Turn 飞书 API operations into reusable skills for AI agents using lark-cli. Create SKILL.md instructions for individual commands or multistep workflows, documenting required permissions, data passed between steps, and failure recovery.
创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。
Review the instructions the agent will receive before you install.
基于 lark-cli 创建新 Skill。Skill = 一份 SKILL.md，教 AI 用 CLI 命令完成任务。
lark-cli <service> <resource> <method> # 已注册 API
lark-cli <service> +<verb> # Shortcut（高级封装）
lark-cli api <METHOD> <path> [--data/--params] # 任意飞书 OpenAPI
lark-cli schema <service.resource.method> # 查参数定义
优先级：Shortcut > 已注册 API > api 裸调。
# 1. 查看已有的 API 资源和 Shortcut
lark-cli <service> --help
# 2. 查参数定义
lark-cli schema <service.resource.method>
# 3. 未注册的 API，用 api 直接调用
lark-cli api GET /open-apis/vc/v1/rooms --params '{"page_size":"50"}'
lark-cli api POST /open-apis/vc/v1/rooms/search --data '{"query":"5F"}'
如果以上命令无法覆盖需求（CLI 没有对应的已注册 API 或 Shortcut），使用 lark-openapi-explorer 从飞书官方文档库逐层挖掘原生 OpenAPI 接口，获取完整的方法、路径、参数和权限信息，再通过 lark-cli api 裸调完成任务。
通过以上流程确定需要哪些 API、参数和 scope。
文件放在 skills/lark-<name>/SKILL.md：
---
name: lark-<name>
version: 1.0.0
description: "<功能描述>。当用户需要<触发场景>时使用。"
metadata:
requires:
bins: ["lark-cli"]
---
# <标题>
> **前置条件：** 先阅读 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)。
## 命令
\```bash
# 单步操作
lark-cli api POST /open-apis/xxx --data '{...}'
# 多步编排：说明步骤间数据传递
# Step 1: ...（记录返回的 xxx_id）
# Step 2: 使用 Step 1 的 xxx_id
\```
## 权限
| 操作 | 所需 scope |
|------|-----------|
| xxx | `scope:name` |
lark-cli auth login --domain <name>--dry-run 预览No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find and process approval requests in 飞书, including approving, rejecting, transferring, or returning them. Review forms and progress, search existing approval forms and workflows, and submit native requests such as leave or expense claims.
Build, publish, and manage apps on 妙搭（Spark/Miaoda） through local development or cloud AI sessions. Create page designs, manage data and permissions, inspect logs and usage, and configure automated triggers.
Retrieve your own attendance clock records from 飞书 through lark-cli. The skill fills in fixed query parameters and uses read-only attendance access to look up the records you want to check.
Build and manage business tables in Feishu Base, including fields, records, views, and data queries. Create forms and dashboards, configure automated workflows, organize BaseApp pages and components, and manage role-based access permissions.
Manage events, attendees, and meeting rooms in 飞书. Check shared availability, get meeting time suggestions that account for working hours and breaks, and create or update events with room reservations.
Finds Lark contacts by name or email and retrieves open_id, an identifier used in later actions. It also looks up profile details, personal status, and signatures, and searches for bots or agents visible to the current user.