Topics
- MCP
- TypeScript
- chatgpt
- app-builder
- llm
- ui
- oauth
- deployment
- skybridge
What it does
Guides developers through the complete lifecycle of building ChatGPT apps—from ideation and project setup through implementation, debugging, and deployment to the ChatGPT Directory. Covers the Skybridge MCP server framework, tool integration, custom UI views, state management, OAuth, and the dual-user model where both the human and ChatGPT LLM interact with the same view.
Generated from the current SKILL.md.
Frequently asked
What is a ChatGPT app and how does it work?
A ChatGPT app is a conversational experience that extends ChatGPT through tools and custom UI views, built as an MCP server. The view serves as a shared surface where both the human user and the ChatGPT LLM interact and collaborate.
Do I need a SPEC.md file before building?
Yes. You should read discover.md first to create a SPEC.md that documents your app's requirements and design decisions before implementing anything.
What does this skill cover?
The skill guides the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools and views, debugging, running dev servers, deploying via Alpic, and publishing to the ChatGPT Directory.
Does this skill provide API documentation?
Yes. Full API docs are available at https://docs.skybridge.tech/api-reference.md, and the skill includes implementation references for specific tasks like OAuth, state management, and CSP configuration.
Generated from the current SKILL.md. These answers refresh after source changes.