Chatgpt App Builder

OrganizationPopular

mcp-use

chatgpt-app-builder

Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.

Overview

Publisher	mcp-use
Repository	`mcp-use`
Skill name	`chatgpt-app-builder`
Stars	10.6K
Forks	1.5K
Bundled files	7
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
7 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by mcp-use on GitHub. Read the source before you install it.

Installation

Install the Chatgpt App Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/mcp-use/mcp-use.git /tmp/mcp-use
mkdir -p .claude/skills
cp -r /tmp/mcp-use/skills/chatgpt-app-builder .claude/skills/chatgpt-app-builder

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chatgpt App Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Chatgpt App Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Chatgpt App Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Build with mcp-use

Treat the installed mcp-use package, its exported types, generated declarations, and the project's existing code as the source of truth. Inspect the installed version before choosing APIs or changing code.

Workflow

Inspect package.json, the server entry, exported tool refs, mcp-env.d.ts, views/, skills/, and the installed mcp-use version.
Scaffold a new stable project with create-mcp-use-app@latest and the appropriate template. Match the package version or dist-tag when working on beta, canary, or an existing versioned project.
Read only the references needed for the task:
- Server for tools, resources, prompts, MCP middleware, request context, and result envelopes.
- Views for interactive MCP Apps, React hooks, model context, host capabilities, assets, and CSP.
- Authentication for OAuth providers, verified identity, scopes, permissions, and authorization.
- Skills over MCP when a server should ship reusable workflows alongside its tools.
- Advanced features for OpenAPI, proxying, notifications, subscriptions, and elicitation.
- Migration only when retired or compatibility-only imports, helpers, registration shapes, UI patterns, or session assumptions are present.
- Verification before reporting implementation work complete.
Implement against installed types. Prefer the framework's current conventions over copied examples or historical changelogs.
Validate the smallest real lifecycle that proves the changed behavior, then expand checks in proportion to risk.

Core invariants

Import server APIs from mcp-use, React APIs from mcp-use/react, and OAuth provider adapters from their mcp-use/oauth/* subpaths.
Define tool arguments with inputSchema. Add outputSchema for structured results and every View-bound tool.
Return raw MCP result envelopes. A successful schema-backed tool must include matching structuredContent; an expected failure may return isError: true with model-readable content.
Put each View at views/<name>/view.tsx and bind it with view: { name: "<name>" }.
Export every statically declared tool ref consumed by a View. Default-export the server entry used by mcp-use dev, build, and start.
Keep identity and mutable workflow state request-scoped or in an external store. Treat client-reported metadata as unverified.
Consider Skills over MCP when a server exposes a repeatable, multi-step workflow that would otherwise inflate tool descriptions.

Guardrails

Do not invent exports, configuration fields, or callback shapes. Confirm uncertain details in installed declarations or source.
Do not preserve APIs that are absent from the installed version merely because they appear in an existing project.
Do not return a plain domain object from a tool callback.
Do not bind a View without a matching outputSchema and structuredContent result.
Do not use module globals for cross-request identity, elicitation continuity, or durable business state.
Do not claim success from a source build alone when types, package exports, authentication, or interactive behavior changed.
Do not deploy or mutate external systems unless the user explicitly requests it.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Chatgpt App Builder AI skill do?

Why use Chatgpt App Builder on TypingMind?

Because you install it once and use it with any model. Chatgpt App Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Chatgpt App Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mcp-use/mcp-use/tree/main/skills/chatgpt-app-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Chatgpt App Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Chatgpt App Builder?

As many as you like. As long as a model supports skills, you can use Chatgpt App Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Chatgpt App Builder AI skill free?

Yes. It is published on GitHub by mcp-use under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Using Git Worktrees

obra

CommunityPopular

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Using Superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Verification Before Completion

obra

CommunityPopular

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence…

Writing Plans

Use when you have a spec or requirements for a multi-step task, before touching code

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Build with mcp-use

Workflow

Core invariants

Guardrails

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now