lark-doc

Read, create, and edit Feishu Docx and Wiki documents via lark-cli.

Updated May 28, 2026
One-click install
npx skills add https://github.com/changfengpro/agent-skills --skill lark-doc-changfengpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-doc
Source: https://github.com/changfengpro/agent-skills/tree/main/skills/lark-doc
Command: npx skills add https://github.com/changfengpro/agent-skills --skill lark-doc-changfengpro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Working with Feishu (Lark) cloud documents programmatically requires navigating complex APIs for reading, authoring, editing, and managing embedded resources like images, whiteboards, and mindnotes. This Skill provides a structured, scenario-routed workflow for all Docx and Wiki content operations through the lark-cli command line. ## Core Features & Use Cases - Document Reading & Authoring: Fetch full or partial document content (by outline, section, range, or keyword), and create new documents from XML or Markdown with a guided multi-step authoring workflow including genre contracts and presentation decisions. - Precise Editing: Update documents with block-level commands (str_replace, block_replace, block_insert_after, block_delete, block_move_after) plus history version listing and rollback. - Media & Resource Management: Insert local or clipboard images, preview and download embedded assets, manage Docx cover images, create whiteboards from Mermaid/SVG, and operate mindnote nodes. - Use Case: A user provides a Feishu doc URL and asks to summarize a section, rewrite a paragraph, insert an architecture diagram as a whiteboard, and download an embedded attachment—all handled through routed reference guides. ## Quick Start Read the Feishu document at this URL and summarize its main sections, then insert a comparison table at the end.

Frequently Asked Questions about lark-doc

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I read a Feishu document from a URL?

Use lark-cli docs +fetch with the document URL or token. It supports /docx/ and /wiki/ links, and you can narrow the read with --scope outline, section, range, or keyword to fetch only the part you need.

How do I edit a specific part of a Feishu Docx document?

First fetch the target area with --detail with-ids to get block IDs, then run docs +update with commands like str_replace, block_replace, block_insert_after, or block_delete. Always re-fetch after writing since block IDs change.

Can I insert images into a Feishu document from my clipboard?

Yes, docs +media-insert supports --from-clipboard on macOS and Windows natively, and on Linux with xclip, wl-paste, or xsel. If the clipboard has no image, provide a local file path with --file instead.

Does this skill handle Feishu spreadsheets or Bitable data?

No. Sheet and Bitable content embedded in documents is routed to the lark-sheets and lark-base skills respectively. Document comments and Drive file operations like copy, import, and permissions belong to lark-drive.

How do I roll back a Feishu document to a previous version?

Use docs +history-list to find the target history_version_id, then docs +history-revert with that ID, and poll docs +history-revert-status until done. If no record matches, you can fetch the target revision and overwrite once with verification.

What content format should I use when creating Feishu documents?

XML is the default and recommended format for semantic authoring, supporting tables, whiteboards, callouts, and extended blocks. Markdown is only used when explicitly requested or for faithful Markdown import, with required character escaping rules.