lark-doc

Read, create, and edit Lark Docs documents via the lark-cli v2 API.

Updated May 22, 2026
One-click install
npx skills add https://github.com/CalWade/aigc-creator --skill lark-doc-calwade
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lark-doc
Source: https://github.com/CalWade/aigc-creator/tree/main/.agents/skills/lark-doc
Command: npx skills add https://github.com/CalWade/aigc-creator --skill lark-doc-calwade

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Working with Lark (Feishu) cloud documents programmatically requires handling authentication, block-level document structure, XML/Markdown formatting rules, and embedded resources like whiteboards and spreadsheets. This Skill provides a complete operational guide for reading, creating, and precisely editing Lark Docx and Wiki documents through the lark-cli v2 API. ## Core Features & Use Cases - Document Reading with Scoped Fetching: Fetch full documents or use outline, section, range, and keyword scopes to read only the parts you need, with detail levels from simple text to full block IDs and styles. - Document Creation and Precise Editing: Create documents from XML or Markdown, then apply eight update commands (str_replace, block_insert_after, block_replace, block_delete, block_move_after, and more) for surgical block-level edits. - Media and Whiteboard Handling: Insert images from clipboard or local files, preview and download document media, and embed whiteboards using Mermaid or self-contained SVG. - Use Case: Given a Lark document URL, fetch its outline, rewrite a specific section with richer structured blocks (callouts, tables, grids), and insert an architecture diagram as a whiteboard, all through CLI commands. ## Quick Start Ask the AI to fetch the content of a Lark document by providing its docx or wiki URL, making sure lark-cli is installed and you have run lark-cli auth login first.

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 Lark document from the command line?▼

Run lark-cli docs +fetch --api-version v2 --doc followed by the document URL or token. Use --scope outline, section, range, or keyword to read only part of a document, and --detail with-ids to get block IDs for later editing.

How do I edit a specific section of a Lark doc without rewriting everything?▼

First fetch the document with --detail with-ids to locate the target block ID, then use docs +update with commands like block_replace, block_insert_after, or str_replace. This performs precise block-level edits instead of a full overwrite.

Should I use XML or Markdown format when creating Lark documents?▼

XML is the default and preferred format because it supports rich blocks like callouts, grids, and checkboxes. Use Markdown only when the user explicitly requests it or provides a .md file to import.

Can this skill handle spreadsheets or bitables embedded in a document?▼

No. When a fetched document contains embedded sheet or bitable tags, extract the token and switch to the lark-sheets or lark-base skill for operations inside those objects. Document comments are handled by lark-drive.

How do I insert an image into a Lark document?▼

Use lark-cli docs +media-insert with --from-clipboard for images already on the system clipboard, or --file with a local path. You can also insert network images directly via docs +update with an img tag containing an href URL.

Why does docs +create or +update fail without --api-version v2?▼

This skill uses the v2 API exclusively, so the --api-version v2 flag is mandatory on docs +create, +fetch, and +update commands. Omitting it targets the wrong API version and causes errors.