mcpField
C
choose-zoom-approach

choose-zoom-approach

github.com/anthropicsDevelopment33.6k2.1k installsUpdated 1d ago
Repository

About choose-zoom-approach

choose-zoom-approach is a decision skill for selecting the smallest suitable Zoom product surface for a task. It maps problem types to Zoom options and identifies supporting components, constraints, and the next implementation step.

Key features

  1. 01Maps tasks to Zoom surfaces
  2. 02Identifies supporting components
  3. 03Highlights constraints and tradeoffs
  4. 04Suggests an implementation step

Use cases

  1. 01Selecting an API for backend automation
  2. 02Choosing a meeting or video SDK
  3. 03Planning AI workflows over Zoom data
  4. 04Combining deterministic and AI-driven operations

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/anthropics/knowledge-work-plugins --skill choose-zoom-approach

After installing, type/choose-zoom-approachin Claude Code to confirm it loaded.

Details

From the project README

Choose Zoom Approach

Pick the smallest correct Zoom surface for the job, then layer in only the supporting pieces that are actually required.

Decision Framework

Problem TypePrimary Zoom Surface
Deterministic backend automation, account management, reporting, scheduled jobsrest-api
Event delivery to your backendwebhooks or websockets
Embed Zoom meetings into your appmeeting-sdk
Build a fully custom video experiencevideo-sdk
Build inside the Zoom clientzoom-apps-sdk
AI-agent tool workflows over Zoom datazoom-mcp
Real-time media extraction or meeting botsrtms plus meeting-sdk when needed
Phone workflowsphone
Contact Center or Virtual Agent flowscontact-center or virtual-agent

Guardrails

  • Do not recommend Video SDK when the user actually needs Zoom meeting semantics.
  • Do not recommend Meeting SDK when the user needs a fully custom session product.
  • Do not replace deterministic backend automation with MCP-only guidance.
  • Prefer hybrid rest-api + zoom-mcp when the user needs both stable system actions and AI-driven discovery.

What To Produce

  • One recommended path
  • Minimum supporting components
  • Hard constraints and tradeoffs
  • Immediate next implementation step

Comments

Markdown supported