
Lark Skill Maker
- 384k installs
- 15.9k repo stars
- Updated July 28, 2026
- larksuite/cli
This is a copy of lark-skill-maker by open.feishu.cn - installs and ranking accrue to the original listing.
lark-skill-maker is an agent skill that scaffolds reusable SKILL.md files wrapping lark-cli API calls or multi-step Feishu/Lark workflows for developers who want repeatable agent instructions instead of one-off CLI invoc
About
lark-skill-maker is a meta-skill in the larksuite/cli repository for packaging Feishu/Lark automation as agent-ready SKILL.md files. It teaches the priority order Shortcut > registered API > lark-cli api raw call, and guides research with lark-cli --help, lark-cli schema <service.resource.method>, and lark-openapi-explorer for unregistered endpoints. A finished skill is one SKILL.md that documents CLI commands, parameters, and workflow steps so Claude, Cursor, or Codex agents can execute Feishu tasks reliably. Developers reach for it after validating an API path and wanting durable, shareable agent instructions. Version 1.0.0; requires lark-cli.
- Generates complete SKILL.md files that teach Claude or Cursor how to use lark-cli commands
- Supports three invocation priorities: Shortcut > registered API > raw api command
- Includes schema lookup, help exploration, and fallback to lark-openapi-explorer
- Produces ready-to-use command blocks with data passing between orchestrated steps
- Enforces shared prerequisites via lark-shared/SKILL.md reference
Lark Skill Maker by the numbers
- 383,822 all-time installs (skills.sh)
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/larksuite/cli --skill lark-skill-makerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 384k |
|---|---|
| repo stars | ★ 15.9k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 28, 2026 |
| Repository | larksuite/cli ↗ |
How do you package Lark API workflows as agent skills?
Quickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.
Who is it for?
Developers who validated a Feishu/Lark API workflow and want a reusable agent skill instead of repeating manual lark-cli exploration.
Skip if: Developers running a one-off Lark API call that an existing lark-* skill or registered lark-cli command already handles.
When should I use this skill?
A Feishu/Lark API operation or multi-step workflow should be encapsulated as a new reusable lark-cli agent skill.
What you get
SKILL.md file with lark-cli commands, parameter schemas, and workflow steps
- SKILL.md agent skill file
By the numbers
- Version 1.0.0 in skill manifest
- Requires the lark-cli binary as a prerequisite
Files
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` |关键原则
- description 决定触发 — 包含功能关键词 + "当用户需要...时使用"
- 认证 — 说明所需 scope,登录用
lark-cli auth login --domain <name> - 安全 — 写入操作前确认用户意图,建议
--dry-run预览 - 编排 — 说明数据传递、失败回滚、可并行步骤
Related skills
FAQ
What does lark-skill-maker produce?
lark-skill-maker produces a SKILL.md file that teaches coding agents how to run lark-cli commands—either a single atomic Feishu API wrapper or a multi-step Lark workflow with documented parameters and invocation order.
How does lark-skill-maker choose an API invocation method?
lark-skill-maker follows lark-cli priority: Shortcut commands first, then registered service.resource.method APIs, then lark-cli api for unregistered Feishu OpenAPI endpoints discovered via schema or openapi-explorer.
Is Lark Skill Maker safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.