Lark CLI is a command-line tool for using Lark/Feishu services such as messaging, documents, spreadsheets, calendars, mail, tasks, and meetings. It is intended for people and AI agents that need to work with these business tools through terminal commands.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/larksuite/clinpx agentmods add skills/larksuite/cli/lark-workflow-meeting-summaryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/larksuite/cli/lark-workflow-meeting-summary)<a href="https://agentmods.dev/skills/larksuite/cli/lark-workflow-meeting-summary"><img src="https://agentmods.dev/badge/skills/larksuite/cli/lark-workflow-meeting-summary.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.02069 |
| Opus 5 | $0.00028 | $0.01035 |
| Sonnet 5 | $0.00011 | $0.00414 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
lark-workflow-meeting-summary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- lark-workflow-meeting-summary — 86% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
会议纪要汇总工作流
CRITICAL — 开始前 MUST 先完整读取 ../lark-shared/SKILL.md 和 ../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:
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
# 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为包含当天的日期(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。- 有
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
- 查询会议关联的纪要信息
# 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_id和minute_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)。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 130 lines · 55 tokens per session scan A 2cc95a5db67b
lark-workflow-meeting-summary is a skill published in the GitHub repository larksuite/cli (17,058 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,069 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.