Agent skill · Frontend

building-chatgpt-apps

Guides creation of ChatGPT Apps with interactive widgets using the Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill building-chatgpt-apps --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 20 KB
Bundled scripts: none
Path: skills/ai-llm/building-chatgpt-apps/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Apps SDK Development Guide ## Overview Create ChatGPT Apps with interactive widgets that render rich UI inside ChatGPT conversations. The Apps SDK combines MCP servers (providing tools) with embedded HTML widgets that communicate via the `window.openai` API. **Official Documentation**: https://developers.openai.com/apps-sdk/ **Examples Repository**: https://github.com/openai/openai-apps-sdk-examples ## Three-Layer Architecture ``` ┌─────────────────────────────────────────────────────────────────┐ │ ChatGPT UI │ │ ┌─────────────────────────────────────────────────────────────┐│ │ │ Widget (iframe) ││ │ │ React/Vanilla JS + CSS ││ │ │ window.openai.* APIs for host communication ││ │ └─────────────────────────────────────────────────────────────┘│ │ │ │ │ ▼ │ │ ChatGPT Backend │ │ │ │ │ ▼ │ │ MCP Server (HTTP/SSE) │ │ - Tools: exposed actions │ │ - Resources: widget HTML (text/html+skybridge) │ │ - Response: structuredContent + _meta │ └─────────────────────────────────────────────────────────────────┘ ``` **Flow**: User prompt → Model invokes tool → Server returns structured data → Widget renders → Model narrates result --- ## window.openai API Reference Complete API surface for w

What's inside
Steps it walks through
  1. Overview
  2. Three-Layer Architecture
  3. window.openai API Reference
  4. State & Data Access
  5. Runtime Actions
  6. Layout Control
  7. Context Properties (Read-Only)
  8. Code Examples
  9. Tool Definition with Metadata
  10. TypeScript/Node.js Pattern
  11. Python/FastMCP Pattern
  12. Tool Metadata Reference
  13. Response Payload Structure
  14. Widget Resource Registration
Ships with 1 file
  • metadata.json
Commands it runs
cd my_chatgpt_app
python main.py
Server runs on http://localhost:8001
ngrok http 8001
Get URL like: https://abc123.ngrok-free.app
More from claude-skill-registry
All skills →
About this skill
What does the building-chatgpt-apps skill do?

Guides creation of ChatGPT Apps with interactive widgets using the Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill building-chatgpt-apps --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going