Search, download, upload, and edit Lark Minutes recordings and AI artifacts via lark-cli.
npx skills add https://github.com/U1traVeno/skills --skill lark-minutes-u1traveno
Please help me install this Agent Skill. Skill: lark-minutes Source: https://github.com/U1traVeno/skills/tree/main/profiles/lark/lark-minutes Command: npx skills add https://github.com/U1traVeno/skills --skill lark-minutes-u1traveno
minute_token. - Media and content workflows: Download minute audio/video files, or upload local media through Drive to generate a new minute with transcript and summary. - Edit minute content: Rename titles, replace the AI summary, add/update/delete AI todos, batch-replace transcript keywords, and reassign speakers to the correct Feishu users. - Use Case: You have a local MP3 of a client interview. Upload it to Drive, convert it into a minute, then retrieve the transcript and summary, and fix a misidentified speaker so the right colleague is credited. ## Quick Start Ask the AI to search your recent Feishu minutes for a keyword and pull the transcript and AI summary of the matching minute.High-intent search queries and answers about installing and using this skill.
Use lark-cli minutes +search with --query for keywords, --start and --end for time ranges, or --owner-ids and --participant-ids with open_ids or 'me'. At least one filter condition is required, and results paginate via page_token.
First upload the file with lark-cli drive +upload to get a file_token, then run minutes +upload to generate the minute, and finally call minutes +detail --wait-ready --transcript to fetch the transcript. Do not use local tools like ffmpeg or whisper.
Yes. First query the speaker list via lark-cli api GET on the transcript speakerlist endpoint to get the speaker_id, resolve the new speaker to an ou_ open_id via contacts, then run minutes +speaker-replace with --from-speaker-id and --to-user-id.
Supported audio formats include wav, mp3, m4a, aac, ogg, wma, and amr; video formats include avi, wmv, mov, mp4, m4v, mpeg, and flv. Files must be under 6 hours long and 6 GB in size.
Error 2091003 means the minute has not finished transcription yet, so its media file is not ready for download. Wait for transcription to complete and retry; other codes like 2091005 indicate missing read permission from the minute owner.
Use minutes +todo only for AI todos inside a specific minute, such as adding or marking items done within that minute. Personal or shared Feishu task lists belong to the separate lark-task skill and must not be mixed.
larksuiteQuery Lark video meetings, minutes, transcripts, and control in-meeting bot interactions.
ZJU-REALOrganize meeting records and minutes into structured summaries for a specified time period.
zephyrwang6Query Feishu corporate directory for contacts and organization details.
tedtv1007-ctrlTranscribes audio files into text using the local Whisper CLI engine.