chatgpt-apps

Scaffold ChatGPT Apps SDK applications with MCP server and widget UI.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/ironkid90/Lucky5-v7 --skill chatgpt-apps-ironkid90
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chatgpt-apps
Source: https://github.com/ironkid90/Lucky5-v7/tree/main/.github/skills/chatgpt-apps
Command: npx skills add https://github.com/ironkid90/Lucky5-v7 --skill chatgpt-apps-ironkid90

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-apps-sdk, @modelcontextprotocol/sdk, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of building and scaffolding ChatGPT Apps SDK applications, providing a structured approach to create applications that combine an MCP server and widget UI.

Core Features & Use Cases

  • Scaffold ChatGPT Apps SDK Implementations: Offers a docs-first, example-first workflow to generate code that follows current Apps SDK and MCP Apps bridge patterns.
  • MCP Server Scaffold: Generates a server that registers a widget resource/template and registers tools with clear names, schemas, titles, and descriptions.
  • Widget Scaffold: Generates a widget UI that uses the MCP Apps bridge for portability and optionally integrates ChatGPT-specific window.openai APIs for enhanced UX.
  • Documentation Alignment: Ensures that the generated code aligns with current OpenAI Apps SDK documentation and best practices.
  • Validation and Testing: Provides local run/test instructions and validation against a minimum working repo contract to ensure the application is functional and secure.

Quick Start

Use the chatgpt-apps skill to scaffold a new ChatGPT app with a minimal demo pattern.

Frequently Asked Questions about chatgpt-apps

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scaffold a ChatGPT app with an MCP server and widget UI?

Scaffolding a ChatGPT app involves generating an MCP server that registers widget resources and tools alongside a widget UI using the MCP Apps bridge. This skill provides a docs-first workflow ensuring code alignment with current Apps SDK patterns and best practices.

What is the MCP Apps bridge and how does it work with widget UI development?

The MCP Apps bridge enables widget UI portability within ChatGpt Apps SDK applications. The generated widget scaffold uses this bridge for communication and optionally integrates ChatGPT-specific window.openai APIs to enhance the user experience.

Do I need the OpenAI Apps SDK to build ChatGPT applications with this tool?

Yes, the OpenAI Apps SDK is a required dependency for building and scaffolding ChatGPT applications. You also need the @modelcontextprotocol/sdk to implement the MCP server and widget UI patterns correctly.

Can I use the window.openai APIs in my ChatGPT widget without losing portability?

You can use ChatGPT-specific window.openai APIs to enhance UX, but the scaffolded widget uses the MCP Apps bridge as its foundation for portability. The window.openai integration is optional to maintain compatibility across environments.

How do I validate and test a scaffolded ChatGPT Apps SDK application locally?

The skill provides local run and test instructions, validating the generated application against a minimum working repo contract. This ensures the MCP server and widget UI are functional, secure, and aligned with SDK documentation.

What are the limitations of scaffolding ChatGPT apps with the MCP Apps bridge?

The scaffold focuses specifically on MCP server and widget UI patterns using the Apps SDK. It requires strict adherence to current OpenAI documentation patterns and depends on the openai-apps-sdk and modelcontextprotocol/sdk environments for functionality.