lark-skill-maker

SkillCommunityAudit warningsTranslated from Chinese

This skill provides a framework for creating custom skills for lark-cli. It enables users to wrap Lark API operations into reusable instructions for AI agents, supporting both atomic API calls and multi-step workflows.

Compatibility:

Visit lark-skill-maker

Install:

npx skills add larksuite/cli/lark-skill-maker

View on skills.sh

Skill Maker

Create a new Skill based on lark-cli. A Skill = a SKILL.md file that teaches an AI how to complete tasks using CLI commands.

CLI Core Capabilities

lark-cli <service> <resource> <method>          # Registered API
lark-cli <service> +<verb>                      # Shortcut (Advanced encapsulation)
lark-cli api <METHOD> <path> [--data/--params]  # Any Feishu OpenAPI
lark-cli schema <service.resource.method>       # Check parameter definitions

Priority: Shortcut > Registered API > api raw call.

Researching APIs

# 1. View existing API resources and Shortcuts
lark-cli <service> --help

# 2. Check parameter definitions
lark-cli schema <service.resource.method>

# 3. For unregistered APIs, call directly using api
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"}'

If the above commands cannot cover the requirements (the CLI does not have a corresponding registered API or Shortcut), use lark-openapi-explorer to dig through the official Feishu documentation library layer by layer to obtain complete method, path, parameter, and permission information, and then complete the task via lark-cli api raw calls.

Determine which APIs, parameters, and scopes are needed through the above process.

SKILL.md Template

Place the file in skills/lark-<name>/SKILL.md:

---
name: lark-<name>
version: 1.0.0
description: "<Function description>. Use when the user needs to <trigger scenario>."
metadata:
  requires:
    bins: ["lark-cli"]
---


# <Title>

> **Prerequisites:** Read [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md) first.

## Commands

\```bash
# Single-step operation
lark-cli api POST /open-apis/xxx --data '{...}'

# Multi-step orchestration: Explain data transfer between steps
# Step 1: ... (record the returned xxx_id)
# Step 2: Use the xxx_id from Step 1
\```

## Permissions

| Operation | Required scope |
|-----------|----------------|
| xxx       | `scope:name`   |

Key Principles

description determines triggering, Include functional keywords + "Use when the user needs to..."
Authentication, Explain the required scope, use lark-cli auth login --domain <name> for login
Security, Confirm user intent before write operations, recommend --dry-run for preview
Orchestration, Explain data transfer, failure rollback, and parallelizable steps

Skill Maker

基于 lark-cli 创建新 Skill。Skill = 一份 SKILL.md，教 AI 用 CLI 命令完成任务。

CLI 核心能力

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。

调研 API

# 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。

SKILL.md 模板

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` |