larkcowork/lark-cowork-plugins/start
Claude Code and agent skill by larkcowork/lark-cowork-plugins
- community
Checking that the SKILL.md file is still in the repository.
Start here for any Zoom integration or app idea. Use when you need to choose the right Zoom surface, shape the architecture, or route into the correct implementation skill without reading the whole Zoom doc set first.
Install
npx vskill@latest install larkcowork/lark-cowork-plugins/startSKILL.md
Start
Use this as the default entry skill for the plugin.
What This Skill Does
- Classifies the request by job-to-be-done, not by product name alone
- Routes into the right implementation skill
- Pulls in product-specific Zoom references only after the route is clear
- Prevents common early mistakes, especially Meeting SDK vs Video SDK and REST API vs MCP confusion
Routing Table
| If the user wants to... | Route to | |
|---|---|---|
| Choose the right Zoom surface for a new project | plan-zoom-product | |
| Set up OAuth, tokens, scopes, or app credentials | setup-zoom-oauth | |
| Embed or customize a Zoom meeting flow | build-zoom-meeting-app | |
| Build a bot, recorder, or real-time meeting processor | build-zoom-bot | |
| Use Zoom-hosted MCP for AI workflows | setup-zoom-mcp | |
| Debug a broken integration | debug-zoom |
Supporting Zoom References
Use these only after selecting the workflow:
Lark-native note
Zoom stays the specialty engine (meetings, SDKs, recordings, transcripts, phone, contact center). Once you have Zoom output, the collaboration handoff lives in Lark: notify a channel/person with an interactive card or draft (lark_im_card_send / lark_mail_draft_create, resolve people via lark_contact_search), log calls/deals to a Lark Base system-of-record (lark_base_search / lark_base_record_upsert), turn meeting notes/action items into tasks (lark_minutes_search → lark_task_create), and file durable docs in Wiki (lark_wiki_node_create). See ../../connectors/LARK-PATTERNS.md, LARK-RECIPES.md, and LARK-FUSION.md for the patterns and which deep lark-* skill owns each step.
Operating Rules
- Prefer one clear recommendation over a product catalog dump.
- Ask a short clarifier only when the route is genuinely ambiguous.
- Keep the first response architectural and actionable, then go deep.
- Pull in deeper references only when they directly help the current decision or implementation.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpartner-built/zoom-plugin/skills/start/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/larkcowork/lark-cowork-plugins/start)