chatgpt-app-builder

alpic-ai/skybridge

Build conversational ChatGPT apps with tools and custom UI views using the Skybridge MCP framework.

What is chatgpt-app-builder?

A framework and guide for creating ChatGPT apps that extend the LLM through tools and custom UI views. Use this when building new ChatGPT applications or updating existing ones, from initial design through deployment to the ChatGPT Directory.

Design UX flows and API architecture for LLM-integrated apps
Bootstrap new ChatGPT app projects from templates
Implement server handlers, data fetching, and view rendering
Manage view state and LLM context updates
Configure OAuth authentication for user-specific data access
Deploy apps to production and publish to ChatGPT Directory

How to install chatgpt-app-builder

npx skills add https://github.com/alpic-ai/skybridge --skill chatgpt-app-builder

Prerequisites

Node.js environment for running dev servers
Understanding of MCP (Model Context Protocol) servers
ChatGPT account for testing and deployment

Claude Code

Cursor

Windsurf

Cline

How to use chatgpt-app-builder

1.Create or review SPEC.md to document app requirements and design decisions
2.Read architecture.md to design UX flows and API shape for your feature
3.Follow the relevant implementation guide (fetch-and-render-data.md, state-and-context.md, etc.) based on what you're building
4.Use copy-template.md to bootstrap a new project with the template
5.Run the dev server locally with run-locally.md to test your changes
6.Deploy to production using deploy.md when ready
7.Publish to ChatGPT Directory using publish.md for wider distribution

Use cases

Good for

Building a new ChatGPT app that provides custom tools and interactive UI
Updating an existing ChatGPT app with new features or views
Implementing authentication for apps that need user-specific data
Debugging and testing ChatGPT apps locally before deployment
Publishing a completed app to the ChatGPT Directory

Who it's for

Full-stack developers building ChatGPT extensions
Backend developers implementing MCP servers
Frontend developers designing conversational UI experiences
Teams deploying LLM-integrated applications

chatgpt-app-builder FAQ

What is a ChatGPT app?

A ChatGPT app is a conversational experience that extends ChatGPT through tools and custom UI views. It's built as an MCP server that the LLM invokes during conversations.

Who are the two users of a ChatGPT app?

The human user interacts with the view directly, while the ChatGPT LLM sees the view's state and collaborates through it. The view is the shared surface between both users.

Where do I start if I don't have a SPEC.md yet?

Read discover.md first to understand the app's requirements and design decisions. Create SPEC.md before proceeding with any other steps.

How do I test my app locally?

Use run-locally.md to set up and run a dev server, then connect it to ChatGPT for testing before deploying to production.

What if my app needs user authentication?

Follow oauth.md to implement OAuth authentication for tools that need access to user-specific data.

Full instructions (SKILL.md)

Source of truth, from alpic-ai/skybridge.

name: chatgpt-app-builder description: | Guide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app / MCP server for ChatGPT, or use the Skybridge framework.

Creating Apps For LLMs

ChatGPT apps are conversational experiences that extend ChatGPT through tools and custom UI views. They're built as MCP servers invoked during conversations.

⚠️ The app is consumed by two users at once: the human and the ChatGPT LLM. They collaborate through the view—the human interacts with it, the LLM sees its state. Internalize this before writing code: the view is your shared surface.

SPEC.md keeps track of the app's requirements and design decisions. Keep it up to date as you work on the app.

No SPEC.md? → Read discover.md first. Nothing else until SPEC.md exists.

SPEC.md exists? → Read SPEC.md, then follow architecture.md to design the change. Update SPEC.md, then read the relevant Implementation references below before writing code.

Setup

Copy template → copy-template.md: when starting a new project with ready SPEC.md
Run locally → run-locally.md: when ready to test, need dev server or ChatGPT connection

Architecture

Design or evolve UX flows and API shape → architecture.md

Implementation

Fetch and render data → fetch-and-render-data.md: when implementing server handlers and view data fetching
State and context → state-and-context.md: when persisting view UI state and updating LLM context
Prompt LLM → prompt-llm.md: when view needs to trigger LLM response
UI guidelines → ui-guidelines.md: display modes, layout constraints, theme, device, and locale
External links → open-external-links.md: when redirecting to external URLs or setting "open in app" target
OAuth → oauth.md: when tools need user authentication to access user-specific data
CSP → csp.md: when declaring allowed domains for fetch, assets, redirects, or iframes