choose-zoom-approach

Anthropic ｜ 架構與重構 ｜ 原文 ｜ Apache-2.0

依使用情境挑選最小而正確的 Zoom API 或 SDK 架構

---
name: choose-zoom-approach
description: 為某個使用情境選擇對的 Zoom 架構。當要在 REST API、Webhooks、WebSockets、Meeting SDK、Video SDK、Zoom Apps SDK、Zoom MCP、Phone、Contact Center 或混合方案之間做決定時使用。
user-invocable: false
---

# Choose Zoom Approach

替這份工作挑最小而正確的 Zoom 介面，再只疊上真正需要的輔助元件。

## 決策框架

| 問題類型 | 主要的 Zoom 介面 |
|---|---|
| 確定性的後端自動化、帳號管理、報表、排程工作 | [rest-api](../rest-api/SKILL.md) |
| 把事件送到你的後端 | [webhooks](../webhooks/SKILL.md) 或 [websockets](../websockets/SKILL.md) |
| 把 Zoom 會議嵌進你的 app | [meeting-sdk](../meeting-sdk/SKILL.md) |
| 建立完全客製的視訊體驗 | [video-sdk](../video-sdk/SKILL.md) |
| 在 Zoom 用戶端裡面開發 | [zoom-apps-sdk](../zoom-apps-sdk/SKILL.md) |
| 針對 Zoom 資料的 AI agent 工具工作流程 | [zoom-mcp](../zoom-mcp/SKILL.md) |
| 即時媒體擷取或會議機器人 | [rtms](../rtms/SKILL.md)，需要時加上 [meeting-sdk](../meeting-sdk/SKILL.md) |
| 電話工作流程 | [phone](../phone/SKILL.md) |
| Contact Center 或 Virtual Agent 流程 | [contact-center](../contact-center/SKILL.md) 或 [virtual-agent](../virtual-agent/SKILL.md) |

## 護欄

- 當使用者實際上需要的是 Zoom 會議的語意時，不要推薦 Video SDK。
- 當使用者需要的是完全客製的 session 產品時，不要推薦 Meeting SDK。
- 不要用只靠 MCP 的做法，取代確定性的後端自動化。
- 當使用者同時需要穩定的系統動作和 AI 驅動的探索時，優先採用 `rest-api + zoom-mcp` 的混合方案。

## 要產出什麼

- 一條推薦的路徑
- 最少的輔助元件
- 硬性限制與取捨
- 立即的下一個實作步驟

---
name: choose-zoom-approach
description: Choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP, Phone, Contact Center, or a hybrid approach.
user-invocable: false
---

# 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 Type | Primary Zoom Surface |
|---|---|
| Deterministic backend automation, account management, reporting, scheduled jobs | [rest-api](../rest-api/SKILL.md) |
| Event delivery to your backend | [webhooks](../webhooks/SKILL.md) or [websockets](../websockets/SKILL.md) |
| Embed Zoom meetings into your app | [meeting-sdk](../meeting-sdk/SKILL.md) |
| Build a fully custom video experience | [video-sdk](../video-sdk/SKILL.md) |
| Build inside the Zoom client | [zoom-apps-sdk](../zoom-apps-sdk/SKILL.md) |
| AI-agent tool workflows over Zoom data | [zoom-mcp](../zoom-mcp/SKILL.md) |
| Real-time media extraction or meeting bots | [rtms](../rtms/SKILL.md) plus [meeting-sdk](../meeting-sdk/SKILL.md) when needed |
| Phone workflows | [phone](../phone/SKILL.md) |
| Contact Center or Virtual Agent flows | [contact-center](../contact-center/SKILL.md) or [virtual-agent](../virtual-agent/SKILL.md) |

## 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