Feishu Fetch Doc

Pulls Markdown content from Feishu (Lark) cloud documents via their API. The main thing to know is that images, files, and whiteboards come back as HTML tokens in the Markdown, not actual content, so you'll need to call a separate feishu_doc_media tool to download those assets. It handles both direct document URLs and wiki links, though wiki links require an extra step to figure out what type of document you're actually dealing with since they could point to spreadsheets or databases instead of docs. Straightforward if you're building Feishu integrations and need to extract document text programmatically.

skills.sh installs: 229
GitHub stars: 2.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add larksuite/openclaw-lark --skill feishu-fetch-doc --agent claude-code

Installs into .claude/skills of the current project.

Files

feishu_mcp_fetch_doc

获取飞书云文档的 Markdown 内容（Lark-flavored 格式）。

重要：图片、文件、画板的处理

文档中的图片、文件、画板需要通过 feishu_doc_media（action: download）工具单独获取！

识别格式

返回的 Markdown 中，媒体文件以 HTML 标签形式出现：

图片：

<image token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc" width="1833" height="2491" align="center"/>

文件：

<view type="1">
  <file token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc" name="skills.zip"/>
</view>

画板：

<whiteboard token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc"/>

获取步骤

从 HTML 标签中提取 token 属性值

调用 feishu_doc_media 下载：

{
  "action": "download",
  "resource_token": "提取的token",
  "resource_type": "media",
  "output_path": "/path/to/save/file"
}

参数

doc_id（必填）：支持直接传文档 URL 或 token
- 直接传 URL：https://xxx.feishu.cn/docx/Z1FjxxxxxxxxxxxxxxxxxxxtnAc（系统自动提取 token）
- 直接传 token：Z1FjxxxxxxxxxxxxxxxxxxxtnAc
- 知识库 URL/token 也支持：https://xxx.feishu.cn/wiki/Z1FjxxxxxxxxxxxxxxxxxxxtnAc 或 Z1FjxxxxxxxxxxxxxxxxxxxtnAc