projects with comprehensive configuration. Supports 70+ project types: HTML/CSS websites, React, Next.js, Vue, Astro, Remix, React Native, Flutter, Expo, FastAPI, Django, Express, NestJS, Go/Gin, Rust/Axum, Spring Boot, Hono, Elysia, Chrome Extensions, VS Code Extensions, Tauri desktop apps, serverless functions, and more. Provides WebStorm/PyCharm-level project creation with interactive SDK selection, framework configuration, database setup, and DevOps tooling. Use when: creating a new project, setting up a framework application, initializing a codebase, scaffolding boilerplate, building extensions, creating mobile/desktop/web apps, setting up monorepos, or making static websites/landing pages.

Overview

Publisherhmohamed01
RepositoryClaude-Code-Scaffolding-Skill
Skill nameproject-scaffolding
Stars
56
Forks
4
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

    Published by hmohamed01 on GitHub. Read the source before you install it.

Installation

Install the Project Scaffolding 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.
    https://github.com/hmohamed01/Claude-Code-Scaffolding-Skill/tree/main/project-scaffolding
  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/hmohamed01/Claude-Code-Scaffolding-Skill.git /tmp/Claude-Code-Scaffolding-Skill
mkdir -p .claude/skills
cp -r /tmp/Claude-Code-Scaffolding-Skill/project-scaffolding .claude/skills/project-scaffolding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Project Scaffolding 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 Project Scaffolding 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 Project Scaffolding 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.

Project Scaffolding Wizard

Professional-grade project scaffolding comparable to WebStorm/PyCharm project wizards. Creates fully configured projects with SDK setup, framework options, database configuration, linting, and CI/CD.

Version Freshness

All dependency versions live in assets/versions.json — never hardcode a version in generated output or in scripts/scaffold.py. Treat that manifest as the only source of truth.

Before recommending frameworks in Step 3, check how stale it is:

bash
python3 scripts/scaffold.py --version-status
  • Under 30 days — proceed without comment.
  • 30–90 days — proceed, and mention the manifest's age once when presenting version-sensitive choices.
  • Over 90 days — say so before recommending, and offer to refresh: python3 scripts/refresh_versions.py (dry run; add --apply to write).

Never guess at current versions or "update" the manifest from memory. Registry facts come only from refresh_versions.py, which queries npm and PyPI directly. If the refresh cannot run (no network), state that the versions may be stale rather than substituting recalled numbers.

Wizard Workflow

When a user requests a new project, follow this interactive workflow:

Step 1: Project Type Selection

Present the project type menu. Ask the user to select a category and type:

CategoryTypes
Static WebsitesHTML5 (no CSS), HTML/CSS, HTML+Sass, HTML+Tailwind, Landing Page, Multi-page Site
Frontend WebReact, Next.js, Vue, Nuxt, Svelte, Angular, Astro, Remix, Solid, Qwik, Preact
Mobile/DesktopReact Native, Expo, Flutter, Tauri, Electron, Ionic
Backend (JS/TS)Express, NestJS, Fastify, Hono, Elysia, tRPC, Koa
Backend (Python)FastAPI, Django, Django REST, Flask, Litestar
Backend (Go)Gin, Fiber, Echo, Chi
Backend (Rust)Axum, Actix, Rocket
Backend (Java)Spring Boot, Quarkus, Ktor, Micronaut
Backend (Other)Laravel, Rails, .NET Web API
LibrariesTypeScript NPM, Python PyPI, Go Module, Rust Crate
CLI ToolsNode CLI, Python CLI (Typer/Click), Go CLI (Cobra), Rust CLI (Clap)
ExtensionsChrome Extension, Firefox Extension, VS Code Extension, Figma Plugin, Obsidian Plugin
ServerlessAWS Lambda, Cloudflare Workers, Vercel Functions, Supabase Functions
Full-StackT3 Stack, MERN, PERN, MEAN
MonoreposTurborepo, Nx Workspace, pnpm Workspace

Step 2: Basic Configuration

Gather for ALL projects:

  • Project name (required)
  • Location/directory
  • Description
  • Author name
  • License (MIT, Apache-2.0, GPL-3.0, ISC, Unlicense)

Step 3: Framework-Specific Options

Load references/wizard-options.md for detailed configuration options based on the selected project type. Key decisions include:

  • Language/SDK version - Node.js, Python, Go, Rust, Java versions
  • Package manager - npm, pnpm, yarn, bun, poetry, uv
  • CSS framework - Tailwind, CSS Modules, Styled Components
  • State management - Zustand, Redux, Jotai, TanStack Query
  • Database/ORM - PostgreSQL, SQLite, Prisma, SQLAlchemy, sqlc
  • Authentication - NextAuth, JWT, OAuth2
  • Testing - Vitest, Jest, pytest, Playwright

Step 4: Code Quality & DevOps

  • Linting - ESLint, Ruff, golangci-lint, clippy
  • Formatting - Prettier, Ruff, gofmt, rustfmt
  • Pre-commit hooks - husky + lint-staged, pre-commit framework
  • CI/CD - GitHub Actions, GitLab CI
  • Docker - Dockerfile (multi-stage), docker-compose
  • Deployment - Vercel, Railway, Fly.io, AWS, self-hosted

Step 5: Generate Project

Use scripts/scaffold.py or native CLI tools to create the project structure.

CLI Integration

Prefer native CLI tools when available:

FrameworkCLI Command
Next.jsnpx create-next-app@latest
React (Vite)npm create vite@latest -- --template react-ts
Vuenpm create vue@latest
Nuxtnpx nuxi@latest init
Astronpm create astro@latest
Remixnpx create-remix@latest
SvelteKitnpm create svelte@latest
Solidnpm create solid@latest
Exponpx create-expo-app@latest
React Nativenpx @react-native-community/cli init
Flutterflutter create
Taurinpm create tauri-app@latest
NestJSnpx @nestjs/cli new
Spring Bootspring init or start.spring.io
Gogo mod init
Rustcargo new
Chrome Extnpm create plasmo@latest
T3 Stacknpx create-t3-app@latest

Quick Start Examples

HTML/CSS Website

bash
mkdir my-website && cd my-website
touch index.html style.css
# Or use boilerplate:
npx degit h5bp/html5-boilerplate my-website

HTML + Tailwind (CDN)

html
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>My Website</title>
  <script src="https://cdn.tailwindcss.com"></script>
</head>
<body class="bg-gray-100">
  <h1 class="text-3xl font-bold">Hello World</h1>
</body>
</html>

T3 Stack (Next.js + tRPC + Prisma)

bash
npx create-t3-app@latest my-app

Expo (React Native)

bash
npx create-expo-app@latest my-app --template tabs

Tauri Desktop App

bash
npm create tauri-app@latest my-app -- --template react-ts

Chrome Extension

bash
npm create plasmo@latest my-extension

Example Conversations

Simple HTML/CSS Website

User: Create a simple website with HTML and CSS

Claude: I'll create a static HTML/CSS website:

- Multi-page (Home, About, Contact)
- Mobile-first responsive CSS
- BEM naming convention
- Live Server for development

Structure:
my-website/
├── index.html
├── about.html
├── contact.html
├── css/style.css
├── js/main.js
└── images/

Shall I create this?

Mobile App

User: Create a mobile app for iOS and Android

Claude: I recommend Expo for the easiest setup:

- TypeScript
- Expo Router (file-based navigation)
- NativeWind (Tailwind for RN)
- Tab navigation template

Ready to scaffold?

Full-Stack with Type Safety

User: Create a full-stack app with type-safe API

Claude: I recommend the T3 Stack:

- Next.js 16 (App Router)
- tRPC (type-safe API)
- Prisma (type-safe ORM)
- Tailwind CSS
- NextAuth.js
- PostgreSQL with docker-compose

This gives you full type safety from database to frontend!

Chrome Extension

User: Build a Chrome extension

Claude: What features do you need?

- Popup UI
- Content script (modifies pages)
- Background service worker
- Side panel

Tech stack: React + Vite + TypeScript + Manifest V3

I recommend using Plasmo framework for easier development.

Recording Observations

This skill improves from real usage. Append a line to assets/observations.md when — and only when — one of these happens during a scaffolding session:

TriggerExample line
User rejects a recommended default`2026-09-12
Requested framework or option is missing`2026-09-12
Generated project fails to install or start`2026-09-12
A template is wrong for the pinned major`2026-09-12

Format: DATE | TAG | project-type | one-line factual description. Record only what actually happened — never speculation about what users might want. Do not log successful, unremarkable scaffolds; a log of routine successes carries no signal and buries the real findings.

Use the scaffolding-maintainer skill to act on the accumulated log.

Available Resources

Load reference files based on what you need:

ResourceWhen to LoadPurpose
assets/versions.jsonAlways, via v()/req() in scaffold.pySingle source of truth for every dependency version
references/wizard-options.mdDuring Step 3 (gathering user preferences)Configuration choices and defaults for each framework
references/frameworks.mdWhen generating codeProject structures, code examples, configuration files
references/best-practices.mdFor architecture decisionsDirectory organization, naming conventions, patterns
scripts/scaffold.pyFor custom scaffoldingPython engine when CLI tools aren't suitable
scripts/refresh_versions.pyWhen the manifest is staleQueries npm/PyPI for current versions

Workflow:

  1. Present options from wizard-options.md to gather user preferences
  2. Use frameworks.md for code patterns and project structure when generating
  3. Consult best-practices.md for architecture decisions

Default Recommendations

Runtime and SDK versions are not listed here — they live in assets/versions.json under runtimes and are reported by python3 scripts/scaffold.py --version-status. Read them from there so this table cannot drift out of sync with what the scaffolder actually generates.

CategoryRecommendation
Package Managerpnpm
CSS FrameworkTailwind CSS
State (React)Zustand + TanStack Query
ORM (Node)Prisma
ORM (Python)SQLAlchemy 2.0
ORM (Go)sqlc
Testing (JS)Vitest
Testing (Python)pytest
E2E TestingPlaywright
Linting (JS)ESLint + Prettier
Linting (Python)Ruff
CI/CDGitHub Actions
ContainerizationMulti-stage Dockerfile

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 Project Scaffolding AI skill do?

IDE-grade project scaffolding wizard for creating new projects with comprehensive configuration. Supports 70+ project types: HTML/CSS websites, React, Next.js, Vue, Astro, Remix, React Native, Flutter, Expo, FastAPI, Django, Express, NestJS, Go/Gin, Rust/Axum, Spring Boot, Hono, Elysia, Chrome Extensions, VS Code Extensions, Tauri desktop apps, serverless functions, and more. Provides WebStorm/PyCharm-level project creation with interactive SDK selection, framework configuration, database setup, and DevOps tooling. Use when: creating a new project, setting up a framework application, initia...

Why use Project Scaffolding on TypingMind?

Because you install it once and use it with any model. Project Scaffolding 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 Project Scaffolding in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hmohamed01/Claude-Code-Scaffolding-Skill/tree/main/project-scaffolding. 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 Project Scaffolding?

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 Project Scaffolding?

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

Is the Project Scaffolding AI skill free?

It is published on GitHub by hmohamed01. 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 👇