building-chatgpt-apps SKILL.md skillF

building-chatgpt-apps from mjunaidca/mjs-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mjunaidca/mjs-agent-skills/building-chatgpt-apps@git:20251222.ace8bd5

Pins git:20251222.ace8bd5 in mdr.lock. Pin the fingerprint instead.

Audit grade
F, 15 of 17 checks passed
Kind
SKILL.md skill
Repository
mjunaidca/mjs-agent-skills
Path
.claude/skills/building-chatgpt-apps/SKILL.md
Versions recorded
1
Latest version
git:20251222.ace8bd5, committed Dec 22, 2025
Size
13,522 bytes
Repository stars
28
License
none declared

Guides creation of ChatGPT Apps with interactive widgets using OpenAI 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).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ChatGPT Apps SDK Development Guide

## Overview

Create ChatGPT Apps with interactive widgets that render rich UI inside ChatGPT conversations. Apps combine MCP servers (providing tools) with embedded HTML widgets that communicate via the `window.openai` API.

---

## window.openai API Reference

Widgets communicate with ChatGPT through these APIs:

### sendFollowUpMessage (Recommended for Actions)

Send a follow-up prompt to ChatGPT on behalf of the user:

```javascript
// Trigger a follow-up conversation
if (window.openai?.sendFollowUpMessage) {
  await window.openai.sendFollowUpMessage({
    prompt: 'Summarize this chapter for me'
  });
}
```

**Use for**: Action buttons that suggest next steps (summarize, explain, etc.)

### toolOutput

Send structured data back from widget interactions:

```javascript
// Send data back to ChatGPT
if (window.openai?.toolOutput) {
  window.openai.toolOutput({
    action: 'chapter_selected',
    chapter: 1,
    title: 'Introduction'
  });
}
```

**Use for**: Selections, form submissions, user choices that feed into tool responses.

### callTool

Call another MCP tool from within a widget:

```javascript
// Call a tool directly
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mjunaidca/mjs-agent-skills/building-chatgpt-apps@sha256:b8aff5d8b7f84116

The line at the top of this page pins the label git:20251222.ace8bd5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_kye2glkva3smqx5p.svg)](https://markdownregistry.com/a/art_kye2glkva3smqx5p)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Dec 22, 2025.

versioncommittedcommitsizeaudit
git:20251222.ace8bd5 latest2025-12-22 ace8bd5 13,522 BF view

Audit of the latest version

F  15 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • FAIL, critical: No link to an exfiltration or paste host (matched: https://your-tunnel.ngrok-free.app)
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13522 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

mjunaidca/mjs-agent-skills · 28 stars · license none declared · pushed 2026-08-12 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kye2glkva3smqx5p
GET https://markdownregistry.com/api/v1/resolve?ref=mjunaidca/mjs-agent-skills/building-chatgpt-apps
GET https://markdownregistry.com/api/v1/blob/b8aff5d8b7f84116b765cc384a9585e171455d6e41861d8d24af11776695e0c2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from mjunaidca/mjs-agent-skills

browsing-with-playwright SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/browsing-with-playwright/SKILL.md · Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract…
git:20251221.180758f · audit A · 28 stars
building-chat-interfaces SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/building-chat-interfaces/SKILL.md · Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with…
git:20251222.3cc0c3c · audit B · 28 stars
building-chat-widgets SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/building-chat-widgets/SKILL.md · Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with…
git:20251222.3cc0c3c · audit A · 28 stars
building-mcp-servers SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/building-mcp-servers/SKILL.md · Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
git:20251221.e60e67d · audit A · 28 stars
building-nextjs-apps SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/building-nextjs-apps/SKILL.md · Build Next.js 16 applications with correct patterns and distinctive design. Use when creating pages, layouts, dynamic…
git:20251222.3cc0c3c · audit A · 28 stars
building-rag-systems SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/building-rag-systems/SKILL.md · Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when…
git:20251222.1a21d20 · audit A · 28 stars
configuring-better-auth SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/configuring-better-auth/SKILL.md · Implement OAuth 2.1 / OIDC authentication using Better Auth with MCP assistance. Use when setting up a centralized auth…
git:20251222.3cc0c3c · audit A · 28 stars
creating-skills SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/creating-skills/SKILL.md · Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new…
git:20251222.8a87f42 · audit A · 28 stars
docker SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/docker/SKILL.md · Production-grade Docker containerization for Python and Node.js applications. This skill should be used when users ask…
git:20260124.14c9905 · audit A · 28 stars
evaluation SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/evaluation/SKILL.md · Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering…
git:20251222.04068a4 · audit A · 28 stars
fetching-library-docs SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/fetching-library-docs/SKILL.md · Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings. Fetches code examples, API…
git:20251222.3cc0c3c · audit A · 28 stars
helm SKILL.md skill
mjunaidca/mjs-agent-skills · .claude/skills/helm/SKILL.md · Production-grade Helm 4 chart development, release management, and debugging. This skill should be used when users ask…
git:20260124.14c9905 · audit A · 28 stars

Every file in mjunaidca/mjs-agent-skills

Browse by kind, by grade F, or by owner.