Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ddpie/lark-mcp-on-agentcore --skill lark-taskgit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-task)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-task"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-task"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00125 | $0.02946 |
| Opus 5 | $0.00063 | $0.01473 |
| Sonnet 5 | $0.00025 | $0.00589 |
| Haiku 4.5 | $0.00013 | $0.00295 |
Grade A, and why
lark-task 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task (v2)
(authentication is handled automatically by the MCP server)
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
lark_task_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lark_task_search与lark_task_get_related_tasks/lark_task_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lark_task_get_related_tasks;"我负责的 / 分配给我"的列表优先考虑lark_task_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lark_task_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lark_discover(query="task.tasklists.list"),再lark_invoke(tool_name="lark_task_tasklists_list", args={...})),再按creator、created_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lark_task_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 — 待办 disambiguation(必读):
- 用户提到「待办 / todo / 任务」时,先判断归属,不要默认走本 skill。
- 走 minutes 的
lark_minutes_todo(禁止本 skill):上下文含 妙记 / 会议纪要 / minute_token / 妙记 URL(/minutes/);或「在某某妙记里新建/修改待办」「妙记 AI 待办」「会议录制里的待办」。详见lark_get_skill(domain="minutes")。- 走本 skill(lark-task):任务清单、分配给我、项目待办、截止日期/提醒、子任务、任务清单成员;或 applink 含
client/todo/task?guid=;或明确说「飞书任务」「任务中心」「我的任务清单」。- 禁止:用户要在妙记里加待办时,不要通过
lark_invoke(tool_name="lark_task_tasklists_list")、lark_task_create()或任何 task 工具去「找清单再放任务」。 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工具返回结果中的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:
- 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)。- 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。- 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:
- 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。- 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。- 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。
| Shortcut | 说明 |
|---|---|
lark_get_skill(domain="task", section="create") |
create a task |
lark_get_skill(domain="task", section="update") |
update task attributes |
lark_get_skill(domain="task", section="set-ancestor") |
set or clear a task ancestor |
lark_get_skill(domain="task", section="comment") |
add a comment to a task |
lark_get_skill(domain="task", section="complete") |
mark a task as complete |
lark_get_skill(domain="task", section="reopen") |
reopen a completed task |
lark_get_skill(domain="task", section="assign") |
assign or remove task members |
lark_get_skill(domain="task", section="followers") |
manage task followers |
lark_get_skill(domain="task", section="reminder") |
manage task reminders |
lark_get_skill(domain="task", section="get-my-tasks") |
List tasks assigned to me |
lark_get_skill(domain="task", section="get-related-tasks") |
list tasks related to me |
lark_get_skill(domain="task", section="search") |
search tasks |
lark_get_skill(domain="task", section="upload-attachment") |
upload a local file as an attachment to a task |
lark_get_skill(domain="task", section="tasklist-create") |
create a tasklist and optionally add tasks |
lark_get_skill(domain="task", section="tasklist-search") |
search tasklists |
lark_get_skill(domain="task", section="tasklist-task-add") |
add tasks to a tasklist |
lark_get_skill(domain="task", section="tasklist-members") |
manage tasklist members |
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/lark-task-assign.md 1.2 KB
- references/lark-task-comment.md 734 B
- references/lark-task-complete.md 591 B
- references/lark-task-create.md 2.5 KB
- references/lark-task-followers.md 1.1 KB
- references/lark-task-get-my-tasks.md 3.1 KB
- references/lark-task-get-related-tasks.md 2.7 KB
- references/lark-task-reminder.md 1.3 KB
- references/lark-task-reopen.md 591 B
- references/lark-task-search.md 1.3 KB
- references/lark-task-set-ancestor.md 794 B
- references/lark-task-tasklist-create.md 1.1 KB
- references/lark-task-tasklist-members.md 1016 B
- references/lark-task-tasklist-search.md 1.2 KB
- references/lark-task-tasklist-task-add.md 1.3 KB
- references/lark-task-update.md 1.2 KB
- references/lark-task-upload-attachment.md 2.8 KB
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 · 163 lines · 125 tokens per session scan A 8cc2164a9feb
lark-task is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 10d ago), licensed MIT. It adds 125 tokens to every session and 2,946 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
calendar
Manage Lark calendar - view schedule, create/update/delete events, check availability, find meeting slots, RSVP to invitations. Use when user asks about meetings, schedule, availability, or calendar.
luma-event-promo
End-to-end Luma event launch: research comparable events in the target city, draft copy that doesn't read like AI slop, create a Private draft via the admin API, fix the startat / duration / capacity traps, and polish theme, font, and cover. Use this whenever the user wants to publish, edit, or shape an event for…
recipe-project-tracker
Sync project data between Lark and Notion.
reserve-equipment
A scheduling skill for reserving shared laboratory equipment, including GPUs, 3D printers, and microscopes. It interprets requested times, checks for conflicts, and handles the reservation or asks for a different slot.
daily-standup
An automated weekday stand-up process for a laboratory. It gathers yesterday's progress, today's plans, and blockers, then posts a summary to the lab's group chat at 09:30.
lab-onboarding
An onboarding checklist for new laboratory members. It keeps 12 tasks in a document and follows up each day on anything unfinished.