Lark Workflow Meeting Summary logo

Lark Workflow Meeting Summary

OrganizationPopular
larksuite
lark-workflow-meeting-summary

会议纪要整理工作流:汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

Overview

Publisherlarksuite
Repositorycli
Skill namelark-workflow-meeting-summary
Stars
17.3K
Forks
1.4K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by larksuite on GitHub. Read the source before you install it.

Installation

Install the Lark Workflow Meeting Summary AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/larksuite/cli.git /tmp/cli
mkdir -p .claude/skills
cp -r /tmp/cli/skills/lark-workflow-meeting-summary .claude/skills/lark-workflow-meeting-summary
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lark Workflow Meeting Summary in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lark Workflow Meeting Summary on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lark Workflow Meeting Summary is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

会议纪要汇总工作流

CRITICAL — 开始前 MUST 先完整读取 ../lark-shared/SKILL.md../lark-meeting/SKILL.md。认证、身份和权限以 lark-shared 为准;会议与产物关系、产物选择和逐字稿路由以 lark-meeting 为准。

适用场景

  • "帮我整理这周的会议纪要" / "总结最近的会议" / "生成会议周报"
  • "看看今天开了哪些会" / "回顾过去一周开了哪些会"

前置条件

仅支持 user 身份。执行前确保已授权:

bash
lark-cli auth login --domain vc        # 基础(查询+纪要)
lark-cli auth login --domain vc,drive   # 含读取纪要文档正文、生成文档
lark-cli auth login --domain vc,drive,minutes  # 含无 note_id 时的妙记备选路径

工作流

{时间范围} ─► vc +search ──► 会议列表 (meeting_ids)
               vc +detail ──► 获取 note_id 
               note +detail ──► 纪要文档 tokens
               drive metas batch_query 纪要元数据
               结构化报告

Step 1: 确定时间范围

默认过去 7 天。推断规则:"今天"→当天,"这周"→本周一now,"上周"→上周一上周日,"这个月"→1日~now。

注意:日期转换必须调用系统命令(如 date),不要心算。时间范围参数需根据 CLI 实际要求格式化(通常为 YYYY-MM-DD 或 ISO 8601)。

Step 2: 查询会议记录

bash
# page-size 最大为 30
lark-cli vc +search --start "<YYYY-MM-DD>" --end "<YYYY-MM-DD>" --format json --page-size 30
  • 时间范围拆分:搜索的时间范围最大为 1 个月。搜索更长时间范围的会议,需要拆分为多次时间范围为一个月查询。
  • --end包含当天的日期(即查"今天"时 start 和 end 都填今天)
  • --format json 输出 JSON 格式,你更佳擅长解析 JSON 数据。
  • --page-size 30 每页最多 30 条。
  • page_token 时必须继续翻页,收集所有 id 字段(meeting-id)

Step 3: 获取纪要元数据

  1. 查询会议关联的纪要信息
bash
# 首先获取 note_id 和 minute_token
lark-cli vc +detail --meeting-ids "id1,id2,...,idN"

# 然后用 note_id 获取文档 tokens(如有多个需分别获取)
lark-cli note +detail --note-id "note_id"
  • 根据上一步搜集到的 meeting-id 查询。
  • 单次最多查询 50 个,超过 50 个需分批调用。
  • 部分会议没有 note_id 或报错 no notes available不要直接标注"无纪要":先看 vc +detail 是否返回了 minute_token,有则走下面的妙记备选路径;note_idminute_token 都没有时才标注"无纪要"。
  • 记录每个纪要的 note_id(纪要 ID)、note_display_type(展示类型:unknown / normal / unified)、note_doc_token(纪要文档 Token)和 verbatim_doc_token(逐字稿文档 Token)。

妙记备选路径(无 note_id、有 minute_token 时):智能纪要与妙记是两条独立产物链路,缺少智能纪要不代表这场会没有内容。

bash
# --minute-tokens 是复数形式(+download 同);--output-dir 只接受相对路径
lark-cli minutes +detail --minute-tokens "<minute_token>" --transcript --output-dir ./transcripts --as user

逐字稿会落盘,供 Step 4 基于原始发言独立提炼(不要照搬 AI 总结)。若返回 No read permission2091005),先把无权限事实告知用户,用户明确同意后再用单数 flag 申请:lark-cli minutes +apply-permission --minute-token "<minute_token>" --perm view --as user;申请需 owner 在客户端批准后才可重试。详见 基于 minute_token 查询妙记及关联产物

逐字稿路由按 note_display_type 决定(详见 基于 note_id 查询智能纪要及关联产物):

  • normal:逐字稿是独立文档,链接/正文走 verbatim_doc_token
  • unified:逐字稿不是独立文档,没有可分享的逐字稿文档链接;需要逐字稿内容时用 note +transcript --note-id <note_id>lark-meeting)拉取到本地,报告中标注"unified 纪要"即可。
  1. 获取纪要文档和逐字稿文档链接
bash
# 学习命令使用方式
lark-cli schema drive.metas.batch_query

# 批量获取纪要文档与逐字稿链接: 一次最多查询 10 个文档
# 仅对 note_doc_token 与 normal 纪要的 verbatim_doc_token 查询链接
lark-cli drive metas batch_query --data '{"request_docs": [{"doc_type": "docx", "doc_token": "<doc_token>"}], "with_url": true}'

Step 4: 整理纪要报告

根据时间跨度选择输出格式:

  • 单日汇总("今天"/"昨天"):用"今日会议概览"标题,逐会议列出会议时间、主题、纪要链接、逐字稿链接(unified 纪要无逐字稿链接,标注"unified 纪要,逐字稿需 note +transcript 拉取")。
  • 多日/周报("这周"/"过去 7 天"等):用"会议纪要周报"标题,含概览统计、逐会议详情。

Step 5: 生成文档(可选,用户要求时)

阅读 ../lark-doc/SKILL.md 学习云文档技能。

bash
lark-cli docs +create --doc-format markdown --content $'<title>会议纪要汇总 (<start> - <end>)</title>\n<内容>'
# 或追加到已有文档
lark-cli docs +update --doc "<url_or_token>" --command append --doc-format markdown --content $'<内容>'

参考

Frequently asked questions

What does the Lark Workflow Meeting Summary AI skill do?

会议纪要整理工作流:汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

Why use Lark Workflow Meeting Summary on TypingMind?

Because you install it once and use it with any model. Lark Workflow Meeting Summary is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lark Workflow Meeting Summary in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/larksuite/cli/tree/main/skills/lark-workflow-meeting-summary. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Lark Workflow Meeting Summary?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lark Workflow Meeting Summary?

As many as you like. As long as a model supports skills, you can use Lark Workflow Meeting Summary with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lark Workflow Meeting Summary AI skill free?

Yes. It is published on GitHub by larksuite under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇