lark-minutes

minutes (v1)

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

Core Concepts

Minutes: originates from recordings of Feishu video meetings or audio/video files uploaded by users, identified by minute_token .
Minute Token (minute_token): the unique identifier of a Minute, which can be extracted from the end of the Minute URL (for example, https://*.feishu.cn/minutes/obcnq3b9jl72l83w4f14xxxx in obcnq3b9jl72l83w4f14xxxx). If the URL contains additional parameters (such as ?xxx), the last segment of the path should be taken.

Core Scenarios

1. Search Minutes

When the user describes "my Minutes", "Minutes containing a certain keyword", or "Minutes within a certain time period", prioritize using minutes +search。
Only supports searching Minutes records using filter conditions such as keywords, time periods, participants, and owners. For unsupported filter conditions, the user needs to be prompted.
When the search results contain multiple records, be sure to pay attention to paginated data retrieval and do not miss any Minutes records.
If it is the Minutes of a meeting, prioritize using vc +search to first locate the meeting, then as needed use vc +recording to get minute_token。

2. View basic Minutes information

When the user only needs to confirm basic information about a Minute such as its title, cover, duration, owner, URL, etc., use minutes minutes get。
If the user provides a Minute URL, first extract minute_tokenfrom the end of the URL, then call minutes minutes get。
When the user's intent is unclear, by default first provide the basic metadata to help confirm whether the target Minute is matched.

Use lark-cli schema minutes.minutes.get to view the complete return value structure. Core fields include:title(title),cover(cover URL),duration(duration, in milliseconds),owner_id(owner ID),url(Minute link).

3. Download Minutes audio/video files

Download Minutes audio/video files locally, or obtain a download link valid for 1 day. See minutes +download。
minutes +download only handles audio/video media files.
When the user only wants a shareable download address, use --url-only; when the user wants to save to a local file, download directly.

Note：+download only handles audio/video media files. If what the user needs is Minutes content such as transcripts, summaries, todos, chapters, etc., please use vc +notes --minute-tokens。

4. Get the Minute's transcript, summary, todos, chapters

When the user says "this Minute's transcript", "summary", "todos", or "chapters",does not belong to this skill。
Should use vc +notes --minute-tokens to get the corresponding Minutes output.
If the current context already contains minute_token, it can be passed directly to vc +notes; if there is only the Minute URL, first extract minute_token。

# 通过 minute_token 获取纪要产物（逐字稿、总结、待办、章节）
lark-cli vc +notes --minute-tokens <minute_token>

Cross-skill routing: Minutes content such as transcripts, AI summaries, todos, chapters, etc. is provided by lark-vc of +notes commands

Resource Relationships

Minutes (妙记) ← minute_token 标识
├── Metadata (标题、封面、时长、owner、url) → minutes minutes get
└── MediaFile (音频/视频文件) → minutes +download

Capability Boundaries：minutes Responsible for searching Minutes, viewing basic metadata, downloading audio/video files。

Routing rules：

User says "Minutes list / search Minutes / Minutes for a certain keyword" → minutes +search

The user just wants to see "my Minutes / Minutes within a certain period / Minutes list"; do not first go through lark-vc, but instead use this skill directly

If the user also mentions "meeting / conference / have a meeting / a certain meeting," even if they also mention "Minutes," prioritize going through lark-vc to first locate the meeting, then through vc +recording to get minute_token

When the user says "my Minutes / Minutes I own / Minutes I participated in," the relevant filter conditions can be mapped to me；me represents the current user

When the results have multiple pages, use page_token to continue paging until it is confirmed there are no more results

minutes +search Returns at most 200 items per call; there is no fixed upper limit on the total number of results

User says "this Minutes' title / duration / cover / link" → minutes minutes get

User says "download this Minutes' video / audio / media file" → minutes +download

User says "this Minutes' transcript / summary / to-dos / chapters" → use vc +notes --minute-tokens

Shortcuts (prefer using first)

Shortcut is a high-level wrapper for common operations (lark-cli minutes +<verb> [flags]). For operations that have a Shortcut, prefer using it.

Shortcut	description
`+search`	Search minutes by keyword, owners, participants, and time range
`+download`	Download audio/video media file of a minute

When using the +search command, you must read references/lark-minutes-search.mdto understand the search parameters and return value structure.
When using the +download command, you must read references/lark-minutes-download.mdto understand the download parameters and return value structure.

API Resources

lark-cli schema minutes.<resource>.<method>   # 调用 API 前必须先查看参数结构
lark-cli minutes <resource> <method> [flags] # 调用 API

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

minutes

get — get Minutes information

Permissions table

Method	Required scope
`+search`	`minutes:minutes.search:read`
`minutes.get`	`minutes:minutes:readonly`
`+download`	`minutes:minutes.media:export`