PluginBench
Skill

lark-attendance

open.feishu.cn

Query your Lark/Feishu attendance check-in records via CLI

What is lark-attendance?

lark-attendance is a skill for coding agents that enables querying personal attendance and check-in records from Feishu (Lark) using the lark-cli tool. It wraps the Feishu Attendance API with automatic parameter injection so agents never need to prompt users for standard fields like employee_type or user_ids.

  • Queries user attendance check-in records from Feishu via lark-cli
  • Automatically injects required parameters (employee_type, user_ids) without prompting the user
  • Provides schema inspection for API parameters before making calls
  • Enforces correct scope (attendance:task:readonly) for API access
  • Reads shared authentication config from lark-shared SKILL.md at runtime

How to install lark-attendance

npx skills add null --skill lark-attendance
Prerequisites
  • lark-cli must be installed and available in PATH
  • lark-shared SKILL.md must be present (provides authentication and permission handling)
  • Feishu app must have the attendance:task:readonly scope granted
Claude Code
Cursor
Windsurf
Cline

How to use lark-attendance

  1. 1.Install the skill: npx skills add null --skill lark-attendance
  2. 2.Ensure lark-cli is installed and lark-shared SKILL.md is accessible
  3. 3.Run lark-cli attendance --help to confirm the CLI is working
  4. 4.Before calling any API, inspect the parameter schema: lark-cli schema attendance.user_tasks.query
  5. 5.Call the query method: lark-cli attendance user_tasks query with appropriate --params or --data flags
  6. 6.employee_type is always set to employee_no automatically — do not override
  7. 7.user_ids array is always set to [] automatically — do not override
  8. 8.Review returned check-in records for the requested date range

Use cases

Good for
  • Check your own attendance punch-in/punch-out history for a date range
  • Audit attendance records programmatically inside a coding agent workflow
  • Retrieve check-in data as part of an automated HR or reporting task
Who it's for
  • Developers using Claude Code or Cursor who need to query Feishu attendance data
  • Teams automating HR workflows via Feishu APIs
  • Engineers building internal tools on top of the Feishu attendance system

lark-attendance FAQ

Do I need to provide user_ids or employee_type when making API calls?

No. Both are injected automatically: user_ids is always [] and employee_type is always employee_no. You must not ask the user for these values.

What permission scope is required?

The attendance:task:readonly scope must be granted to your Feishu app.

Where is authentication handled?

Authentication is handled by lark-shared SKILL.md, which must be read before using this skill.

How do I check what parameters an API method accepts?

Run lark-cli schema attendance.user_tasks.query before calling the API to inspect the expected --data and --params structure.

Which API methods are available?

Currently only user_tasks.query is available, which retrieves attendance check-in records.

Full instructions (SKILL.md)

Source of truth, from open.feishu.cn.


name: lark-attendance version: 1.0.0 description: "飞书考勤打卡:查询自己的考勤打卡记录" metadata: requires: bins: ["lark-cli"] cliHelp: "lark-cli attendance --help"

attendance (v1)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../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:

{
  "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

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.queryattendance:task:readonly
lark-attendance — AI Skill | PluginBench