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.

インストールへ移動ファイルを確認

リポジトリ: anthropics/knowledge-work-plugins
ソースの最終更新活動: 2026年4月9日 23:28
検出された SKILL.md の言語: 英語
スター: 29,826
フォーク: 3,372

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

AI アシスタントでインストール

このプロンプトをコピーして、使用中の AI アシスタントに送ってください。

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/anthropics/knowledge-work-plugins/tree/main/partner-built/zoom-plugin/skills/virtual-agent.

直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill build-zoom-virtual-agent

コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。

ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

ファイルエクスプローラー

23 ファイル

SKILL.md

ソースの指示 · 読み取り専用プレビュー

name: build-zoom-virtual-agent
description: 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.
triggers: ["virtual agent","zva","virtual assistant sdk","knowledge base sync"]

# /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: - https://developers.zoom.us/docs/virtual-agent/ - https://developers.zoom.us/docs/virtual-agent/web/ - https://developers.zoom.us/docs/virtual-agent/android/ - https://developers.zoom.us/docs/virtual-agent/ios/ ## Routing Guardrail - If the user is implementing Contact Center app surfaces inside Zoom client, chain with [../contact-center/SKILL.md](../contact-center/SKILL.md). - If the user needs backend knowledge-base CRUD or automation scripts, chain with [../rest-api/SKILL.md](../rest-api/SKILL.md) and [../oauth/SKILL.md](../oauth/SKILL.md). - If the user asks only for website bot embed and campaign controls, stay on [web/SKILL.md](web/SKILL.md). - If the user asks for mobile native wrappers around web chat, route to [android/SKILL.md](android/SKILL.md) or [ios/SKILL.md](ios/SKILL.md). ## Quick Links 1. [concepts/architecture-and-lifecycle.md](concepts/architecture-and-lifecycle.md) 2. [scenarios/high-level-scenarios.md](scenarios/high-level-scenarios.md) 3. [references/versioning-and-drift.md](references/versioning-and-drift.md) 4. [references/samples-validation.md](references/samples-validation.md) 5. [references/environment-variables.md](references/environment-variables.md) 6. [troubleshooting/common-drift-and-breaks.md](troubleshooting/common-drift-and-breaks.md) 7. [RUNBOOK.md](RUNBOOK.md) Platform skills: - [web/SKILL.md](web/SKILL.md) - [android/SKILL.md](android/SKILL.md) - [ios/SKILL.md](ios/SKILL.md) ## 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 - Contact Center app/web/mobile patterns: [../contact-center/SKILL.md](../contact-center/SKILL.md) - OAuth app setup and tokens: [../oauth/SKILL.md](../oauth/SKILL.md) - API workflows for KB automation: [../rest-api/SKILL.md](../rest-api/SKILL.md) - Event-driven backend follow-up: [../webhooks/SKILL.md](../webhooks/SKILL.md) ## Operations - [RUNBOOK.md](RUNBOOK.md) - 5-minute preflight and debugging checklist.

GitHubで見る

検索に戻るインストールに戻る

ad-manager

The ads consultant that becomes an ads agent. Reads paid-ad performance natively through the TikTok Ads connector, or via a build-connector Zapier connection for other ad platforms, explains in plain English what is working and what is burning money, recommends budget, targeting, and creative changes with the dollar impact of each, drafts new ad copy in the owner's voice plus Canva creative briefs, and — only after an explicit yes — executes the approved changes in the ad account. Works from exported CSV reports when nothing is connected, the normal starting point. Use this whenever the owner talks about ads or ad spend at all, including "are my ads working," "what's my ROI on ads," "I'm spending money on Facebook and I don't know what I'm getting," "should I turn this campaign off," "my cost per lead is going up," "write me a new ad," "who should I be targeting," or "the ad guy quit."

2026-09-15

ap-processor

Works the bill pile end to end: reads bills and vendor statements out of the AP inbox or from uploaded PDFs and phone photos, pulls out vendor, amount, due date, and line detail, codes each one to the right account and job, matches it against the purchase order and the receiving ticket, then stages the entries and a proposed payment run in QuickBooks, Xero, or NetSuite for the owner to approve in one pass. Nothing is entered and nothing is paid without an explicit yes. Reach for this whenever bills, vendor invoices, or paying people comes up — including "what do I owe," "the bills are piling up," "pull the invoices out of my email and into QuickBooks," "code these for me," "who needs to get paid this week," "did we get billed twice," or when the owner forwards a supplier invoice with no message at all. Use it before cash-flow-snapshot or month-end-prep so those run on real payables instead of a guess.

2026-09-15

brand-style

Sets and updates the owner's brand look and output preferences, which every page and document the plugin produces then follows automatically. Captures the brand from a pasted website link or a plain-words description — never a hex code, color picker, or upload — previews it on a sample page, asks how they want their outputs delivered (visual artifacts, Word docs, markdown, Notion pages, Canva Docs, or best-for-the-skill), and saves both to the business profile. Runs inside smb-onboard on first setup and stands alone forever after. Use when the owner says "update my brand," "we rebranded," "change my colors," "make the reports match our new look," "change how you give me reports," "I want Word docs instead," or anything about the look or format of what the plugin hands them.

2026-09-15

このリポジトリのすべてを見る

build-zoom-virtual-agent

ソース情報

インストール方法

AI アシスタントでインストール

ソースファイルを確認

このリポジトリの他の Skills

AI アシスタントでインストール

このリポジトリの他の Skills