
build-zoom-virtual-agent
✓ Official★ 4,081by openai · part of openai/plugins
Use when using Virtual Agent.
🧩 One of 7 skills in the openai/plugins package — works on its own, and pairs well with its siblings.
This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.
Build Zoom Virtual Agent
Use this skill when the workflow embeds or wraps Zoom Virtual Agent, including web campaigns and mobile WebView integrations.
Workflow
- Identify the client: web, Android WebView, iOS WKWebView, campaign entry, support handoff, or knowledge-base sync pipeline.
- Route to the platform skill before coding because event handling and native bridge behavior differ by client.
- Confirm campaign, entry ID, allowed origins, lifecycle events, and support handoff behavior.
- Keep user context updates, native URL handling, and handoff payloads explicit.
- Debug by checking SDK readiness, campaign configuration, bridge injection, CSP, WebView lifecycle, and version drift.
References
- Full preserved guide: references/full-guide.md
- Web: web/SKILL.md
- Android: android/SKILL.md
- iOS: ios/SKILL.md
- Architecture and lifecycle: concepts/architecture-and-lifecycle.md
- Common drift and breaks: troubleshooting/common-drift-and-breaks.md
Copy & paste — that's it
npx skills add https://github.com/openai/plugins --skill build-zoom-virtual-agentRun this in your project — your agent picks the skill up automatically.
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.