Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
op7418 avatar

Feishu Fetch Doc

  • 2 installs
  • 6.4k repo stars
  • Updated August 4, 2026
  • op7418/codepilot

Retrieves Feishu cloud document content as Lark-flavored Markdown, resolving wiki token types and downloading embedded images, files, and boards.

About

A tool skill for retrieving Feishu cloud document content as Markdown, including handling wiki links and embedded media. A developer uses it when an agent needs to read an existing Feishu doc's text and attachments.

  • Fetches Feishu doc content as Lark-flavored Markdown from a URL or token
  • Resolves wiki tokens to real object type and downloads embedded images/files/boards

Feishu Fetch Doc by the numbers

  • 2 all-time installs (skills.sh)
  • Ranked #1,839 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/op7418/codepilot --skill feishu-fetch-doc

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2
repo stars6.4k
Last updatedAugust 4, 2026
Repositoryop7418/codepilot

What it does

Retrieves Feishu cloud document content as Lark-flavored Markdown, resolving wiki token types and downloading embedded images, files, and boards.

Files

SKILL.mdMarkdownGitHub ↗

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

1. 从 HTML 标签中提取 token 属性值 2. 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/Z1FjxxxxxxxxxxxxxxxxxxxtnAcZ1FjxxxxxxxxxxxxxxxxxxxtnAc

Wiki URL 处理策略

知识库链接(/wiki/TOKEN)背后可能是云文档、电子表格、多维表格等不同类型的文档。当不确定类型时, 不能直接假设是云文档,必须先查询实际类型。

处理流程

1. 先调用 `feishu_wiki_space_node`(action: get)解析 wiki token

   { "action": "get", "token": "wiki_token_here" }

2. 从返回的 `node` 中获取 `obj_type`(实际文档类型)和 `obj_token`(实际文档 token) 3. 根据 `obj_type` 调用对应工具

obj_type工具传参
docxfeishu_mcp_fetch_docdoc_id = obj_token
sheetfeishu_sheetspreadsheet_token = obj_token
bitablefeishu_bitable_* 系列app_token = obj_token
其他告知用户暂不支持该类型

示例

用户:帮我看下这个文档 https://xxx.feishu.cn/wiki/ABC123

1. 调用 feishu_wiki_space_node(action: get, token: ABC123) 2. 返回 obj_type: "docx", obj_token: "doxcnXYZ789" 3. 调用 feishu_mcp_fetch_doc(doc_id: doxcnXYZ789)

工具组合

需求工具
获取文档文本feishu_mcp_fetch_doc
下载图片/文件/画板feishu_doc_media(action: download)
解析 wiki token 类型feishu_wiki_space_node(action: get)
读写电子表格feishu_sheet
操作多维表格feishu_bitable_* 系列

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.