Search, download, upload, and edit Feishu Minutes recordings via lark-cli commands.
npx skills add https://github.com/CalWade/aigc-creator --skill lark-minutes-calwade
Please help me install this Agent Skill. Skill: lark-minutes Source: https://github.com/CalWade/aigc-creator/tree/main/.agents/skills/lark-minutes Command: npx skills add https://github.com/CalWade/aigc-creator --skill lark-minutes-calwade
minutes +search and minutes minutes get. - Media Download & Upload: Download minute audio/video files (or get 1-day download links), and convert local audio/video files into minutes through the drive +upload → minutes +upload → vc +notes pipeline instead of local transcription tools like ffmpeg or whisper. - Edit AI Artifacts: Rename minutes, replace transcript speakers, batch add/update/delete AI todos inside a minute, and replace the full AI summary. - Use Case: A user says "turn this meeting recording mp4 into a transcript and summary"—the Skill uploads the file to Feishu Drive, generates a minute, extracts the minute_token, and fetches the transcript and AI summary via vc +notes. ## Quick Start Ask the AI to search your Feishu minutes from last week with a keyword, for example: "Find my minutes about budget review from last week and download the video."High-intent search queries and answers about installing and using this skill.
Use `lark-cli minutes +search` with filters like `--query`, `--owner-ids`, `--participant-ids`, `--start`, and `--end`. At least one filter is required, and `me` can be passed to represent the current user. Results paginate via `page_token` when `has_more` is true.
Upload the file with `lark-cli drive +upload` to get a file_token, run `lark-cli minutes +upload --file-token` to generate a minute, then extract the minute_token from the returned URL and call `lark-cli vc +notes --minute-tokens` to fetch the transcript and summary. Do not use local tools like ffmpeg or whisper.
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.
No. The `minutes +speaker-replace` command only accepts `ou_` prefixed open_id values for both `--from-user-id` and `--to-user-id`. If you only have a person's name, resolve it to an open_id first using the lark-contact skill.
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. Other common codes include 2091005 for missing read permission.
AI todos live inside a specific minute and are managed with `lark-cli minutes +todo` using add, update, or delete operations. Feishu Task list items are a separate product handled by the lark-task skill; the two must not be mixed.
luojiaaooQuery Feishu video meetings, minutes, and AI notes via lark-cli commands.
yokingmaRetrieve historical meeting data, notes, and transcripts via Lark VC commands.
QuixiAIGenerates meeting briefings from calendar events, contacts, and recalled memories.
yudameConvert podcast audio to MP3, transcribe locally with Whisper, and embed chapter metadata.