lark-doc

Create, read, and edit Feishu cloud documents via the lark-cli v2 API.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/sliec/shared-files --skill lark-doc-sliec
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-doc
Source: https://github.com/sliec/shared-files/tree/main/skills/lark-doc
Command: npx skills add https://github.com/sliec/shared-files --skill lark-doc-sliec

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lark-cli, and includes references (resource) components.

What problem does it solve? Working with Feishu (Lark) cloud documents programmatically requires handling authentication, block-level document structure, XML/Markdown formatting rules, and embedded resources like whiteboards, sheets, and media. This Skill provides a complete operational guide for creating, fetching, updating, and enriching Feishu documents through lark-cli commands without manually learning the API surface. ## Core Features & Use Cases - Document CRUD via Shortcuts: Create documents from XML or Markdown, fetch content with scoped reads (outline, section, range, keyword), and apply precise updates (str_replace, block_insert_after, block_replace, block_delete, block_move_after). - Rich Block Authoring: Compose documents with callouts, grids, tables, checkboxes, code blocks, LaTeX, buttons, and embedded whiteboards following a built-in style guide with richness checks. - Media & Whiteboard Handling: Insert images from clipboard or file, preview and download document media, and orchestrate Mermaid/SVG whiteboard diagrams through SubAgents. - Use Case: Given a Feishu document URL, fetch only the relevant section by keyword, rewrite it with structured blocks, insert an architecture diagram as an SVG whiteboard, and append a summary callout. ## Quick Start Ask the AI to read the Feishu document at a given URL and summarize its content, or to create a new Feishu document from an outline you provide.

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 the command line?

Use lark-cli docs +fetch --api-version v2 --doc with the document URL or token. You can limit the read scope with --scope outline, section, range, or keyword to avoid fetching the entire document.

How do I edit a specific paragraph in a Feishu doc?

First fetch the document with --detail with-ids to get block IDs, then run docs +update with commands like block_replace, block_insert_after, or block_delete targeting the block ID. For simple text changes, str_replace works without block IDs.

Should I use XML or Markdown format for Feishu documents?

XML is the default and recommended format because it supports rich blocks like callouts, grids, and checkboxes, and gives more control for precise edits. Use Markdown only when the user explicitly provides Markdown content or requests it.

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

Yes, use docs +media-insert --from-clipboard to insert a clipboard image directly without saving it to disk. This works on macOS and Windows natively; Linux requires xclip, wl-paste, or xsel.

How do I add a diagram or whiteboard to a Feishu document?

Insert a whiteboard block with type mermaid for flowcharts, sequence diagrams, pie charts, and similar, or type svg with a complete self-contained SVG for custom diagrams. Editing an existing whiteboard requires the lark-whiteboard skill.

Why does docs +fetch not show embedded spreadsheet data?

Embedded sheets and bitables appear only as tags with tokens in the fetched content. Extract the token and switch to the lark-sheets or lark-base skill to read the internal data of those embedded resources.