vc (v1)

CRITICAL, Before starting, you MUST use the Read tool to read ../lark-shared/SKILL.md, which contains information on authentication and permission handling.

Core Concepts

• Meeting: A Lark video meeting instance, identified by meeting_id. Ended meetings can be searched using keywords, time ranges, participants, organizers, meeting rooms, etc. (see +search).
• Note: A structured document generated after a video meeting ends, containing a note document (including summaries, to-dos, and chapters) and a verbatim transcript document.
• Minutes: Recording products from Lark video meetings or audio/video files uploaded by users, supporting transcription and meeting notes, identified by minute_token.
• MainDoc: The main document of the AI intelligent notes, containing AI-generated summaries and to-dos, corresponding to note_doc_token.
• MeetingNotes: Note documents explicitly bound to a meeting by the user, corresponding to meeting_notes. Returned only via the --calendar-event-ids path.
• VerbatimDoc: A sentence-by-sentence text record of the meeting, including speakers and timestamps.

Core Scenarios

1. Searching Meeting Records

1. Only ended meetings are supported. For future meetings that have not yet started, use the lark-calendar skill.
2. Only filtering conditions such as keywords, time ranges, participants, organizers, and meeting rooms are supported. For unsupported filtering conditions, prompt the user.
3. When search results contain multiple items, be sure to handle pagination to ensure no meeting records are missed.

2. Organizing Meeting Notes

1. When organizing note documents, providing links to the note document and the verbatim transcript by default is sufficient. There is no need to read the content of the note document or the verbatim transcript.
2. Only read the document to obtain specific content when the user explicitly requests summaries, to-dos, or chapter products from the note document.
3. When reading the content of intelligent notes (note_doc_token), the first <whiteboard> tag in the note document is the cover image (AI-generated summary visualization), which should be downloaded and displayed to the user:

# 1. Read note content
lark-cli docs +fetch --api-version v2 --doc <note_doc_token> --doc-format markdown
# 2. Extract the token of the first <whiteboard token="xxx"/> from the returned markdown
# 3. Download the cover image to the aggregation directory (same directory as the verbatim transcript and recording, to keep products together)
#    Not all notes have a cover whiteboard; skip if there is no <whiteboard> tag
lark-cli docs +media-download --type whiteboard --token <whiteboard_token> --output ./minutes/<minute_token>/cover

Product Directory Specification: All downloaded products for the same meeting (recordings, verbatim transcripts, cover images, etc.) should be placed in the ./minutes/{minute_token}/ directory. This is consistent with the default output locations of minutes +download and vc +notes --minute-tokens, facilitating Agent aggregation. Explicit paths (such as cover images) must be manually aligned to the same directory.

Note-related Documents, Choose based on user intent:

• note_doc_token → AI Intelligent Notes (AI summary + to-dos + chapters)
• meeting_notes → User-bound Meeting Notes (documents explicitly associated with the meeting by the user, returned only via the --calendar-event-ids path)
• verbatim_doc_token → Verbatim Transcript (complete sentence-by-sentence text record, including speakers and timestamps), Use this when the user asks for "verbatim transcript," "complete record," or "who said what"
• When the user asks for "notes," "summary," or "note content," return both note_doc_token and meeting_notes (if available)
• When user intent is unclear, display all document links for the user to choose from, rather than deciding for them
• If the user provides a local audio/video file and says "convert to notes" or "convert to verbatim transcript," do not start directly with vc +notes; first use minutes +upload to generate a minute_url, then extract the minute_token to call vc +notes --minute-tokens

3. Linking Note Documents and Verbatim Transcripts

1. Note documents, verbatim transcript documents, and associated shared documents are returned using document Tokens by default.
2. When only basic information such as document name and URL is needed, use lark-cli drive metas batch_query to query.

# Learn how to use the command
lark-cli schema drive.metas.batch_query

# Batch get basic document information: query up to 10 documents at a time
lark-cli drive metas batch_query --data '{"request_docs": [{"doc_type": "docx", "doc_token": "<doc_token>"}], "with_url": true}'

3. When document content is needed, use lark-cli docs +fetch --api-version v2.

# Get document content
lark-cli docs +fetch --api-version v2 --doc <doc_token> --doc-format markdown

4. Querying Participant Snapshots (Read Operation)

When a user asks questions like "who attended this meeting," "who are the participants in this meeting," or "did so-and-so attend," use vc meeting get --with-participants: This is a server-side participant snapshot API that does not rely on the bot joining the meeting, and ended meetings can also be queried:

lark-cli vc meeting get --params '{"meeting_id":"<meeting_id>","with_participants":true}'

Selection Decision Table:

Resource Relationships

Meeting
├── Note
│   ├── MainDoc (AI Intelligent Note Document, note_doc_token)
│   ├── MeetingNotes (User-bound Meeting Note Document, meeting_notes)
│   ├── VerbatimDoc (Verbatim Transcript, verbatim_doc_token)
│   └── SharedDoc (Shared document during meeting)
└── Minutes ← identified by minute_token, +recording obtained from meeting_id
    ├── Transcript
    ├── Summary
    ├── Todos
    └── Chapters

Note: +search can only query ended historical meetings. To query future calendar arrangements, use lark-calendar.

Priority: When a user searches for historical meetings, vc +search should be prioritized over calendar events search. Calendar search is oriented toward schedules, while VC search is oriented toward ended meeting records, supporting filtering by participants, organizers, meeting rooms, etc.

Routing Rules: If the user asks about "meetings held," "what meetings were held today," "what have I attended recently," "ended meetings," or "historical meeting records," prioritize vc +search. Only prioritize lark-calendar when querying future schedules, upcoming meetings, or agendas.

Minutes Boundary: +notes is responsible for note content, verbatim transcripts, and AI products; for basic information about Minutes, please prioritize +recording and lark-minutes.

File-to-Notes Boundary: If the user provides a local audio/video file and wants notes, verbatim transcripts, summaries, to-dos, or chapters, the entry point should first go through the lark-minutes upload process to generate a minute_url / minute_token, then return to vc +notes --minute-tokens to obtain content products.

Special Case: When a user asks "what meetings are there today," query meeting records held today via vc +search, and simultaneously use the lark-calendar skill to query meetings that have not yet started today, then organize and display them to the user.

Shortcuts (Recommended for priority use)

Shortcuts are advanced wrappers for common operations (lark-cli vc +<verb> [flags]). Use shortcuts whenever available.

• When using the +search command, you must read references/lark-vc-search.md to understand search parameters and return value structures.
• When using the +notes command, you must read references/lark-vc-notes.md to understand query parameters, product types, and return value structures.
• When using the +recording command, you must read references/lark-vc-recording.md to understand query parameters and return value structures.

Agent meeting-related commands are independent: For +meeting-join / +meeting-leave / +meeting-events, please use the lark-vc-agent skill.

API Resources

lark-cli schema vc.<resource>.<method>   # Must view parameter structure before calling API
lark-cli vc <resource> <method> [flags] # Call API

Important: When using native APIs, you must first run schema to view the --data / --params parameter structure; do not guess field formats.

meeting

• get, Get meeting details (topic, time, participants, note_id)

# Get basic meeting information: does not include participant list
lark-cli vc meeting get --params '{"meeting_id": "<meeting_id>"}'


# Get basic meeting information: includes participant list
lark-cli vc meeting get --params '{"meeting_id": "<meeting_id>", "with_participants": true}'

minutes (Cross-domain, see lark-minutes for details)

• get, Get basic Minutes information (title, duration, cover); to query note content, use +notes --minute-tokens <minute-token>

Permissions Table

For Agent meeting-related scopes (vc:meeting.bot.join:write / vc:meeting.meetingevent:read), see lark-vc-agent.