What problem does it solve? Working with Lark (Feishu) cloud documents programmatically requires navigating complex APIs for reading, creating, and precisely editing document content. This Skill wraps those operations into lark-cli docs shortcuts so an AI agent can fetch, create, update, and manage Docx/Wiki documents directly from a URL or token. ## Core Features & Use Cases - Document Fetching: Read full documents or targeted sections using scope modes (outline, section, range, keyword) with selectable detail levels (simple, with-ids, full) in XML or Markdown. - Creation & Precise Editing: Create documents from XML/Markdown and apply eight update commands (str_replace, block_insert_after, block_replace, block_delete, block_move_after, and more) with block-ID lifecycle guidance. - Media & Resources: Insert images from clipboard or file, preview/download media and whiteboard thumbnails, manage Docx cover images, roll back to history versions, and count words with a dedicated statistics script. - Use Case: Given a Feishu doc URL, fetch its outline, rewrite one section with block-level edits, insert a Mermaid whiteboard diagram, and verify the final word count. ## Quick Start Ask the agent to fetch the content of a Feishu document by pasting its docx or wiki URL, then request edits such as replacing specific text or appending a new section.
