feishu-fetch-doc

To convert a Feishu or Lark document to Markdown, provide the document token extracted from docx or wiki URLs. The skill extracts cloud document content and outputs Lark-flavored Markdown suitable for automation and indexing.

Extracting embedded images and files from a Feishu wiki page requires a separate media retrieval step. The Markdown extraction preserves the media tokens for images, files, and whiteboards, which you then fetch individually using those specific tokens.

You need a doc_id token from the Lark cloud document URL to fetch it into Markdown. This token is extracted from standard docx or wiki links to access shared workspace content, knowledge base pages, and other docs.

Feishu Markdown extraction does not directly embed whiteboard content but preserves the whiteboard token. You must use this token separately to retrieve the whiteboard media alongside any images and files embedded in the document.

The best way to get clean text from a shared Feishu doc for summarization is to fetch the document using its doc_id token. This converts the cloud document into Lark-flavored Markdown, making it ready for indexing and analysis.