ChatGPT app builder with Skybridge (MCP servers for ChatGPT)
End-to-end guide for building ChatGPT apps as MCP servers — spec-first workflow, UI guidelines, OAuth, deploy and publish
- What
- End-to-end guide for building ChatGPT apps as MCP servers — spec-first workflow, UI guidelines, OAuth, deploy and publish
- Cost
- Free
- Needs
- familiarity with ChatGPT Apps / MCP servers helps; deployment and directory publishing run through Alpic's hosted platform (check their pricing) — otherwise nothing to install for the guide itself
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @alpic-ai's full-lifecycle playbook for turning an idea into a ChatGPT app: conversational experiences built as MCP servers that both a human and the ChatGPT model consume through a shared view. It enforces a SPEC.md-driven workflow — brainstorm against UX guidelines, bootstrap from a template, implement tools and views through about fifteen focused reference docs (architecture, state and context, prompt-LLM, UI guidelines, OAuth, CSP, assets, deploy, publish), then ship and submit to the ChatGPT directory — including a dedicated ecommerce track and migration guides between Skybridge versions. MIT-licensed. Honest notes: the deploy/publish path runs through Alpic's own hosted platform (the framework is open, the hosting is theirs — check their pricing); the ChatGPT Apps SDK moves fast so some references may lag; and the SKILL.md points at external doc URLs that live outside the repo. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: familiarity with ChatGPT Apps / MCP servers helps; deployment and directory publishing run through Alpic's hosted platform (check their pricing) — otherwise nothing to install for the guide itself Install "ChatGPT app builder with Skybridge (MCP servers for ChatGPT)" for me. It gives my agent @alpic-ai's full-lifecycle playbook: build conversational ChatGPT apps as MCP servers through a SPEC.md-driven workflow — brainstorm against UX guidelines, bootstrap from the template, implement tools and views with ~15 focused reference docs (architecture, state and context, prompt-LLM, UI guidelines, OAuth, CSP, assets), then deploy via Alpic and publish to the ChatGPT directory — including an ecommerce track and Skybridge migration guides. MIT-licensed. Repository: https://github.com/alpic-ai/skybridge/blob/main/skills/chatgpt-app-builder/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "chatgpt-app-builder". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. create the SPEC.md for my app idea, sign up for Alpic's platform for deployment). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.