Lark Attendance
Query your own Feishu/Lark attendance punch records through lark-cli when an agent needs factual check-in history—without asking you for employee IDs.
Overview
lark-attendance is an agent skill for the Operate phase that queries your own Lark attendance punch records through lark-cli user_tasks.query.
Install
npx skills add https://github.com/larksuite/cli --skill lark-attendanceWhat is this skill?
- Single API surface: attendance user_tasks.query via lark-cli
- Auto-fills employee_type employee_no and empty user_ids—never prompt the user for those fields
- Requires lark schema before guessing --data or --params JSON shapes
- Scope attendance:task:readonly documented in the permission table
- Must read lark-shared SKILL.md first for authentication
- 1 documented API method: user_tasks.query
- 2 auto-filled fields: employee_type employee_no and user_ids []
Adoption & trust: 161k installs on skills.sh; 13.7k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need your punch-in history from Lark in an agent session but the attendance API expects fixed employee fields you should not have to specify manually.
Who is it for?
Lark employees who want a one-command attendance history pull inside Claude Code, Cursor, or Codex.
Skip if: Managers bulk-querying other employees, editing punches, or teams not on Lark attendance with lark-cli and attendance:task:readonly.
When should I use this skill?
User asks to see their own Lark/Feishu attendance or punch/check-in records.
What do I get? / Deliverables
The agent returns your attendance task/query results using auto-filled employee_no parameters and schema-valid lark-cli calls.
- Structured attendance query results for the authenticated user
Recommended Skills
Journey fit
Canonical shelf is Operate → iterate because the skill only supports personal attendance lookup for day-to-day work rhythm, not building product features. Punch history informs how you allocate coding time and proves compliance during ongoing operations, not greenfield integration design.
How it compares
Thin read-only Lark HR CLI skill—not a full time-tracking SaaS integration or spreadsheet exporter.
Common Questions / FAQ
Who is lark-attendance for?
Individual Lark users who want their agent to fetch personal attendance records using the official lark-cli attendance skill.
When should I use lark-attendance?
Use it during Operate when you need to verify your own check-in/out history for a date range— for example reconciling remote work days before planning the week's ship goals.
Is lark-attendance safe to install?
It only documents readonly attendance scope usage, but still accesses personal HR data over the network—review the Security Audits panel on this page and tenant privacy rules.
SKILL.md
READMESKILL.md - Lark Attendance
# attendance (v1) **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** ## 默认参数自动填充规则 调用任何 API 时，以下参数 **必须自动填充，禁止向用户询问**： | 参数 | 固定值 | 说明 | |------|--------|------------------------------------| | `employee_type` | `"employee_no"` | `employee_type`始终等于`"employee_no"` | | `user_ids` | `[]`（空数组） | `user_ids`始终等于`[]` | ### 填充示例 当构建 `--params` 参数时，自动注入上述字段： - `employee_type` 保持 `"employee_no"` 不变 当构建 `--data` 参数时，自动注入上述字段： ```json { "user_ids": [], ...用户提供的参数 } ``` > **注意**：`user_ids` 数组保持为空[]，`employee_type` 保持 `"employee_no"` 不变。 ## API Resources ```bash lark-cli schema attendance.<resource>.<method> # 调用 API 前必须先查看参数结构 lark-cli attendance <resource> <method> [flags] # 调用 API ``` > **重要**：使用原生 API 时，必须先运行 `schema` 查看 `--data` / `--params` 参数结构，不要猜测字段格式。 ### user_tasks - `query` — 查询用户考勤打卡记录 ## 权限表 | 方法 | 所需 scope | |------|-----------| | `user_tasks.query` | `attendance:task:readonly` |