lark-skill-maker Skill for Claude: Build Your Own Lark Skills

Shows Claude how to turn Lark or Feishu API calls and multi-step flows into your own reusable lark-cli skill.

Installs: 470K; on skills.sh
Stars: 17.9K; on GitHub
Updated: Oct 2026; last repo commit

lark-skill-maker is a guide for writing new skills. It defines a skill as one SKILL.md that teaches the AI to use CLI commands, and gives a template to fill in. Claude researches the API first, picks the right command layer, then writes skills/lark-<name>/SKILL.md.

It prefers shortcuts, then registered API commands, then raw lark-cli api calls. If the CLI has no command for a step, it points to lark-openapi-explorer. The template lists the scopes the skill needs and says to confirm before writes and to preview with --dry-run. It needs lark-cli, and the template tells new skills to read lark-shared.

Good for

Developers who repeat the same Lark API steps and want them as a skill
Teams building internal skills on top of lark-cli
Skill authors who want the lark-cli conventions

Install lark-skill-maker

Claude Code

Copy this prompt.

Install the lark-skill-maker skill in Claude Code. Run this command:

npx @larksuite/cli@latest install

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

This skill only gives Claude instructions for the lark-cli command line, so install the CLI first, then the skills, then sign in. The skills command adds the whole larksuite/cli set, which includes lark-shared, the skill this one reads first for sign-in and permissions.

From the project README. Source.

What's in the skill

When it loads

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。

Sections in SKILL.md

CLI 核心能力
调研 API
SKILL.md 模板
命令
权限
关键原则

Key facts

Author: Lark Suite (larksuite)
Repository: larksuite/cli, folder skills/lark-skill-maker
Installs on skills.sh: 469,973 as of 2026-11-02
GitHub stars: 17,911 for the whole larksuite/cli repo, 2026-11-02
License: MIT
Last repo commit: 2026-10-30
What is inside: SKILL.md only; no scripts or extra files
skills.sh audits: Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass

What it includes

Checks commands, schemas and raw endpoints
Uses lark-cli <service> --help, lark-cli schema and lark-cli api.
Runs code · Research the API
Shortcut first, then registered API, then raw api
SKILL.md ranks shortcut above registered API above raw lark-cli api.
Read · Command priority
Front matter, commands and a permissions table
Claude fills it in and saves it under skills/lark-<name>/.
Try: “Make a lark skill that posts our daily metrics to a chat.”
Write · SKILL.md template
Write triggers into the description, state scopes, confirm writes
Includes advice on multi-step flows: pass IDs between steps and plan for rollback.
Read · Key principles

From the official docs

Permissions

Low risk

The skill writes a SKILL.md file and may run lark-cli commands while researching. Review the new skill before you rely on it, since it can contain write commands.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It acts as you in Lark after you sign in
The repo README warns that the agent works under your user identity within the authorized scope. Grant only the scopes you need and read commands before you approve them. github.com
It writes files and may try API calls
Research can run lark-cli api calls. Check that Claude uses read calls while exploring and keeps writes for the finished skill. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	The skill has no read-only switch. Sign in with a narrow scope list, for example lark-cli auth login --domain <name>, so the agent cannot reach more than you intend.
Talks to	Lark/Feishu Open Platform API calls made by lark-cli. Your AI provider receives whatever Claude reads from Lark
Sign-in and keys	lark-cli stores credentials in the OS keychain, per the repo README.
Scopes	Claude runs lark-cli commands in your terminal After you sign in, commands run as your Lark or Feishu user within the permissions you granted Writes a new SKILL.md at skills/lark-<name>/SKILL.md May run lark-cli help, schema and api calls while researching

Questions

How do I install lark-skill-maker?

Use the install box at the top of this page. The box lists three steps: install the Lark CLI, add the Lark skills, then set up an app and sign in. The skill is only instructions, so Claude cannot use it until lark-cli is installed and you are signed in.

Do I need a Lark account to use lark-skill-maker?

Yes. You need a Lark or Feishu account, plus an app set up with lark-cli config init. The README then has you sign in with lark-cli auth login --recommend. There is no separate API key to paste.

What does lark-skill-maker produce?

A new SKILL.md file at skills/lark-<name>/SKILL.md, following the template in the skill. It describes lark-cli commands for Claude to follow. It does not generate code or a program.

What if the API I need has no lark-cli command?

SKILL.md sends Claude to lark-openapi-explorer to dig the endpoint out of the official docs, then to wrap the call with lark-cli api.

Is lark-skill-maker safe?

Use it with care. The skill itself bundles no scripts and writes a text file, but the skills you build with it can call Lark APIs. The repo README warns that after you authorize Lark permissions the agent acts under your user identity and that model mistakes or prompt injection can cause real changes.

Information

updated Nov 2, 2026

Repository: larksuite/cli
Folder: skills/lark-skill-maker

larksuite/cli skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2

larksuite/cli README · github.com
lark-skill-maker SKILL.md · github.com