chatgpt-apps

Scaffold, refactor, and troubleshoot ChatGPT Apps SDK MCP server and widget components.

4|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/heyzude/skills_for_codex --skill chatgpt-apps-heyzude
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chatgpt-apps
Source: https://github.com/heyzude/skills_for_codex/tree/main/skills_by_openai/chatgpt-apps
Command: npx skills add https://github.com/heyzude/skills_for_codex --skill chatgpt-apps-heyzude

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill streamlines the development of ChatGPT Apps SDK applications, enabling users to build, scaffold, refactor, and troubleshoot complex integrations that combine MCP server logic with widget user interfaces.

Core Features & Use Cases

  • Scaffolding: Generates complete ChatGPT Apps SDK project structures.
  • Tooling: Designs and registers tools, including schema definition and annotation.
  • UI Development: Creates MCP server and widget components, integrating with the MCP Apps bridge and window.openai APIs.
  • Workflow Guidance: Enforces a docs-first approach using $openai-docs and provides clear validation against a minimum working repo contract.
  • Use Case: A developer needs to create a new ChatGPT app that allows users to search a knowledge base, display results in a custom widget, and perform actions based on those results. This Skill will scaffold the entire application, define the necessary search and display tools, and set up the server and widget code.

Quick Start

Use the chatgpt-apps skill with openai-docs to scaffold a ChatGPT app for <use case> with a <TS/Python> MCP server and <React/vanilla> widget.

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 Apps SDK application with an MCP server and widget?

Scaffolding a ChatGPT Apps SDK application generates complete project structures combining MCP server logic with widget UI components. This Skill creates the foundational repo, registers tools, and sets up the server and widget code for immediate development.

What is the docs-first workflow for building ChatGPT apps?

The docs-first workflow integrates OpenAI developer documentation directly into the development process. It enforces best practices for tool design and UI implementation by validating your project against a minimum working repo contract before writing functional code.

Can I use TypeScript and Python when creating MCP server components?

Yes, you can scaffold MCP server components using either TypeScript or Python. The generated project integrates with the MCP Apps bridge and window.openai APIs to ensure proper communication between the server backend and the frontend widget components.

How do I design and register tools for a ChatGPT widget integration?

Designing and registering tools requires schema definition and annotation within the MCP server. This Skill facilitates tool creation by enforcing best practices for tool design, allowing your custom widget to trigger actions and display results based on user interactions.

What is the best way to troubleshoot an existing ChatGPT Apps SDK project?

Troubleshooting a ChatGPT Apps SDK project involves refactoring MCP server and widget components to align with the minimum working repo contract. This Skill validates your existing code against OpenAI developer documentation to identify and resolve integration issues.