chatgpt-apps

Scaffold ChatGPT Apps SDK projects coupling an MCP server with a widget UI.

2|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/metric-space-ai/ctox --skill chatgpt-apps-metric-space-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chatgpt-apps
Source: https://github.com/metric-space-ai/ctox/tree/main/skills/packs/development/chatgpt-apps
Command: npx skills add https://github.com/metric-space-ai/ctox --skill chatgpt-apps-metric-space-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams scaffold, refactor, and govern ChatGPT Apps SDK projects that combine an MCP server and widget UI. It addresses the complexity of wiring UI resources, server tooling, and CSP/domain metadata, and guides users through a docs-first workflow to reduce integration risk and accelerate start-up.

Core Features & Use Cases

  • Docs-first scaffolding and plan generation for MCP-based ChatGPT Apps with a minimal server and a widget.
  • Upstream adaptation guidance: choose between official examples, ext-apps baselines, or local scaffolds, and reconcile with current docs.
  • Validation and governance: a lightweight contract and guidance to ensure a runnable repo with /mcp route, registered resources and tools, and widget rendering.
  • Local development and testing steps, plus hosting and submission considerations for production deployments.

Quick Start

Scaffold a minimal ChatGPT Apps repository using the docs-first workflow and adapt it to your use case.

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?

To scaffold a ChatGPT App, this skill generates a minimal repository combining an MCP server with a widget UI. It delivers registered server endpoints, tool definitions, and widget metadata using a docs-first workflow to ensure production-ready alignment with the Apps SDK.

What is a docs-first workflow for ChatGPT Apps SDK development?

A docs-first workflow for ChatGPT Apps SDK guides you through wiring UI resources and server tooling by aligning with current documentation. This approach reduces integration risk by validating the repo shape, /mcp route, and CSP domain metadata before deployment.

Can I adapt upstream official examples for my MCP server and widget UI?

Yes, you can adapt upstream examples for your MCP server and widget UI. The skill provides guidance on choosing between official examples, ext-apps baselines, or local scaffolds, and reconciles them with current Apps SDK docs.

How do I validate that my ChatGPT Apps repository is ready for production?

To validate your ChatGPT Apps repository for production, the skill applies a lightweight governance contract. It checks for a runnable repo with a registered /mcp route, defined resources and tools, and proper widget rendering metadata.

Does this scaffolding tool handle hosting and submission for OpenAI Apps deployments?

Yes, the scaffolding tool handles hosting and submission considerations for OpenAI Apps deployments. It provides local development steps and testing guidance alongside production governance to ensure your MCP server and widget UI are deployment-ready.

What are the limitations of using a minimal scaffold for ChatGPT Apps?

Using a minimal scaffold for ChatGPT Apps limits you to basic server and widget UI configurations. It focuses on minimal validation and registered endpoints, meaning teams needing complex custom logic beyond the docs-first baseline must extend the generated repo manually.