Build Zoom Bot — Agent Skill by Anthropic

From the author

Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.

— the description by Zoom

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The build-zoom-bot skill provides a systematic approach to developing applications that interact with Zoom meetings programmatically. It guides developers through the architectural requirements for joining meetings, capturing live media streams, handling transcripts, and orchestrating backend services. By focusing on the integration of the Meeting SDK, RTMS, and supporting APIs, it ensures that developers address critical lifecycle constraints, authentication models, and post-processing workflows effectively.

What it does

Defines the architectural requirements for meeting bot integration.
Outlines the implementation path for joining meetings and capturing media.
Integrates real-time media and transcript handling workflows.
Provides guidance on using REST APIs and Webhooks for meeting management.
Addresses post-meeting storage and event-driven processing requirements.

When to use it

When building a custom bot to join and record Zoom meetings.
When implementing real-time transcription or media analysis for live sessions.
When designing backend services that need to react to meeting events.
When planning the lifecycle and authentication strategy for meeting-based automation.

Advantages

Prevents common architectural pitfalls like confusing batch and live processing.
Ensures proper definition of join authority and authentication before development.
Promotes a robust design for post-meeting data handling and retry logic.
Standardizes the use of Zoom SDKs and APIs for consistent bot performance.

Usage examples

“How should I structure a bot that joins a Zoom meeting to transcribe it in real-time?”: The agent will guide you through the Meeting SDK and RTMS integration, defining the join strategy, media stream capture, and the pipeline for sending audio to a transcription service.
“What are the key considerations for a Zoom recording bot?”: The agent will outline the necessary auth models, the lifecycle of the bot from joining to leaving, and how to handle storage and post-processing of the captured media.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/anthropics/build-zoom-bot/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip build-zoom-bot.zip -d .agents/skills

Documentation by Zoom

/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

Clarify whether the bot needs to join, observe, transcribe, summarize, or act.
Route to Meeting SDK and RTMS as the core implementation path.
Add REST API for meeting/resource management and Webhooks for asynchronous events when needed.
Call out environment and lifecycle constraints early.

Primary References

meeting-sdk
rtms
scribe
rest-api
webhooks

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

Files

ATTRIBUTION.mdAdded by AutoGineer984 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md1.2 KiB

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Wizard
Matt Pocock· Community
Generate interactive bash wizards to guide humans through complex manual setup, migration, or configuration tasks.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository317.5k
Emails
Corey Haines· Community
Design and optimize automated email sequences for onboarding, nurturing, and lifecycle management.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository59k
Conversion Tracking
Corey Haines· Community
A systematic approach to setting up, auditing, and verifying website conversion tracking across major ad platforms and analytics tools.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository59k
Directory Submissions
Corey Haines· Community
A strategic framework for submitting software products to directories to build backlinks, improve domain rating, and drive discovery.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITMedium riskGitHub stars of the source repository59k
Sms
Corey Haines· Community
Plan, build, and optimize compliant SMS, MMS, and WhatsApp marketing programs for high-engagement customer communication.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository59k
Marketing Loops
Corey Haines· Community
Orchestrate and schedule repeatable, self-running marketing workflows that operate on a defined cadence.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository59k