PluginBench
Skill
Review
Audit score 70

lark-note

larksuite/cli

Query Lark meeting notes by note_id: fetch details, display type, document tokens, and unified transcripts.

View on skills.sh

What is lark-note?

Retrieves meeting note (Note) details when you have a note_id or vc-node-id. Use this to access note metadata, associated document tokens, and unified verbatim transcripts. Does not handle meeting/calendar lookup, document title search, or Docx content reading.

  • Query note details including display type (normal/unified/unknown) and associated document tokens
  • Retrieve unified meeting transcripts with original word-for-word records
  • Access note document token (MainDoc), verbatim document token (VerbatimDoc), and shared document tokens
  • Route to appropriate downstream skills based on note_display_type
  • Extract vc-node-id from document fetch results to identify note_id

How to install lark-note

npx skills add null --skill lark-note
Prerequisites
  • lark-cli installed and configured
  • Valid note_id or vc-node-id (from docs +fetch or vc +detail)
  • Read lark-vc/references/vc-domain-boundaries.md to understand meeting product relationships
Claude Code
Cursor
Windsurf
Cline

How to use lark-note

  1. 1.Obtain note_id (from user input, docs +fetch vc-node-id, or vc +detail result)
  2. 2.Run `lark-cli note +detail --note-id <note_id>` to get document tokens and display type
  3. 3.Check note_display_type: if 'unified', use `note +transcript --note-id <note_id>` for raw transcript; if 'normal' with verbatim_doc_token, use `docs +fetch --doc <verbatim_doc_token>`; if 'unknown', treat as independent document
  4. 4.Use returned note_doc_token with `docs +fetch` to read the AI summary document
  5. 5.Use returned shared_doc_tokens to access screenshared documents from the meeting

Use cases

Good for
  • You have a note_id and need to fetch the AI-generated summary document and verbatim transcript
  • A document contains a vc-transcribe-tab with vc-node-id; extract it and retrieve the full note details
  • You have a meeting_id and need to find its associated note_id and transcripts
  • Access the unified original transcript for a meeting note to see who said what with timestamps
  • Retrieve shared documents that were screenshared during the meeting
Who it's for
  • Users with explicit note_id or vc-node-id from documents
  • Meeting participants needing transcripts and summaries
  • Teams managing meeting documentation and records

lark-note FAQ

What is the difference between note_id and minute_token?

note_id identifies a meeting note (Note); minute_token identifies a meeting minute (妙记). They are separate products with independent generation conditions. Do not confuse them—use lark-minutes skill for minute_token.

How do I get a note_id if I only have a meeting_id?

Use `lark-cli vc +detail --meeting-ids <meeting_id>` to retrieve the note_id from the meeting details.

What should I do if note_display_type is 'unknown'?

If verbatim_doc_token is present, treat it as an independent document and use `docs +fetch`. If no verbatim_doc_token exists, you cannot determine the transcript entry point and should stop.

Can I search for notes by title?

No. This skill only accepts explicit note_id. For title-based search, use lark-drive or lark-doc skills to find the document first, then extract vc-node-id.

How do I read the full note content?

Use `note +detail` to get note_doc_token, then use `docs +fetch --doc <note_doc_token>` to read the AI-generated summary document.

Full instructions (SKILL.md)

Source of truth, from larksuite/cli.

name: lark-note version: 1.0.0 description: "飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。" metadata: requires: bins: ["lark-cli"] cliHelp: "lark-cli note --help"

note (v1)

身份：仅使用 --as user。使用前阅读 ../lark-shared/SKILL.md。

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-vc/references/vc-domain-boundaries.md，不读将导致命令使用、会议产物决策、领域边界职责判断错误：

  1. 了解日历 & VC、会议产物 & 文档的关联关系和职责划分
  2. 了解会议产物（妙记和纪要）之间的关联关系，例如：妙记和纪要产生条件相互独立
  3. 了解不同会议产物的组成部分，以便根据需求决策使用哪种产物的数据

Note 域只接受显式 note_id：用户直接提供，或 docs +fetch 返回的 <vc-transcribe-tab vc-node-id="..."> 中的 vc-node-id。不要从 doc_token、标题、正文或 backlink 反推 note_id。

命令路由

用户表达 / 上下文路由
已知 note_id，查纪要类型 / 文档 tokennote +detail --note-id NOTE_ID
docs +fetch 返回 <vc-transcribe-tab vc-node-id="...">取 vc-node-id 作为 NOTE_ID，先 note +detail --note-id NOTE_ID
只持有 meeting_id先 vc +detail --meeting-ids <id> 拿 note_id，再 note +detail --note-id NOTE_ID
只持有 minute_token（妙记 URL）先 minutes +detail --minute-tokens <token> 顶层取 note_id，再 note +detail --note-id NOTE_ID（不要把 minute_token 当 note_id）
只持有日程 event_id先 calendar +meeting --event-ids <id> 拿 meeting_id，再按上一行继续
已知 note_id，读纪要正文note +detail → docs +fetch --doc <note_doc_token>
已知 note_id，查 unified 原始记录 / 逐字稿note +transcript --note-id NOTE_ID
只有自然语言纪要标题，用户要逐字稿 / 原始记录 / 谁说了什么不进本 skill；先走文档搜索与 docs +fetch，拿到 vc-node-id 后再回来

note_display_type 路由

note +detail 结果用户要逐字稿 / 原始记录时
normal + verbatim_doc_token 非空docs +fetch --doc <verbatim_doc_token>
unknown + verbatim_doc_token 非空先按独立文档处理；不要猜成 unified
unknown + 无逐字稿 token停止重试并说明无法确定逐字稿入口
unifiednote +transcript --note-id <note_id>

判别键是 note_display_type，不是 verbatim_doc_token 是否为空：unified 纪要也可能返回非空 verbatim_doc_token。

关键字段

  • note_id：Note 域唯一入口。
  • note_display_type：unknown / normal / unified。
  • note_doc_token：纪要正文文档，正文读取交给 lark-doc。
  • verbatim_doc_token：普通纪要逐字稿文档；unified 逐字稿不按这个 token 路由。

不在本 Skill 范围

  • 通过 meeting_id 定位纪要（note_id）→ lark-vc（vc +detail）。
  • 通过 minute_token 定位纪要（note_id）→ lark-minutes（minutes +detail 顶层返回 note_id）。
  • 通过日程 event_id 定位会议(meeting_id) / 用户绑定纪要(meeting_note) → lark-calendar（calendar +meeting）。
  • 自然语言纪要标题搜索 → lark-drive / lark-doc。
  • Docx 正文读取 → lark-doc。
  • 妙记基础信息与媒体文件 → lark-minutes。

Shortcuts

Shortcut何时读 reference
+detail需要解释输出字段或根据展示类型继续路由
+transcript需要拉取 unified 原始记录或处理本地输出文件

核心概念

  • 会议纪要（Note）：视频会议结束后生成的结构化文档，通过 note_id 标识。一个 Note 包含 AI 智能纪要文档、逐字稿文档和会中共享文档。
  • note_id：纪要的唯一标识符，可通过 vc +detail --meeting-ids 获取。
  • AI 智能纪要（MainDoc）：AI 生成的会议总结与待办，对应 note_doc_token。
  • 逐字稿（VerbatimDoc）：会议的逐句发言记录，含说话人和时间戳，对应 verbatim_doc_token。
  • 共享文档（SharedDoc）：会中投屏共享的文档，对应 shared_doc_tokens。

核心场景

1. 通过 note_id 获取纪要文档 Token

  1. 当用户已有 note_id，需要获取对应的 note_doc_token、verbatim_doc_token 或 shared_doc_tokens 时，使用 note +detail。
  2. note_id 通常来自 vc +detail 的返回结果。
  3. 获取到文档 Token 后，可使用 docs +fetch 读取文档内容，或使用 drive metas batch_query 获取文档元信息。
# 1. 从会议获取 note_id
lark-cli vc +detail --meeting-ids <meeting_id>

# 2. 用 note_id 拿文档 Token
lark-cli note +detail --note-id <note_id>

# 3. 读取纪要文档内容
lark-cli docs +fetch --doc <note_doc_token> --doc-format markdown

Related skills

More from larksuite/cli and the wider catalog.

LA

lark-doc

larksuite/cli

Read and edit Lark/Feishu Docx & Wiki documents via CLI — fetch, create, update, and manage media attachments.

293k installs
LA

lark-base

larksuite/cli

Manage Lark Base (multi-dimensional tables): create tables, fields, records, views, formulas, forms, dashboards, workflows, and roles.

292k installs
LA

lark-im

larksuite/cli

Lark/Feishu IM skill: send messages, manage group chats, download files, and handle interactive cards via lark-cli

292k installs
LA

lark-drive

larksuite/cli

Manage Lark/Feishu Drive files and folders: upload, download, import, organize, comment, and control permissions.

292k installsAudited
LA

lark-shared

larksuite/cli

Manage Lark CLI auth, identity, permissions, and scopes for coding agents like Claude Code and Cursor

291k installsAudited
LA

lark-calendar

larksuite/cli

Manage Lark calendar events and meeting rooms: view, create, update events, check availability, and book rooms.

291k installsAudited