All skills
alpic-ai avatar

/chatgpt-app-builder

@3340b34
by Alpicalpic-ai/skybridge2.1k stars
140

Guide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app / MCP server for ChatGPT, or use the Skybridge framework.

Use this Skill: https://skilld.dev/gh/alpic-ai/skybridge/chatgpt-app-builder

This session only. Nothing lands on disk.

referencescopy-template.md

≈310 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Start From Template

Scaffold a project by setting up the Skybridge template starter. Skybridge is a TypeScript framework for building MCP servers with type-safe APIs and React views.

Workflow

  1. Ask: "Which package manager?" (npm / pnpm / yarn / bun / deno)

  2. Run (do not rm beforehand—create handles conflicts):

{pm} create skybridge@latest {target-dir}

# deno
deno init --npm skybridge {target-dir}

Template flags: --blank (minimal, no tools), --ecom (ecommerce starter) or --example <name> (a copy of examples/<name> from the Skybridge repo, downloaded from GitHub). With npm, separate flags: npm create skybridge@latest {target-dir} -- --ecom. Scaffolding with --ecom? → follow ecommerce.md to fill it.

  1. Start the dev server. Read logs to assess readiness/health; fix any errors (TypeScript, etc.) before proceeding.

  2. Start implementing your app using these core concepts:

  1. Delete unused views files and leftover code.

Source: SKILL.md on GitHub

1 alert6d5 checks · Risk SAFE
  • Gen Agent Trust Hub6d

    The skill is a comprehensive development guide for the Skybridge framework, which helps build ChatGPT applications. It is generally safe and follows security best practices, such as documenting CSP and OAuth configurations. It identifies a minor risk of indirect prompt injection as it processes user-provided specification files to guide the development process.

  • Socket6d

    No alerts

  • Snyk6d

    Risk: LOW · No issues

  • Runlayer7mo

    8/23 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 3340b34. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last week

README badge

README badge for alpic-ai/skybridge

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.

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.