AI assistants do not understand our API and web components out of the box. With curated context material they become useful co-developers for your museum IT. We build that material and help with the integration.
Claude Skill for web components
Available: a Git repository with our skill for the go~mus web components. It teaches AI assistants how to embed the <go-*> custom elements, from tags, attributes and events through the ticket-selection filters to complete integration flows. A compiled bundle is included so the assistant can look up real behaviour.
Repository: github.com/giantmonkey/agent-skills
Install for any agent (Claude Code, Cursor and many more):
npx skills add github.com/giantmonkey/agent-skills --skill go-webcomponentsInstall as a plugin in Claude Code:
/plugin marketplace add giantmonkey/agent-skills
/plugin install go-webcomponents@giantmonkeyYou get updates by running the install again. To pin a version that matches your release of the library, use the release tags in the format go-webcomponents-v<version>.
Right now the repository covers the web components. Skills for the REST API and common integration patterns will follow. If you would like a specific integration prioritised, drop us a note at support@giantmonkey.de.
Other AI tools
The material is not tied to Claude. Markdown context is read by ChatGPT, Cursor, Aider, Continue and other coding assistants just as well. The repository works in any tool that takes a documentation path into its prompt context. The npx skills add command works with Claude Code, Cursor and many more agents.
We help with the integration
An AI toolchain does not replace an architecture conversation. For the actual connection to your museum IT, from ticket sales through POS integration to backoffice connections, we support you, with or without AI tooling. Reach us at support@giantmonkey.de or book a slot via contact.
WebMCP
We are running WebMCP in production on the booking page for our webinars. WebMCP is an experimental browser API that lets a page expose its functions directly to AI agents instead of having them infer behaviour from the DOM. A page registers a tool with name, description and input schema via navigator.modelContext.registerTool(). Browser-internal agents and external agents that drive Chrome over the DevTools protocol then call the tool.
Status May 2026: behind chrome://flags/#enable-webmcp-testing in Chrome 146 Canary. No origin trial so far. The registration call is feature-detected and stays silent elsewhere.
On /en/webinars/ the page registers a book_webinar tool. The input is a termin ID an agent can read from the ?webinar=ID deep-links on the termin cards. The execute opens the booking overlay for the selected termin and returns a status message. The tool deliberately does not prefill the form or submit the booking: submit stays a human action, which matches the fee for third parties.
Lighthouse 13.3.0 picks up the tool, validates the input schema and shows the source location in the bundled JS. The code lives in WebinarePage.svelte, around 50 lines including schema and execute handler.