Knowledge-work-plugins build-zoom-virtual-agent

Reference skill for Zoom Virtual Agent. Use after routing to a virtual-agent workflow when implementing web embeds, Android or iOS wrapper integrations, knowledge-base sync, lifecycle handling, or troubleshooting.

install
source · Clone the upstream repo
git clone https://github.com/anthropics/knowledge-work-plugins
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/anthropics/knowledge-work-plugins "$T" && mkdir -p ~/.claude/skills && cp -r "$T/partner-built/zoom-plugin/skills/virtual-agent" ~/.claude/skills/anthropics-knowledge-work-plugins-build-zoom-virtual-agent && rm -rf "$T"
manifest: partner-built/zoom-plugin/skills/virtual-agent/SKILL.md
source content

/build-zoom-virtual-agent

Background reference for Zoom Virtual Agent across:

  • Web campaign/chat embeds.
  • Android WebView wrappers.
  • iOS WKWebView wrappers.
  • Knowledge-base sync and custom API ingestion.

Official docs:

Routing Guardrail

Quick Links

  1. concepts/architecture-and-lifecycle.md
  2. scenarios/high-level-scenarios.md
  3. references/versioning-and-drift.md
  4. references/samples-validation.md
  5. references/environment-variables.md
  6. troubleshooting/common-drift-and-breaks.md
  7. RUNBOOK.md

Platform skills:

Common Lifecycle Pattern

  1. Configure campaign or entry ID in Virtual Agent admin.
  2. Initialize SDK in web or WebView container.
  3. Wait for readiness (
    zoomCampaignSdk:ready
    or
    waitForReady()
    ) before calling APIs.
  4. Register bridge handlers (
    exitHandler
    ,
    commonHandler
    ,
    support_handoff
    ) when native orchestration is needed.
  5. Handle conversation lifecycle (
    engagement_started
    ,
    engagement_ended
    ) and UI state.
  6. End chat (
    endChat
    ) and clean up listeners.

High-Level Scenarios

  • Website campaign launcher with contextual customer attributes.
  • Mobile app WebView chat with native close/handoff bridge.
  • External URL handling via system browser vs in-app browser policy.
  • Knowledge-base sync from external systems using custom API connector.
  • Cross-team support flow that escalates from bot to live support with handoff payload.

Chaining

Operations

  • RUNBOOK.md - 5-minute preflight and debugging checklist.