Skillzwave Logo
Skillzwave

building-chatgpt-apps

1 stars 2 forks
17
B

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 richinteractive experiences. Covers widget architecture, MCP server setup with FastMCP, responsemetadata, and Developer Mode configuration. NOT when building standard MCP servers withoutwidgets (use building-mcp-servers skill instead).

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install mjunaidca/mjs-agent-skills/building-chatgpt-apps
skilz install mjunaidca/mjs-agent-skills/building-chatgpt-apps --agent opencode
skilz install mjunaidca/mjs-agent-skills/building-chatgpt-apps --agent codex
skilz install mjunaidca/mjs-agent-skills/building-chatgpt-apps --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/mjunaidca/mjs-agent-skills
2. Copy the agent skill directory:
cp -r mjs-agent-skills/.claude/skills/building-chatgpt-apps ~/.claude/skills/
View on GitHub

Need detailed installation help? Check our platform-specific guides:

Claude Desktop Guide Claude Code Guide Troubleshooting

Related Agentic Skills

command-name

by anthropics

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components"...

54
TECHjson
Marketplace

mcp-integration

by anthropics

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Contex...

54
TECHjson
Marketplace

rule-identifier

by anthropics

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs g...

54
json
Marketplace

bloblang-authoring

by redpanda-data

This skill should be used when users need to create or debug Bloblang transformation scripts. Trigger when users ask about transforming data, mappi...

54
TECHjson
Marketplace

Agentic Skill Details

Owner
mjunaidca (GitHub)
Repository
mjs-agent-skills
Stars
1
Forks
2
Type
Technical
Meta-Domain
productivity
Primary Domain
json
Market Score
17
Agentic Skill Grades →

Agent Skill Grade

B
Score: 85/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
26/30
Ease of Use
20/25
Writing Style
8/10
Utility
18/20
Modifiers: +1

Areas to Improve

  • Navigation signals missing from large files
  • Content duplication across SKILL.md and references
  • Discoverability missing key domain terms

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I've been reading through skill implementations lately and noticed yours tackles what I think is actually one of the harder problems—guiding people from "I have an API key" to "I've built something useful" without drowning them in boilerplate. Your structure for that progression is solid, though there are a few areas where the learning curve could get smoother.

Links:

The TL;DR

You're at 85/100, B grade territory. This is solid work based on Anthropic's progressive disclosure architecture standards. Your strongest area is Utility (18/20)—the skill actually solves real problems with concrete widget patterns and debugging guidance. Weakest spot is Spec Compliance (12/15), though that's mostly metadata tuning rather than structural issues.

What's Working Well

  • Utility is chef's kiss – Two complete widget examples (Table of Contents, Chapter Reader) plus a full server template give developers 80% of what they need out of the box. The widget caching and sandboxing solutions address actual pain points.

  • Reference architecture is layered properly – Four supporting files (complete_template.md, widget_patterns.md, response_structure.md, debugging.md) create a clean progression from overview to deep dive without forcing beginners through everything at once.

  • Triggers are developer-focused – "ChatGPT Apps", "interactive widgets", "embedded widgets" nail the language people actually use when they're hunting for this stuff.

The Big One: Navigation in Large Files

Your three largest reference files (widget_patterns.md at 542 lines, complete_template.md at 340 lines, debugging.md at 447 lines) are missing tables of contents. This matters because a developer hunting for "how do ...

Browse Category

More productivity Agentic Skills

Report Security Issue

Found a security vulnerability in this agent skill?