PlugWiki

lark-openapi-explorer Skill for Claude: Find Lark and Feishu APIs

Lets Claude look up Lark or Feishu API endpoints in the official docs and call them with lark-cli when no ready-made command exists.

Installs
470.3K
on skills.sh
Stars
17.9K
on GitHub
Updated
Oct 2026
last repo commit

lark-openapi-explorer is the fallback when other lark skills and commands cannot do the job. Claude first checks lark-cli <service> --help. If nothing fits, it walks the official docs index step by step: top-level index, module page, then one API page. Then it calls the endpoint with lark-cli api.

The docs index is open.feishu.cn/llms.txt for Feishu and open.larksuite.com/llms.txt for Lark. The docs are in Chinese, so SKILL.md has Claude translate when you write in English. It tells Claude not to guess paths or parameters, to confirm before any POST, PUT or DELETE, and to preview with --dry-run where possible. It needs lark-cli and the lark-shared skill.

Good for

  • Developers who hit a Lark task that lark-cli has no command for
  • Admins who need org-chart or group actions the other lark skills skip
  • Anyone building a new lark-cli skill who needs the endpoint details

Install lark-openapi-explorer

Claude Code

  1. 1

    Copy this prompt.

    Install the lark-openapi-explorer 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. 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

飞书/Lark 原生 OpenAPI 探索：从官方文档库中挖掘未经 CLI 封装的原生 OpenAPI 接口。当用户的需求无法被现有 lark-* skill 或 lark-cli 已注册命令满足，需要查找并调用原生飞书 OpenAPI 时使用。

Sections in SKILL.md

  1. 文档库结构
  2. 挖掘流程
  3. Step 1：确认现有能力不足
  4. Step 2：从顶层索引定位模块
  5. Step 3：从模块文档定位具体 API
  6. Step 4：获取 API 完整规范
  7. Step 5：通过 CLI 调用 API
  8. 输出规范
  9. 安全规则
  10. 使用场景示例
  11. 场景 1：用户需要拉人进群（未被 CLI 封装）
  12. 场景 2：用户需要设置群公告
  13. 参考

Key facts

Author
Lark Suite (larksuite)
Repository
larksuite/cli, folder skills/lark-openapi-explorer
Installs on skills.sh
470,317 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: warn

What it includes

  • Looks for a ready-made command or skill first

    Runs lark-cli <service> --help; stops if something fits.

    Runs code · Step 1: check existing commands

  • Fetches the top-level docs index

    Reads llms.txt from the Feishu or Lark site.

    Network · Step 2: find the module

  • Fetches the module page

    Finds the doc link for the specific API.

    Network · Step 3: find the API

  • Fetches the full API page

    Gets method, path, parameters, response, scopes and error codes.

    Network · Step 4: read the spec

  • Runs lark-cli api GET, POST, PUT or DELETE

    Raw calls; writes need your confirmation per SKILL.md.

    Try: “Add these two people to the chat; the CLI has no command for it.”

    Delete · Step 5: call it

  • Summarizes name, method, path, parameters, scopes, example

    Includes a full lark-cli api command.

    Read · Report format

From the official docs

Permissions

Medium risk

Claude can make raw Lark API calls, including writes and deletes, that no other lark skill guards. Confirm each write and use a dry run first when available.

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 can call any API your sign-in allows

    Raw calls skip the safety wrappers of the specific skills. Check each POST, PUT or DELETE before approving, and use --dry-run when it works. github.com

  • It reads docs from the web

    API details come from the official docs pages at run time. Check the endpoint Claude shows against what you asked for. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details
Turning on read-onlyThe 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 toLark/Feishu Open Platform API calls made by lark-cli. Your AI provider receives whatever Claude reads from Lark. open.feishu.cn or open.larksuite.com, to read the API docs
Sign-in and keyslark-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

  • Fetches pages from open.feishu.cn or open.larksuite.com

  • Can make any Lark Open API call that your sign-in allows, including writes and deletes

Questions

How do I install lark-openapi-explorer?

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-openapi-explorer?

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.

When should I use lark-openapi-explorer instead of the other lark skills?

Only when no other lark skill or lark-cli command covers the job. SKILL.md has Claude check for an existing command first and stop if one exists. The org-chart and department questions that lark-contact skips are one example.

Can it change or delete things in Lark?

Yes. It makes raw API calls, including POST, PUT and DELETE. SKILL.md requires confirming your intent before those, suggests --dry-run where supported, and asks Claude to explain the impact of sensitive actions such as removing members.

Is lark-openapi-explorer safe?

Use it with care. Raw API calls can write or delete, and the skill bundles no scripts. 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-openapi-explorer

larksuite/cliskills.sh

Sources

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

Show all 3
  1. larksuite/cli README · github.com
  2. lark-openapi-explorer SKILL.md · github.com
  3. lark-skill-maker SKILL.md · github.com

Updated Nov 2, 2026.