design-mcp-workflow
Design a Zoom connector workflow for Muse AI. Use when deciding whether Zoom connector fits a task, when planning tool-based AI workflows, or when separating connector responsibilities from REST API responsibilities.
- License 许可
- MIT
- 最近更新
- 2026-11-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- design-mcp-workflow
- description
- Design a Zoom connector workflow for Muse AI. Use when deciding whether Zoom connector fits a task, when planning tool-based AI workflows, or when separating connector responsibilities from REST API responsibilities.
- user-invocable
- false
02 资源文件 1
- 参考文档CONNECTORS.md2.4 KB
03 SKILL.md 正文
<!-- Provenance: adapted from anthropics/knowledge-work-plugins (Apache-2.0, (c) Anthropic). Original skill: https://github.com/anthropics/knowledge-work-plugins/tree/main/partner-built/zoom-plugin/skills/design-mcp-workflow. Changes for Muse AI: Claude/Cowork product refs -> Muse AI; MCP -> connector; CLAUDE.md -> MUSE.md; ${CLAUDE_PLUGIN_ROOT} -> this skill's directory; /plugin:command refs -> skill refs. -->
Design connector Workflow
Use this skill when the user wants Muse AI or another connector-capable client to interact with Zoom via tool calls instead of only deterministic API code.
Covers
- connector fit assessment
- REST API vs connector boundaries
- Hybrid architectures
- Connector expectations
- Whiteboard-specific connector routing
Workflow
- Decide whether the problem is agentic tooling, deterministic automation, or both.
- Route connector-only tasks to zoom-mcp.
- Route hybrid tasks to both zoom-mcp and rest-api.
- If Whiteboard is central, route to zoom-mcp/whiteboard.
- Call out transport, auth, and client capability assumptions explicitly.
Common Mistakes
- Using connector for deterministic backend jobs that should stay in REST
- Treating connector as a replacement for all API design
- Ignoring client transport support and auth requirements
04 同仓库更多 Skills
web-scrape
Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.
design-taste-frontend
tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).