
Lark Vc
Let your agent search finished Lark video meetings and pull AI notes, todos, chapters, transcripts, and participant snapshots via lark-cli—without joining live calls.
Overview
lark-vc is an agent skill most often used in Build (also Operate, Grow) that searches completed Lark video meetings and retrieves notes, transcripts, and participant records via lark-cli.
Install
npx skills add https://github.com/larksuite/cli --skill lark-vcWhat is this skill?
- +search for ended meetings with keyword, time, organizer, participant, and room filters
- Distinguishes ended meetings (this skill) from future schedules (lark-calendar)
- Surfaces MainDoc summaries/todos, verbatim transcripts, and Minutes/recording tokens
- vc meeting get --with-participants for attendee snapshots including ended meetings
- Read-only: live join/leave and in-meeting events belong to lark-vc-agent, not this skill
- Supports search filters: keyword, time range, organizer, participant, meeting room
- Artifact types include MainDoc, VerbatimDoc, Minutes, and user MeetingNotes binding path
Adoption & trust: 208k installs on skills.sh; 13.7k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need what was decided in past Lark calls—notes, todos, or who attended—but calendar queries miss instant meetings and conflate future events with history.
Who is it for?
Lark-native teams who want meeting intelligence in the same agent session that ships code, especially retrospectives and customer call follow-ups.
Skip if: Scheduling future meetings (use lark-calendar), agent live presence in an ongoing call (use lark-vc-agent), or workspaces without lark-cli and VC read scopes.
When should I use this skill?
User asks how many or which meetings already finished, wants meeting notes/transcripts/recording metadata, or participant lists for ended Lark VC sessions.
What do I get? / Deliverables
The agent searches ended VC meetings with supported filters and returns note links or fetched summary/todo/chapter/verbatim content plus participant snapshots when requested.
- Paginated meeting search results for ended sessions
- Links or fetched content for AI notes, todos, chapters, and verbatim docs
- Participant snapshot from vc meeting get --with-participants
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Build → integrations because the skill documents read-only lark-cli vc commands and meeting artifact fetches tied to Lark APIs. Search, note retrieval, and participant snapshots are external platform hooks, same integration layer as other Lark CLI skills in this repo.
Where it fits
Pull last week's engineering sync notes and todos into a sprint follow-up list.
Find a customer call by keyword and share the MainDoc summary link with the team.
Verify who attended a architecture review via meeting get --with-participants.
Retrieve release postmortem verbatim transcript sections after the VC ended.
How it compares
Read-only Lark VC catalog skill—not a Zoom/Google Meet bot and not the in-meeting lark-vc-agent writer.
Common Questions / FAQ
Who is lark-vc for?
Builders on Feishu/Lark who want agents to query finished video meetings and meeting-minute artifacts from the terminal using documented lark-cli flows.
When should I use lark-vc?
Use it when users ask about meetings that already happened—counts, search, summaries, todos, chapters, transcripts, or attendees—or during operate retrospectives and grow customer-call debriefs; use lark-calendar for not-yet-started events.
Is lark-vc safe to install?
It reads meeting metadata and documents over the network with Lark credentials—check the Security Audits panel on this page and limit scopes to what your agent actually needs.
SKILL.md
READMESKILL.md - Lark Vc
# vc (v1) **CRITICAL — 开始前 MUST 先用 Read 工具读取 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md),其中包含认证、权限处理** ## 核心概念 - **视频会议(Meeting)**:飞书视频会议实例,通过 meeting\_id 标识。已结束的会议支持通过关键词、时间段、参会人、组织者、会议室等条件搜索(见 `+search`)。 - **会议纪要(Note)**:视频会议结束后生成的结构化文档,包含纪要文档(包含总结、待办、章节)和逐字稿文档。 - **妙记(Minutes)**:来源于飞书视频会议的录制产物或用户上传的音视频文件,支持视频/音频的转写和会议纪要,通过 minute\_token 标识。 - **纪要文档(MainDoc)**:AI 智能纪要的主文档,包含 AI 生成的总结和待办,对应 `note_doc_token`。 - **用户会议纪要(MeetingNotes)**:用户主动绑定到会议的纪要文档,对应 `meeting_notes`。仅通过 `--calendar-event-ids` 路径返回。 - **逐字稿(VerbatimDoc)**:会议的逐句文字记录,包含说话人和时间戳。 ## 核心场景 ### 1. 搜索会议记录 1. 仅支持搜索已结束的会议,对于还未开始的未来会议,需要使用 lark-calendar 技能。 2. 仅支持使用关键词、时间段、参会人、组织者、会议室等筛选条件搜索会议记录,对于不支持的筛选条件,需要提示用户。 3. 搜索结果存在多条数据时,务必注意分页数据获取,不要遗漏任何会议记录。 ### 2. 整理会议纪要 1. 整理纪要文档时默认给出纪要文档和逐字稿链接即可,无需读取纪要文档或逐字稿内容。 2. 用户明确需要获取纪要文档中的总结、待办、章节产物时,再读取文档获取具体内容。 3. 读取智能纪要(`note_doc_token`)内容时,纪要文档的**第一个 `<whiteboard>`** 标签是封面图(AI 生成的总结可视化),应同时下载展示给用户: ```bash # 1. 读取纪要内容 lark-cli docs +fetch --api-version v2 --doc <note_doc_token> --doc-format markdown # 2. 从返回的 markdown 中提取第一个 <whiteboard token="xxx"/> 的 token # 3. 下载封面图到聚合目录(和逐字稿、录像同目录,保持产物归拢) # 并非所有纪要都有封面画板,没有 <whiteboard> 标签时跳过即可 lark-cli docs +media-download --type whiteboard --token <whiteboard_token> --output ./minutes/<minute_token>/cover ``` > **产物目录规范**:同一会议的所有下载产物(录像、逐字稿、封面图等)统一放到 `./minutes/{minute_token}/` 目录下。这与 `minutes +download` 和 `vc +notes --minute-tokens` 的默认落点保持一致,便于 Agent 聚合。显式路径(如封面图)需手动对齐到同一目录。 > **纪要相关文档 — 根据用户意图选择:** > - `note_doc_token` → **AI 智能纪要**(AI 总结 + 待办 + 章节) > - `meeting_notes` → **用户绑定的会议纪要**(用户主动关联到会议的文档,仅 `--calendar-event-ids` 路径返回) > - `verbatim_doc_token` → **逐字稿**(完整的逐句文字记录,含说话人和时间戳)— 用户说"逐字稿""完整记录""谁说了什么"时用这个 > - 用户说"纪要""总结""纪要内容"时,应同时返回 `note_doc_token` 和 `meeting_notes`(如有) > - 用户意图不明确时,应展示所有文档链接让用户选择,而不是替用户决定 > - 如果用户提供的是**本地音视频文件**并说"转纪要""转逐字稿",不要直接从 `vc +notes` 开始;应先用 [minutes +upload](../lark-minutes/references/lark-minutes-upload.md) 生成 `minute_url`,再提取 `minute_token` 调用 `vc +notes --minute-tokens` ### 3. 纪要文档与逐字稿链接 1. 纪要文档、逐字稿文档与关联的共享文档默认使用文档 Token 返回。 2. 仅需要获取文档名称和 URL 等基本信息时,使用 `lark-cli drive metas batch_query` 查询 ```bash # 学习命令使用方式 lark-cli schema drive.metas.batch_query # 批量获取文档基本信息: 一次最多查询 10 个文档 lark-cli drive metas batch_query --data '{"request_docs": [{"doc_type": "docx", "doc_token": "<doc_token>"}], "with_url": true}' ``` 3. 需要获取文档内容时,使用 `lark-cli docs +fetch --api-version v2`。 ```bash # 获取文档内容 lark-cli docs +fetch --api-version v2 --doc <doc_token> --doc-format markdown ``` ### 4. 查询参会人快照(读操作) 用户问"谁参加过这场会议""这个会议有哪些参会人""某某参会了吗"等**参会人快照**类问题时,使用 **`vc meeting get --with-participants`**:这是参会人服务端快照 API,不依赖 bot 身份参会,**已结束会议也可查**: ```bash lark-cli vc meeting get --params '{"meeting_id":"<meeting_id>","with_participants":true}' ``` 选型判断表: | 用户意图 | 推荐命令 | 所在 skill | |---------|---------|--------| | 参会人快照(谁参加过、何时入/离会,任意时点)| `vc meeting get --with-participants` | 本 skill | | 已结束会议的发言内容 | `vc +notes` 取 `verbatim_doc_token` 再 `docs +fetch --api-version v2` | 本 skill | | **进行中会议**的实时事件流(转写、聊天、共享、会中加入/离开)| `vc +meeting-events` | [`lark-vc-agent`](../lark-vc-agent/SKILL.md) | | **Agent 真实入会 / 离会** | `vc +meeting-join` / `vc +meeting-leave` | [`lark-vc-agent`](../lark-vc-agent/SKILL.md) | ## 资源关系 ``` Meeting (视频会议) ├── Note (会议纪要) │ ├── MainDoc (AI 智能纪要文档, note_doc_token) │ ├── MeetingNotes (用户绑定的会议纪要文档, meeting_notes) │ ├── VerbatimDoc (逐字稿, verbatim_doc_token) │ └── SharedDoc (会中共享文档) └── Minutes (妙记) ← minute_token 标识,+recording 从 meeting_id 获取 ├── Transcript (文字记录) ├──