chatgpt-app-builder — Claude Code skill: build ChatGPT plugins
Walks through the full lifecycle of a ChatGPT plugin, from idea to directory submission. Use it when building an MCP server with UI for ChatGPT on Skybridge.
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a claude-codeWhat chatgpt-app-builder does
chatgpt-app-builder is built for one job: creating ChatGPT plugins, formerly called ChatGPT apps. Under the hood these are MCP servers invoked mid-conversation, with custom UI views. The skill keeps repeating a core point — the plugin has two users at once. The human interacts with the view, the LLM reads its state. That shared surface shapes every design decision.
Inside is a set of references, one per stage. No project yet? It sends you to discover.md and refuses to proceed until SPEC.md exists. From there architecture.md covers UX flows and API shape, then implementation splits into narrow topics: fetching data in handlers, persisting view state, prompting the LLM from the view, OAuth, CSP, events, assets. Ecommerce plugins get a dedicated ecommerce.md to read first.
Deployment goes through Alpic, with a separate reference for submitting to the ChatGPT Directory. Migrating from Skybridge < 0.36.x or 1.x to 2.x? The skill fetches release notes first and expects you to follow them. MIT licensed, source in alpic-ai/skybridge.
What it helps with
- design a plugin UX flow against ChatGPT guidelines
- bootstrap a project from a template with a ready SPEC.md
- run a dev server and connect the plugin to ChatGPT
- add OAuth so tools can reach user-specific data
- run evals and check the model reaches the right tools from natural prompts
Example prompts for the agent
- Create a ChatGPT plugin: idea is restaurant booking via chat
- Help me draft a SPEC.md for an online booking plugin
- Set up OAuth in my Skybridge plugin
How to install chatgpt-app-builder
1Skills CLI (Vercel)
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a claude-code2Manually: put the files in place
~/.claude/skills/chatgpt-app-builder/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/chatgpt-app-builder/
1Skills CLI (Vercel)
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a codex2Manually: put the files in place
.agents/skills/chatgpt-app-builder/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a cursor2Manually: put the files in place
.cursor/skills/chatgpt-app-builder/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alpic-ai/skybridge chatgpt-app-builder2Manually: put the files in place
.github/skills/chatgpt-app-builder/SKILL.md1Skills CLI (Vercel)
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a gemini-cli2Platform CLI
gemini skills install https://github.com/alpic-ai/skybridge --path skills/chatgpt-app-builderManually: put the files in place
.devin/skills/chatgpt-app-builder/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Similar
Questions about chatgpt-app-builder
How do I install chatgpt-app-builder in Claude Code?
Run npx skills add alpic-ai/skybridge --skill chatgpt-app-builder -a claude-code. The skill lands in ~/.claude/skills/chatgpt-app-builder/SKILL.md.
What does chatgpt-app-builder do?
It guides you through the whole ChatGPT plugin lifecycle: brainstorming ideas against UX guidelines, bootstrapping the project, implementing tools and views, debugging, deploying via Alpic, and publishing to the ChatGPT Directory.
What should I read before starting an ecommerce plugin?
The skill points to ecommerce.md first. That reference covers ecommerce-specific requirements before you touch any other part of the process.
Source text
SKILL.md · MIT
--- name: chatgpt-app-builder description: | Guide developers through creating and updating ChatGPT plugins. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting plugins to ChatGPT. Use when a user wants to create or update a ChatGPT plugin (formerly called a ChatGPT app) / MCP server for ChatGPT, or use the Skybridge framework. --- # Creating Plugins For LLMs ChatGPT plugins are conversational experiences that extend ChatGPT through tools and custom UI views. They're built as MCP servers invoked during conversations. ⚠️ The plugin is consumed by two users at once: the **human** and the **ChatGPT LLM**. They collaborate through the view—the human interacts with it, the LLM sees its state. Internalize this before writing code: the view is your shared surface. SPEC.md keeps track of the plugin's requirements and design decisions. Keep it up to date as you work on the plugin. **Building an ecommerce plugin?** → Read [ecommerce.md](references/ecommerce.md) first. **No SPEC.md?** → Read [discover.md](references/discover.md) first. Nothing else until SPEC.md exists. **SPEC.md exists?** → Read SPEC.md, then follow [architecture.md](references/architecture.md) to design the change. Update SPEC.md, then read the relevant Implementation references below before writing code. **Migrating from Skybridge `< 0.36.x`?** → Read [migrate-to-v1.md](references/migrate-to-v1.md) first. Users may reference `skybridge >= 0.36.x` as v1. **Migrating from Skybridge `1.x` to `2.x`?** → Fetch the [v2.0.0 release notes](https://github.com/alpic-ai/skybridge/releases/tag/v2.0.0) first and follow them. ## Setup 1. **Copy template** → [copy-template.md](references/copy-template.md): when starting a new project with ready SPEC.md 2. **Run locally** → [run-locally.md](references/run-locally.md): when ready to test, need dev server or ChatGPT connection 3. **Evals** → [evals.md](references/evals.md): when checking that a real model reaches the right tools from natural prompts, in a test ## Architecture Design or evolve UX flows and API shape → [architecture.md](references/architecture.md) ## Implementation - **Fetch and render data** → [fetch-and-render-data.md](references/fetch-and-render-data.md): when implementing server handlers and view data fetching - **State and context** → [state-and-context.md](references/state-and-context.md): when persisting view UI state and updating LLM context - **Prompt LLM** → [prompt-llm.md](references/prompt-llm.md): when view needs to trigger LLM response - **UI guidelines** → [ui-guidelines.md](references/ui-guidelines.md): display modes, layout constraints, theme, device, and locale - **External links** → [open-external-links.md](references/open-external-links.md): when redirecting to external URLs or setting "open in app" target - **OAuth** → [oauth.md](references/oauth.md): when tools need user authentication to access user-specific data - **Assets and styling** → [assets-and-styling.md](references/assets-and-styling.md): when adding images, fonts or CSS to views - **CSP** → [csp.md](references/csp.md): when declaring allowed domains for fetch, assets, redirects, or iframes - **Events** → [events.md](references/events.md): when ChatGPT should react to activity in the app without the user, such as new comments or incidents - **OpenAI MCP extensions** → [openai-extensions.md](references/openai-extensions.md): when the view should open from the ChatGPT sidebar, a conversation side panel, a file, or a deep link, or use ChatGPT at-mentions, titled messages or local files ## Deploy - **Ship to production** → [deploy.md](references/deploy.md): when ready to deploy via Alpic - **Publish to ChatGPT Directory** → [publish.md](references/publish.md): when ready to submit for review Full API docs: [https://docs.skybridge.tech/api-reference.md](https://docs.skybridge.tech/api-reference.md) Release notes & changelog: [https://skybridge.tech/changelog.md](https://skybridge.tech/changelog.md)
© alpic-ai · MIT · alpic-ai/skybridge