Zoom Virtual Agent Web — Agent Skill by OpenAI

From the author

Zoom Virtual Agent SDK for web embeds. Use for campaign or entry ID chat launch, event-driven controls, user context updates, and CSP-safe deployment.

— the description by Zoom

AutoGineer summary

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

The Zoom Virtual Agent SDK for web provides the necessary tools to embed conversational AI agents directly into web interfaces. It supports various deployment patterns, including campaign-based and entry ID-based chat launches, while providing mechanisms for managing user context and event-driven interactions. The SDK is designed to be compatible with Content Security Policy (CSP) requirements and includes specific lifecycle management to ensure stable integration.

What it does

Embeds Zoom Virtual Agent chat interfaces into web pages.
Supports campaign-based and entry ID-based chat initiation.
Provides event-driven controls for managing agent visibility and state.
Allows for updating user context within the chat session.
Facilitates CSP-safe deployment for web applications.

When to use it

When adding a Zoom Virtual Agent to a website or web application.
When implementing specific chat launch patterns like campaigns or entry IDs.
When needing to control agent behavior programmatically based on user events.
When integrating chat functionality within a strict Content Security Policy environment.

Advantages

Centralized admin routing via campaign mode reduces application-side code changes.
Provides structured lifecycle events for reliable SDK initialization.
Supports flexible integration patterns to balance user friction and business requirements.
Includes clear guidelines for environment alignment and troubleshooting.

Usage examples

“How do I initialize the Zoom Virtual Agent SDK on my website?”: The agent provides the necessary lifecycle events, such as waiting for the zoomCampaignSdk:ready event or using waitForReady(), to ensure the SDK is initialized before calling methods like show or open.
“Should I use campaign mode or entry ID mode for my chat embed?”: The SDK documentation suggests that campaign mode is preferred for central admin routing and lower code churn, while entry ID mode is more selective and may increase user friction.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/openai/zoom-virtual-agent-web/download

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

mkdir -p .agents/skills && unzip zoom-virtual-agent-web.zip -d .agents/skills

Documentation by Zoom

Zoom Virtual Agent SDK - Web

Official docs:

Quick Links

Hard Guardrails

Gate calls behind readiness (zoomCampaignSdk:ready or waitForReady()).
Do not call show/hide/open/close before SDK initialization.
Keep CSP and script host policy validated before debugging business logic.
Prefer campaign embed over entry ID when minimizing user friction is a priority.

Chaining

Product-level architecture and drift checks: ../SKILL.md
Contact Center web context: ../../contact-center/web/SKILL.md
OAuth or REST for backend workflows: ../../oauth/SKILL.md, ../../rest-api/SKILL.md

Files

ATTRIBUTION.mdAdded by AutoGineer886 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md1.3 KiB
agents/openai.yaml275 B
concepts/lifecycle-and-events.md608 B
examples/campaign-and-entry-patterns.md944 B
references/web-reference-map.md590 B
troubleshooting/common-issues.md669 B

Requirements and compatibility

Written for: OpenAI Codex

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.

Build MCP App
AnthropicOfficial
Build interactive UI widgets for MCP servers to render forms, pickers, and dashboards directly within the chat interface.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0GitHub stars of the source repository46.3k
MCP Integration
AnthropicOfficial
Comprehensive guide for integrating Model Context Protocol (MCP) servers into Claude Code plugins.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0GitHub stars of the source repository46.3k
Social Publishing
Seth Hobson· Community
Programmatically schedule and publish content across 13 social media platforms using the SocialClaw API.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Hermes Tweet
Seth Hobson· Community
Integrates X/Twitter research and action capabilities into the Hermes Agent framework with strict approval-gated security.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Paypal Integration
Seth Hobson· Community
A guide to integrating PayPal payment processing, including checkout flows, subscriptions, and IPN webhook handling.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Social Publishing Publisher
Seth Hobson· Community
An agent-driven social media publishing specialist for multi-platform campaign management via the SocialClaw API.
Automation and integrationsClaude Code
MITGitHub stars of the source repository42.3k