
Lark Skill Maker
- 493k installs
- open.feishu.cn
lark-skill-maker is a Claude skill that authors new custom lark-cli Skills (SKILL.md files) wrapping Feishu API operations for an AI agent.
About
This skill helps a developer author new custom lark-cli Skills, where a Skill is a SKILL.md that teaches an AI to complete a task with CLI commands. It supplies the SKILL.md template and a research flow (service --help, schema, raw api) to determine the required APIs, parameters and scopes. It is used when wrapping an atomic Feishu API or orchestrating a multi-step flow into a reusable Skill.
- Creates new custom lark-cli Skills that teach an AI to complete Feishu tasks via CLI commands
- Provides a SKILL.md template and the research flow (--help, schema, api) to discover the needed APIs, params and scopes
- Sets priority Shortcut > registered API > raw api call and stresses trigger-focused descriptions
Lark Skill Maker by the numbers
- 492,584 all-time installs (skills.sh)
- +41,431 installs in the week ending Jul 29, 2026 (Skillselion tracking)
- Ranked #2 of 782 Skill Development skills by installs in the Skillselion catalog
- Data as of Jul 29, 2026 (Skillselion catalog sync)
lark-skill-maker capabilities & compatibility
Free skill; needs lark-cli for API research.
- Capabilities
- skill authoring · skill scaffolding · api research · agent tooling
- Runs
- Runs locally
- Pricing
- Free
What lark-skill-maker says it does
基于 lark-cli 创建新 Skill。Skill = 一份 `SKILL.md`,教 AI 用 CLI 命令完成任务。
优先级:Shortcut > 已注册 API > `api` 裸调。
npx skills add https://github.com/open.feishu.cn --skill lark-skill-makerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 493k |
|---|---|
| Repository | open.feishu.cn ↗ |
What it does
Author a new reusable lark-cli Skill (SKILL.md) that wraps Feishu API operations for an AI agent.
Who is it for?
Turning a Feishu API operation or multi-step flow into a reusable lark-cli SKILL.md.
Skip if: Running an existing Feishu task; this only authors new Skills.
When should I use this skill?
A user wants to package Feishu API operations into a new, reusable, trigger-able Skill.
By the numbers
- 4 core CLI capabilities (registered API, shortcut, raw api, schema)
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
Forks & variants (2)
Lark Skill Maker has 2 known copies in the catalog totaling 386k installs. They canonicalize to this original listing.
- larksuite - 386k installs
- liangdabiao - 7 installs
FAQ
What is the command priority when building a Skill?
Shortcut > registered API > raw api call, per the skill's core priority guidance.
What determines whether a Skill triggers?
Its description; it should include the capability keywords plus a '当用户需要...时使用' trigger phrase.