lark-note

Query Lark meeting note details and unified transcripts by note_id via lark-cli.

Updated May 28, 2026
One-click install
npx skills add https://github.com/changfengpro/agent-skills --skill lark-note-changfengpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-note
Source: https://github.com/changfengpro/agent-skills/tree/main/skills/lark-note
Command: npx skills add https://github.com/changfengpro/agent-skills --skill lark-note-changfengpro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? When you already hold a Lark meeting note ID (note_id), this Skill retrieves the note's display type, associated document tokens (AI summary, verbatim transcript, shared docs), and the raw unified transcript—without guessing note IDs from titles or doc tokens. ## Core Features & Use Cases - Note Detail Lookup: Run note +detail --note-id to get note_display_type, note_doc_token, verbatim_doc_token, and shared_doc_tokens, with explicit --as user / --as bot identity handling. - Unified Transcript Retrieval: Run note +transcript --note-id (user identity only) to fetch the full raw verbatim record, auto-paginated and saved to a local file. - Routing Discipline: Routes by note_display_type (normal/unknown/unified) and delegates document body reading to lark-doc, meeting lookup to lark-vc, and minutes lookup to lark-minutes. - Use Case: You received a vc-node-id from a fetched document and need the meeting's verbatim transcript—use this Skill to resolve the note detail, detect it is unified, and pull the full transcript. ## Quick Start Ask the assistant to look up the Lark meeting note with your note_id and fetch its summary document token or unified transcript.

Frequently Asked Questions about lark-note

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

FAQPage Schema
How do I get a Lark meeting note's document tokens from a note_id?

Run `lark-cli note +detail --note-id <note_id>` with the same identity (`--as user` or `--as bot`) that obtained the note_id. It returns note_doc_token, verbatim_doc_token, and shared_doc_tokens, which you then read via docs +fetch.

How to fetch the raw verbatim transcript of a Lark meeting note?

First confirm note_display_type is unified via note +detail, then run `lark-cli note +transcript --note-id <id>`. It only supports --as user and saves the full auto-paginated transcript to ./notes/{note_id}/unified_transcript.md.

Can I derive a note_id from a doc_token or document title?

No. The Note domain only accepts an explicit note_id from the user or the vc-node-id in a <vc-transcribe-tab> element returned by docs +fetch. Never reverse-engineer note_id from doc_token, titles, body text, or backlinks.

Why does note +transcript fail when using bot identity?

The +transcript command only supports --as user. If note +detail --as bot returns a unified note, you must stop and get the user's explicit consent before switching to --as user to fetch the transcript.

What should I do if I only have a meeting_id or minute_token instead of a note_id?

Use vc +detail --meeting-ids to get the note_id from a meeting_id, or minutes +detail --minute-tokens to get it from a minute_token. Then call note +detail with that note_id; never pass a minute_token as a note_id.