Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
larksuite avatar

Lark Task

  • 387k installs
  • 15.9k repo stars
  • Updated July 28, 2026
  • larksuite/cli

This is a copy of lark-task by open.feishu.cn - installs and ranking accrue to the original listing.

lark-task is a Lark CLI agent skill that creates, updates, assigns, and tracks Feishu tasks and task lists for developers who manage project todos from an AI coding agent.

About

lark-task is a version 1.0.0 agent skill in larksuite/cli that exposes Lark (Feishu) task management through lark-cli task v2 commands. It supports creating todos, viewing and updating status, splitting subtasks, organizing task lists, assigning collaborators, uploading attachments, and registering task agents. Developers use lark-task when automating standup prep, syncing issue trackers into Lark tasks, or closing loops on assigned work without leaving the terminal. The skill routes keyword searches to +search while scope-only queries such as my open tasks favor +get-my-tasks or +get-related-tasks. Authentication and permission rules live in lark-shared, which agents must read before invoking any task command.

  • Create, update, and track tasks with subtasks and due dates
  • Manage tasklists, assign collaborators, and upload attachments
  • Register, update, or unregister task agents and write agent task records
  • Smart intent routing: uses search only when explicit query keywords are provided, otherwise prefers get-my-tasks or get-
  • Tasklist search follows identical keyword-vs-range logic before calling list or search endpoints

Lark Task by the numbers

  • 386,599 all-time installs (skills.sh)
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/larksuite/cli --skill lark-task

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs387k
repo stars15.9k
Security audit3 / 3 scanners passed
Last updatedJuly 28, 2026
Repositorylarksuite/cli

How do you manage Lark tasks from the command line?

Let their coding agent create, update, track, assign, and organize tasks inside Lark/Feishu directly from natural language.

Who is it for?

Developers automating Lark todo workflows who need create, assign, search, and status updates via lark-cli from an agent.

Skip if: Teams without Lark/Feishu task modules enabled or agents that only need calendar scheduling without todo tracking.

When should I use this skill?

User asks to create todos, assign tasks, list open work, upload task attachments, or manage Lark task agents.

What you get

Created or updated tasks, assigned collaborators, uploaded attachments, and filtered task lists with status metadata.

  • created or updated tasks
  • task list queries
  • attachment uploads

By the numbers

  • Targets Lark task v2 commands in lark-cli
  • Published as version 1.0.0 with lark-cli binary requirement

Files

SKILL.mdMarkdownGitHub ↗

task (v2)

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

任务搜索技巧:先区分用户是否特地指定使用搜索 skill,以及是否真的提供了查询关键字(例如任务名称、关键词、片段描述)。如果用户特地指定使用搜索 skill,或明确给出了任务查询关键字,则目标是任务时优先使用 +search。如果用户没有特地指定使用搜索 skill,且意图里没有查询关键字,只有范围条件(例如“今年以来”“已完成”“由我创建”“我关注的”),并且使用 +search+get-related-tasks / +get-my-tasks 都能达到目的时,应优先使用列表型能力,而不是搜索型能力。其中,“与我相关 / 我关注的 / 由我创建”等优先考虑 +get-related-tasks;“我负责的 / 分配给我”的列表优先考虑 +get-my-tasks。不要把时间范围词(例如“今年以来”)本身误当成 query 去走搜索。
任务清单搜索技巧:任务清单也遵循同样的判断逻辑。先区分用户是否特地指定使用搜索 skill,以及是否真的提供了清单查询关键字(例如清单名称、关键词、片段描述)。如果用户特地指定使用搜索 skill,或明确给出了清单查询关键字,则优先使用 +tasklist-search。如果用户没有特地指定使用搜索 skill,且意图里没有查询关键字,只有范围条件(例如“由我创建的任务清单”“今年以来创建的清单”),并且使用搜索或原生列取清单都能达到目的时,应优先使用原生 tasklists.list 接口列取清单(先 schema task.tasklists.list,再 lark-cli task tasklists list --as user ...),再按 creatorcreated_at 等字段做本地筛选和分页控制。
意图区分补充:像“搜索飞书中今年以来我关注的任务”这类表达,虽然字面带有“搜索”,但如果没有真正的查询关键字,且本质是在限定“与我相关 + 时间范围”,则应优先走 +get-related-tasks;像“搜索飞书中由我创建的任务清单”这类表达,如果没有清单关键字,且本质是在限定“清单范围 + 创建者”,则应优先走原生 tasklists.list 后筛选,而不是直接走搜索型 shortcut。
用户身份识别:在用户身份(user identity)场景下,如果用户提到了“我”(例如“分配给我”、“由我创建”),请默认获取当前登录用户的 open_id 作为对应的参数值。
术语理解:如果用户提到 “todo”(待办),应当思考其是否是指“task”(任务),并优先尝试使用本 Skill 提供的命令来处理。
友好输出:在输出任务(或清单)的执行结果给用户时,建议同时提取并输出命令返回结果中的 url 字段(任务链接),以便用户可以直接点击跳转查看详情。
创建/更新注意
1. 只有在设置了 due(截止时间)的情况下,才能设置 repeat_rule(重复规则)和 reminder(提醒时间)。
2. 若同时设置了 start(开始时间)和 due(截止时间),开始时间必须小于或等于截止时间。
3. 使用 tenant_access_token(应用身份)时,无法跨租户添加任务成员。
查询注意
1. 在输出任务详情时,如果需要渲染负责人、创建人等人员字段,除了展示 id (例如 open_id) 外,还必须通过其他方式(例如调用通讯录技能)尝试获取并展示这个人的真实名字,以便用户更容易识别。
2. 在输出清单详情时,如果需要渲染 owner、member、角色成员等人员字段,也必须像任务成员展示一样,除了展示 id 外,尽量解析并展示对应人员的真实名字。
3. 在输出任务或清单详情时,如果需要渲染创建时间、截止时间等字段,需要使用本地时区来渲染(格式为2006-01-02 15:04:05)。
Task GUID 定义
Task OpenAPI 中用于更新/操作任务的 guid 是任务的全局唯一标识(GUID),不是客户端展示的任务编号(例如 t104121 / suite_entity_num)。
对于 Feishu 的任务 applink(例如 .../client/todo/task?guid=...),必须使用 URL query 里的 guid 参数作为 task guid。

Shortcuts

  • `+create` — Create a task
  • `+update` — Update a task
  • `+comment` — Add a comment to a task
  • `+complete` — Complete a task
  • `+reopen` — Reopen a task
  • `+assign` — Assign or remove members from a task
  • `+followers` — Manage task followers
  • `+reminder` — Manage task reminders
  • `+get-my-tasks` — List tasks assigned to me
  • `+get-related-tasks` — List tasks related to me
  • `+search` — Search tasks
  • `+subscribe-event` — Subscribe to task events
  • `+set-ancestor` — Set or clear a task ancestor
  • `+tasklist-create` — Create a tasklist and batch add tasks
  • `+tasklist-search` — Search tasklists
  • `+tasklist-task-add` — Add existing tasks to a tasklist
  • `+tasklist-members` — Manage tasklist members
  • `+upload-attachment` — Upload a file as a task attachment

API Resources

lark-cli schema task.<resource>.<method>   # 调用 API 前必须先查看参数结构
l

Related skills

FAQ

When should lark-task use +search versus +get-my-tasks?

lark-task uses +search when the user supplies a task name or keyword. For scope-only filters like created by me or completed this year without keywords, prefer +get-my-tasks or +get-related-tasks per the skill routing rules.

Does lark-task support task attachments?

lark-task supports uploading attachments to Lark tasks through lark-cli task commands. Read lark-shared SKILL.md first to configure user or bot credentials and required API scopes.

Is Lark Task safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Automation & Workflowsagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.