lark-minutes

Search, download, and edit Feishu Minutes recordings and AI-generated meeting artifacts.

2|Updated Aug 9, 2026
One-click install
npx skills add https://github.com/DeepJH/doubao-skill-and-info --skill lark-minutes-deepjh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-minutes
Source: https://github.com/DeepJH/doubao-skill-and-info/tree/main/skills/lark-minutes
Command: npx skills add https://github.com/DeepJH/doubao-skill-and-info --skill lark-minutes-deepjh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Managing Feishu (Lark) Minutes recordings manually is tedious: finding the right minute, downloading its media, reading transcripts, and editing AI-generated summaries or todos all require navigating multiple APIs. This Skill provides a unified command workflow via lark-cli to search, inspect, download, upload, and edit Minutes content programmatically. ## Core Features & Use Cases - Search and inspect Minutes: Find minutes by keyword, owner, participant, or time range, and retrieve details like title, duration, and linked meeting notes. - Media and artifact handling: Download audio/video recordings, upload local media files to generate new Minutes, and fetch AI artifacts such as summaries, todos, chapters, keywords, and transcripts. - Edit Minutes content: Rename titles, replace AI summaries, manage AI todos, replace transcript speakers, and batch-replace keywords in transcripts. - Use Case: A user says "turn this mp3 recording into meeting notes" — the Skill uploads the file to Feishu Drive, converts it into a Minute, waits for transcription, and returns the summary, todos, and full transcript. ## Quick Start Ask the assistant to search your recent Feishu Minutes from last week and show the summary and transcript of the one about the budget review.

Frequently Asked Questions about lark-minutes

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

FAQPage Schema
How do I search my Feishu Minutes by keyword or date?

Use lark-cli minutes +search with --query for keywords, --start/--end for date ranges, and --owner-ids or --participant-ids with 'me' for your own minutes. At least one filter condition is required, and date-only --end values include the entire day.

How to convert a local audio or video file into a Feishu Minute transcript?

First upload the file with lark-cli drive +upload to get a file_token, then run minutes +upload with that token to generate the Minute. Finally call minutes +detail with --wait-ready and --transcript to retrieve the transcript once processing finishes.

What audio and video formats does Minutes upload support?

Supported audio formats include wav, mp3, m4a, aac, ogg, wma, and amr; video formats include avi, wmv, mov, mp4, m4v, mpeg, ogg, and flv. Files must be under 6 hours long and 6 GB in size.

Why does Minutes download fail with error 2091003?

Error 2091003 means the Minute has not finished transcription yet, so its media file is not available for download. Wait for transcription to complete and retry the minutes +download command.

Can I edit AI todos inside a Feishu Minute instead of Feishu Tasks?

Yes, use minutes +todo with --operation add, update, or delete, or pass a --todos JSON array for batch changes. This edits the Minute's own AI todos and must not be confused with the separate Feishu Task list managed by lark-task.

How do I fix a wrongly identified speaker in a Minutes transcript?

First call the speakerlist API via lark-cli api GET to retrieve speaker_id values, then run minutes +speaker-replace with --from-speaker-id set to that id and --to-user-id set to the new speaker's ou_ open_id. Display names cannot be passed directly.