Skill

Review

Audit score 70

lark-openapi-explorer

larksuite/cli

Discover and call native Feishu/Lark OpenAPIs not yet wrapped by lark-cli commands

What is lark-openapi-explorer?

lark-openapi-explorer is a skill for coding agents that enables step-by-step discovery and invocation of raw Feishu/Lark OpenAPI endpoints. When existing lark-* skills or lark-cli registered commands cannot satisfy a user's requirement, this skill guides the agent through the official markdown documentation hierarchy—from top-level index to module docs to individual API specs—and then calls the API directly via `lark-cli api`. It enforces a strict no-guessing policy: all API paths and parameters must be sourced from official docs before any call is made.

Checks existing lark-cli commands before attempting raw API discovery
Fetches and parses the Feishu/Lark llms.txt documentation index to locate relevant modules
Drills into module-level docs to find specific API documentation links
Retrieves full API specs including HTTP method, path, parameters, request body, permissions, and error codes
Calls discovered APIs using `lark-cli api` with GET, POST, PUT, DELETE, or PATCH methods
Requires user confirmation before executing write or delete operations

How to install lark-openapi-explorer

npx skills add null --skill lark-openapi-explorer

Prerequisites

lark-cli must be installed and available in PATH
Authentication must be configured per the lark-shared SKILL.md (credentials, identity switching)
Network access to open.feishu.cn or open.larksuite.com for documentation fetching
Agent must support WebFetch capability to retrieve markdown documentation

Claude Code

Cursor

Windsurf

Cline

How to use lark-openapi-explorer

1.Install the skill: npx skills add null --skill lark-openapi-explorer
2.Ensure lark-cli is installed and authenticated following lark-shared setup
3.Ask the agent to perform a Feishu/Lark action; the skill first checks if an existing lark-cli command covers it
4.If no existing command is found, the skill fetches https://open.feishu.cn/llms.txt (or open.larksuite.com for Lark) to locate the relevant module
5.The skill fetches the module-level doc to find the specific API link
6.The skill fetches the individual API markdown to extract method, path, parameters, permissions, and error codes
7.The skill presents the API spec and example `lark-cli api` command for review before execution
8.Confirm write/delete operations when prompted; the skill then executes via `lark-cli api`

Use cases

Good for

Adding members to a Feishu/Lark group chat when lark-cli has no chat_members command
Setting or updating a group announcement not covered by existing CLI commands
Accessing any Feishu/Lark OpenAPI endpoint that has no corresponding lark-cli shortcut
Exploring available API capabilities across Feishu/Lark modules before building a new skill
Performing one-off administrative API calls without writing custom integration code

Who it's for

Developers using Claude Code or Cursor with lark-cli installed
Teams automating Feishu/Lark workflows that go beyond pre-packaged CLI commands
Administrators needing to call specific Feishu/Lark APIs not yet wrapped as skills
Engineers evaluating which Feishu/Lark APIs to formalize into new lark-* skills

lark-openapi-explorer FAQ

When should I use this skill instead of other lark-* skills?

Use it only when no existing lark-* skill or lark-cli registered command covers your need. The skill itself checks this first via `lark-cli <service> --help`.

Does this skill work for both Feishu and Lark brands?

Yes. It uses open.feishu.cn for Feishu and open.larksuite.com for Lark. If the brand is unclear, it defaults to Feishu.

Will the skill guess API paths if it cannot find documentation?

No. The skill explicitly prohibits guessing API paths or parameters. All specs must be confirmed from official documentation before any call is made.

What happens before a POST, PUT, or DELETE call is made?

The skill requires explicit user confirmation before executing any write or delete operation, and recommends previewing with --dry-run where supported.

Can I turn a discovered API into a reusable skill?

Yes. The lark-skill-maker skill is referenced for formalizing discovered APIs into new installable lark-* skills.

Full instructions (SKILL.md)

Source of truth, from larksuite/cli.

name: lark-openapi-explorer version: 1.0.0 description: "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。" metadata: requires: bins: ["lark-cli"]

OpenAPI Explorer

前置条件： 先阅读 ../lark-shared/SKILL.md 了解认证、身份切换和安全规则。

当用户的需求无法被现有 skill 或 CLI 已注册 API 覆盖时，使用本技能从飞书官方 markdown 文档库中逐层挖掘原生 OpenAPI 接口，然后通过 lark-cli api 裸调完成任务。

文档库结构

飞书 OpenAPI 文档以 markdown 层级组织：

llms.txt                          ← 顶层索引，列出所有模块文档链接
  └─ llms-<module>.txt            ← 模块文档，包含功能概述 + 底层 API 文档链接
       └─ <api-doc>.md            ← 单个 API 的完整说明（方法/路径/参数/响应/错误码）

文档入口：

品牌	入口 URL
飞书 (Feishu)	`https://open.feishu.cn/llms.txt`
Lark	`https://open.larksuite.com/llms.txt`

所有文档以中文编写。如果用户使用英文交流，需将文档内容翻译为英文后输出。

挖掘流程

严格按以下步骤逐层检索，不要跳步或猜测 API：

Step 1：确认现有能力不足

# 先检查是否已有对应的 skill 或已注册 API
lark-cli <可能的service> --help

如果已有对应命令或 shortcut，直接使用，不需要继续挖掘。

Step 2：从顶层索引定位模块

用 WebFetch 获取顶层索引，找到与需求相关的模块文档链接：

WebFetch https://open.feishu.cn/llms.txt
  → 提取问题："列出所有模块文档链接，找出与 <用户需求关键词> 相关的链接"

飞书品牌使用 open.feishu.cn
Lark 品牌使用 open.larksuite.com
如不确定用户品牌，默认使用飞书

Step 3：从模块文档定位具体 API

用 WebFetch 获取模块文档，找到具体 API 的文档链接：

WebFetch https://open.feishu.cn/llms-docs/zh-CN/llms-<module>.txt
  → 提取问题："找出与 <用户需求> 相关的 API 说明和文档链接"

Step 4：获取 API 完整规范

用 WebFetch 获取具体 API 文档，提取完整的调用规范：

WebFetch https://open.feishu.cn/document/server-docs/.../<api>.md
  → 提取问题："返回完整 API 规范：HTTP 方法、URL 路径、路径参数、查询参数、请求体字段（名称/类型/必填/说明）、响应字段、所需权限、错误码"

Step 5：通过 CLI 调用 API

使用 lark-cli api 裸调：

# GET 请求
lark-cli api GET /open-apis/<path> --params '{"key":"value"}'

# POST 请求
lark-cli api POST /open-apis/<path> --data '{"key":"value"}'

# PUT 请求
lark-cli api PUT /open-apis/<path> --data '{"key":"value"}'

# DELETE 请求
lark-cli api DELETE /open-apis/<path>

输出规范

向用户呈现挖掘结果时，按以下格式组织：

API 名称与功能：一句话描述
HTTP 方法与路径：METHOD /open-apis/...
关键参数：列出必填和常用可选参数
所需权限：scope 列表
调用示例：给出 lark-cli api 的完整命令
注意事项：频率限制、特殊约束等

如果用户使用英文交流，将以上所有内容翻译为英文。

安全规则

写入/删除类 API（POST/PUT/DELETE）调用前必须确认用户意图
建议先用 --dry-run 预览请求（如支持）
不要猜测 API 路径或参数——必须从文档中获取确认
涉及敏感操作（删除群、移除成员等）时，向用户说明影响范围

使用场景示例

场景 1：用户需要拉人进群（未被 CLI 封装）

# Step 1: 确认 CLI 没有封装
lark-cli im --help
# → 发现没有 chat_members 相关的 create 命令

# Step 2-4: 通过文档挖掘获得 API 规范
# → POST /open-apis/im/v1/chats/:chat_id/members

# Step 5: 调用
lark-cli api POST /open-apis/im/v1/chats/oc_xxx/members \
  --data '{"id_list":["ou_xxx","ou_yyy"]}' \
  --params '{"member_id_type":"open_id"}'

场景 2：用户需要设置群公告

# Step 1: 确认 CLI 没有封装
lark-cli im --help
# → 没有 announcement 相关命令

# Step 2-4: 挖掘文档
# → PATCH /open-apis/im/v1/chats/:chat_id/announcement

# Step 5: 调用
lark-cli api PATCH /open-apis/im/v1/chats/oc_xxx/announcement \
  --data '{"revision":"0","requests":["<html>公告内容</html>"]}'

参考

lark-shared — 认证和全局参数
lark-skill-maker — 如需将挖掘到的 API 固化为新 Skill

Related skills

More from larksuite/cli and the wider catalog.

lark-doc

larksuite/cli

Read and edit Lark/Feishu Docx & Wiki documents via CLI — fetch, create, update, and manage media attachments.

293k installs

lark-base

larksuite/cli

Manage Lark Base (multi-dimensional tables): create tables, fields, records, views, formulas, forms, dashboards, workflows, and roles.

292k installs

lark-im

larksuite/cli

Lark/Feishu IM skill: send messages, manage group chats, download files, and handle interactive cards via lark-cli

292k installs

lark-drive

larksuite/cli

Manage Lark/Feishu Drive files and folders: upload, download, import, organize, comment, and control permissions.

292k installsAudited

lark-shared

larksuite/cli

Manage Lark CLI auth, identity, permissions, and scopes for coding agents like Claude Code and Cursor

291k installsAudited

lark-calendar

larksuite/cli

Manage Lark calendar events and meeting rooms: view, create, update events, check availability, and book rooms.

291k installsAudited