Build Zoom Bot
Architect a Zoom bot that joins meetings programmatically, handles live RTMS media or transcripts, and wires webhooks plus storage for post-meeting processing.
Overview
Build-zoom-bot is an agent skill for the Build phase that guides architecture and implementation of Zoom meeting bots using Meeting SDK, RTMS, REST API, webhooks, and related backend orchestration.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill build-zoom-botWhat is this skill?
- 5-step workflow: clarify join/observe/transcribe/summarize/act → SDK/RTMS → REST/webhooks as needed
- Covers bot architecture, meeting join strategy, live media vs batch transcription separation
- Routes to meeting-sdk, rtms, scribe, rest-api, and webhooks reference skills
- Calls out environment, lifecycle, storage, retry, and post-meeting processing early
- Common mistakes section: auth model before design, don’t conflate live RTMS with batch Scribe
- 5 primary reference skills linked (meeting-sdk, rtms, scribe, rest-api, webhooks)
- 4-step numbered workflow in SKILL.md
Adoption & trust: 837 installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a program to join Zoom calls and handle live or post-meeting media but are mixing SDK join flows, RTMS streams, and batch transcription into one unclear design.
Who is it for?
Indie developers building meeting bots, live transcription agents, or workflow automation that must join Zoom with correct auth and media handling.
Skip if: Users who only need a one-off Zoom REST call without bots, live media, or meeting join—or who want marketing copy instead of integration architecture.
When should I use this skill?
Build a Zoom meeting bot, recorder, or real-time media workflow; join meetings programmatically; combine Meeting SDK, RTMS, and backend services.
What do I get? / Deliverables
You get a clarified bot role, join/auth model, and a reference-driven path through Meeting SDK and RTMS with REST/webhooks for lifecycle events and durable storage with retries.
- Bot architecture and join strategy
- Live vs batch media pipeline separation
- Event, storage, and retry design outline
Recommended Skills
Journey fit
Build is the primary phase because the skill is an implementation routing guide for Meeting SDK, RTMS, REST, and webhooks—not launch SEO or production incident response. Integrations subphase matches third-party Zoom APIs, auth/join authority, and backend orchestration for meeting automation.
How it compares
Zoom integration workflow skill that chains plugin references; not a hosted bot SaaS or generic video editor.
Common Questions / FAQ
Who is build-zoom-bot for?
Solo builders and small teams implementing Zoom bots or real-time meeting pipelines with Meeting SDK, RTMS, and supporting backend services.
When should I use build-zoom-bot?
Use it in Build → integrations when joining meetings programmatically, processing live transcripts or media, or designing recorder/bot orchestration with webhooks and storage.
Is build-zoom-bot safe to install?
Check this page’s Security Audits panel for the ingested skill package; implementing bots requires Zoom credentials and network access you should scope and rotate yourself.
Workflow Chain
Then invoke: meeting sdk, rtms
SKILL.md
READMESKILL.md - Build Zoom Bot
# /build-zoom-bot Use this skill for automation that joins meetings, captures media, or reacts to live session data. ## Covers - Bot architecture - Meeting join strategy - Real-time media and transcript handling - Backend orchestration - Storage, post-processing, and event flow design ## Workflow 1. Clarify whether the bot needs to join, observe, transcribe, summarize, or act. 2. Route to Meeting SDK and RTMS as the core implementation path. 3. Add REST API for meeting/resource management and Webhooks for asynchronous events when needed. 4. Call out environment and lifecycle constraints early. ## Primary References - [meeting-sdk](../meeting-sdk/SKILL.md) - [rtms](../rtms/SKILL.md) - [scribe](../scribe/SKILL.md) - [rest-api](../rest-api/SKILL.md) - [webhooks](../webhooks/SKILL.md) ## Common Mistakes - Treating batch transcription and live media as the same workflow - Designing the bot before defining join authority and auth model - Forgetting post-meeting storage and retry behavior