skills.rest
trungpr1990-coder
trungpr1990-coderCOMMUNITY
Explore all skills by this author →
GitHub

lark-minutes

Search, download, upload, and edit Feishu Minutes recordings and AI artifacts via lark-cli.

Updated Jun 29, 2026
Search Tags:#feishu#lark#minutes#audio upload#lark-cli#meeting transcript#speaker replace
One-click install
npx skills add https://github.com/trungpr1990-coder/AMI-MAKEUP --skill lark-minutes-trungpr1990-coder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lark-minutes
Source: https://github.com/trungpr1990-coder/AMI-MAKEUP/tree/main/.agents/skills/lark-minutes
Command: npx skills add https://github.com/trungpr1990-coder/AMI-MAKEUP --skill lark-minutes-trungpr1990-coder

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, converting local audio/video into transcripts, and fixing AI-generated summaries, todos, or speaker attributions all require many steps. This Skill wraps the lark-cli minutes commands into a guided workflow so an AI agent can perform all of these operations directly. ## Core Features & Use Cases - Search and inspect Minutes: Find minutes by keyword, owner, participant, or time range, and retrieve titles, durations, and linked meeting notes. - Media and artifact handling: Download recording media files, upload local audio/video via Drive file_token to generate new Minutes, and fetch AI artifacts (summary, todos, chapters, keywords, transcript). - Editing workflows: Rename minutes, replace the AI summary, add/update/delete AI todos, and reassign transcript speakers to the correct Feishu users. - Use Case: A user says "turn this mp3 into a meeting transcript with a summary" — the agent uploads the file to Drive, creates a Minute, then pulls the transcript and summary via minutes +detail. ## Quick Start Ask the agent to search your recent Feishu minutes by keyword and show the summary and todos of the matching one.

Frequently Asked Questions about lark-minutes

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

FAQPage Schema
How do I search Feishu minutes by keyword or date?▼

Use lark-cli minutes +search with --query for keywords, --start/--end for time ranges, and --owner-ids or --participant-ids for people filters. At least one filter condition is required, and 'me' can represent the current user.

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 --file-token to generate the minute, and finally call minutes +detail --transcript to fetch the transcript. Do not use local tools like ffmpeg or whisper.

What audio and video formats does Feishu 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.

How do I fix a wrongly identified speaker in a Feishu minute transcript?▼

First call the speakerlist API via lark-cli api GET to retrieve speaker_id values, resolve the new speaker's open_id via lark-contact, then run minutes +speaker-replace with --from-speaker-id and --to-user-id. Never pass display names as the speaker id.

Why does minutes download fail with error 2091003?▼

Error 2091003 means the minute's transcription has not finished yet, so the media file is not ready for download. Wait until transcription completes and retry the minutes +download command.

Can I edit minute todos through the Feishu task list?▼

No. AI todos inside a minute must be managed with minutes +todo, not lark-task commands. Use --operation add/update/delete for single items or --todos with a JSON array for batch changes.

Related Skills

Explore More Product & Management Skills→
U1traVenoU1traVeno

lark-minutes

Search, download, upload, and edit Lark Minutes recordings and AI artifacts via lark-cli.

Community
Advanced
adiytharpansaadiytharpansa

meeting-assistant

Document meetings by capturing conversations, decisions, and follow-up actions.

Community
Intermediate
liangdabiaoliangdabiao
60

lark-vc

Search Feishu video conference records by date, participants, and keywords.

Community
Intermediate
erguotou520erguotou520

use-local-whisper

Replace cloud WhatsApp voice transcription with local whisper.cpp processing.

Community
Advanced