Webf Quickstart logo

Webf Quickstart

OrganizationPopular
openwebf
webf-quickstart

Get started with WebF development - setup WebF Go, create a React/Vue/Svelte project with Vite, and load your first app. Use when starting a new WebF project, onboarding new developers, or setting up development environment.

Overview

Publisheropenwebf
Repositorywebf
Skill namewebf-quickstart
Stars
2.5K
Forks
163
Bundled files
1
LicenseGPL-3.0
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Webf Quickstart 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/openwebf/webf.git /tmp/webf
mkdir -p .claude/skills
cp -r /tmp/webf/skills/webf-quickstart .claude/skills/webf-quickstart
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Webf Quickstart 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 Webf Quickstart 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 Webf Quickstart 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.

WebF Quickstart

Note: Building WebF apps is nearly identical to building regular web apps with Vite + React/Vue/Svelte. The only difference is you replace your browser with WebF Go for testing during development. Everything else - project structure, build tools, testing frameworks, and deployment - works the same way.

⚠️ IMPORTANT: WebF Go is for development and testing ONLY. For production, you must build a Flutter app with WebF integration. Do NOT distribute WebF Go to end users.

Get up and running with WebF in minutes. This skill guides you through setting up your development environment, creating your first project, and loading it in WebF Go.

What You Need

Only Node.js is required - that's it!

  • Node.js (LTS version recommended) from nodejs.org
  • You do NOT need: Flutter SDK, Xcode, or Android Studio

WebF lets web developers build native apps using familiar web tools.

Step-by-Step Setup

1. Download WebF Go (For Testing Only)

WebF Go is a pre-built native app containing the WebF rendering engine. It's designed for development and testing purposes only - not for production deployment.

For Desktop Development:

For Mobile Testing:

  • iOS: Download from App Store
  • Android: Download from Google Play

Remember: WebF Go is a testing tool. For production apps, you'll need to build a Flutter app with WebF integration.

Launch WebF Go - you'll see an input field ready to load your app.

2. Create Your Project with Vite

Open your terminal and create a new project:

bash
npm create vite@latest my-webf-app

Vite will prompt you to:

  1. Choose a framework: React, Vue, Svelte, etc.
  2. Choose a variant (JavaScript or TypeScript)

3. Install Dependencies and Start Dev Server

bash
# Move into your project
cd my-webf-app

# Install dependencies
npm install

# Start the dev server
npm run dev

Your terminal will show URLs like:

  VITE v5.0.0  ready in 123 ms

  ➜  Local:   http://localhost:5173/
  ➜  Network: http://192.168.1.100:5173/

4. Load in WebF Go

For Desktop:

  1. Copy the http://localhost:5173/ URL
  2. Paste into WebF Go's input field
  3. Press Enter or click "Go"

For Mobile Device: ⚠️ IMPORTANT: Mobile devices cannot access localhost

You MUST use the Network URL instead:

  1. Make sure your computer and mobile device are on the same WiFi network
  2. Use --host flag to expose the dev server:
    bash
    npm run dev -- --host
  3. Copy the Network URL (e.g., http://192.168.1.100:5173/)
  4. Type it into WebF Go on your mobile device
  5. Press "Go"

Your app will now render in WebF! 🎉

5. Verify Hot Reload

Make a quick change to your code and save. The app should automatically update - this is Vite's Hot Module Replacement (HMR) working with WebF.

6. (Optional) Setup Chrome DevTools

To debug your app:

  1. Click the floating debug button in WebF Go
  2. Click "Copy" to get the DevTools URL (devtools://...)
  3. Paste into desktop Google Chrome browser
  4. You can now use Console, Elements, Network tabs

Note: JavaScript breakpoints don't work yet - use console.log() instead.

Common Issues and Solutions

Issue: "Cannot connect" on mobile device

Causes & Solutions:

  • ✗ Using localhost → ✓ Use Network URL (http://192.168.x.x:5173)
  • ✗ Different WiFi networks → ✓ Put both devices on same network
  • ✗ Missing --host flag → ✓ Use npm run dev -- --host
  • ✗ Firewall blocking port → ✓ Allow port 5173 through firewall

Issue: "Connection refused"

  • Dev server not running → Run npm run dev
  • Wrong port number → Check terminal output for correct port
  • Firewall blocking → Temporarily disable to test

Issue: App loads but doesn't update

  • HMR not working → Refresh the page manually
  • Dev server error → Check terminal for errors
  • Network connection lost → Reconnect WiFi

Production Deployment

⚠️ WebF Go is NOT for production use. It's a testing tool for developers.

For Production Apps

When you're ready to deploy to end users, you need to:

1. Build Your Web Bundle

bash
npm run build

2. Host Your Bundle

  • Deploy to any web hosting (Vercel, Netlify, CDN, etc.)
  • Your bundle will be accessible via URL (e.g., https://your-app.com)

3. Create a Flutter App with WebF Integration

You or your Flutter team needs to:

  • Set up a Flutter project
  • Add the WebF Flutter package to pubspec.yaml
  • Configure the app (name, icon, splash screen, permissions)
  • Load your web bundle URL in the WebF widget

Example Flutter Integration:

dart
import 'package:webf/webf.dart';

class MyApp extends StatelessWidget {
  
  Widget build(BuildContext context) {
    return WebF(
      bundle: WebFBundle.fromUrl('https://your-app.com'),
    );
  }
}

4. Build and Deploy Flutter App

  • Build for iOS and Android
  • Submit to App Store and Google Play

Resources:

Development vs Production

AspectDevelopmentProduction
ToolWebF GoCustom Flutter app
PurposeTesting & iterationEnd-user distribution
SetupDownload and runBuild Flutter app
DistributionDon't distributeApp Store/Google Play
RequirementsNode.js onlyFlutter SDK required

Next Steps

Now that you have a working dev environment:

  1. Learn the #1 difference: WebF uses async rendering - see the webf-async-rendering skill
  2. Check API compatibility: Not all web APIs work in WebF - see webf-api-compatibility skill
  3. Add navigation: Multi-screen apps use WebF routing - see webf-routing-setup skill

Quick Reference

bash
# Create new project
npm create vite@latest my-app

# Start dev server (desktop)
npm run dev

# Start dev server (mobile - with network access)
npm run dev -- --host

# Install dependencies
npm install

# Build for production
npm run build

Resources

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 Webf Quickstart AI skill do?

Get started with WebF development - setup WebF Go, create a React/Vue/Svelte project with Vite, and load your first app. Use when starting a new WebF project, onboarding new developers, or setting up development environment.

Why use Webf Quickstart on TypingMind?

Because you install it once and use it with any model. Webf Quickstart 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 Webf Quickstart in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openwebf/webf/tree/main/skills/webf-quickstart. 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 Webf Quickstart?

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 Webf Quickstart?

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

Is the Webf Quickstart AI skill free?

Yes. It is published on GitHub by openwebf under the GPL-3.0 license. 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 👇