lark-meeting

Query Lark video meetings, minutes, transcripts, and control in-meeting bot interactions.

16.9k|1.4k|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/larksuite/cli --skill lark-meeting
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-meeting
Source: https://github.com/larksuite/cli/tree/main/skills/lark-meeting
Command: npx skills add https://github.com/larksuite/cli --skill lark-meeting

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Finding and working with Lark/Feishu video meeting data is fragmented across meetings, AI notes, and Minutes recordings, each with different identifiers and APIs. This Skill unifies the entire meeting domain so an AI agent can locate past meetings, read their artifacts, and interact with live meetings without confusing meeting IDs, note IDs, or minute tokens.

Core Features & Use Cases

  • Meeting & Artifact Query: Search historical meetings by topic, time, organizer, or participant; retrieve linked AI notes (note_id), Minutes recordings (minute_token), transcripts, summaries, todos, and shared documents.
  • Minutes Management: Search, upload local audio/video to generate Minutes, download original media, edit titles, replace AI summaries, manage todos, replace transcript speakers or keywords, and handle permission requests or grants.
  • Live Meeting Interaction: Discover ongoing meetings, read real-time events (speech, chat, shared docs), send in-meeting messages or reactions, manage countdowns, take screenshots, and orchestrate bot join/invite/end/leave flows.
  • Use Case: Ask the agent to summarize what was discussed in yesterday's product review meeting; it locates the meeting via vc +search, resolves the linked Minutes or smart note, reads the transcript, and produces a recap.

Quick Start

Ask the agent to list the meetings you attended today and summarize the key discussion points from the meeting transcript.

Frequently Asked Questions about lark-meeting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search past Lark meeting records with lark-cli?

Use `lark-cli vc +search` with at least one filter such as --query, --start/--end date range, --organizer-ids, or --participant-ids. It only searches ended meetings with user identity; for future schedules use the calendar skill instead.

How to get a meeting transcript or summary from Feishu Minutes?

Run `lark-cli minutes +detail --minute-tokens <token>` with flags like --transcript, --summary, --todo, --chapter, or --keyword. Obtain the minute_token from a Minutes URL, `minutes +search`, or `vc +recording` for a given meeting.

Can a bot join a Lark meeting and read live meeting content?

Yes. Use `lark-cli vc +meeting-join --as bot --meeting-number <9-digit>` to join, then `vc +meeting-events --as bot --meeting-id <id> --page-all` to stream events. The bot is visible to participants, and event access ends about 5 minutes after the meeting ends.

What is the difference between meeting_id, meeting_no, note_id, and minute_token?

meeting_id is the long numeric meeting identifier, meeting_no is the 9-digit meeting number, note_id identifies the AI smart note, and minute_token identifies a Minutes recording. They are distinct objects and cannot be substituted for one another in commands.

Why does minutes upload or summary update fail with quota_exceeded?

The error means the ASR/AI quota is exhausted, so transcription or AI artifacts cannot be generated or saved. Check quota details on the Minutes detail page; retrying the same command will not succeed and it is not a permission issue.

How do I convert a local audio or video file into Feishu Minutes?

First upload the file with `drive +upload` to get a file_token, then run `lark-cli minutes +upload --file-token <token>`. Files must be under 6 hours and 6 GB in supported audio/video formats, and creation is asynchronous so poll with `minutes +detail --wait-ready`.