lark-doc

Routes Lark online Docx/Wiki and local Word/PDF document tasks to specialized processing modules.

2|Updated Aug 9, 2026
One-click install
npx skills add https://github.com/DeepJH/doubao-skill-and-info --skill lark-doc-deepjh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-doc
Source: https://github.com/DeepJH/doubao-skill-and-info/tree/main/skills/lark-doc
Command: npx skills add https://github.com/DeepJH/doubao-skill-and-info --skill lark-doc-deepjh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python-docx, pdfplumber, and includes scripts (resource) and references (resource) components.

What problem does it solve? Handling document tasks across Lark online documents and local Word/PDF files requires different tools and workflows; this Skill acts as a unified entry point that routes each request to the correct module, eliminating guesswork about which commands, scripts, or references to use. ## Core Features & Use Cases - Online Document Operations: Read, create, edit, and summarize Lark Docx/Wiki documents via lark-cli shortcuts like docs +fetch, docs +create, and docs +update, with precise block-level editing and media handling. - Local Word/PDF Processing: Extract text from .docx/.doc/.pdf files, perform format-preserving text replacement in Word documents, and generate standard-layout .docx files from JSON content. - Specialized Sub-Skills: Route to resume writing, patent drafting, visa document filling, and official document generation modules when tasks match those domains. - Use Case: A user pastes a Lark Wiki URL asking to update a section, or uploads a local proposal.docx requesting reformatting—the Skill detects the resource type and delegates to the correct module automatically. ## Quick Start Ask the assistant to read a Lark document URL or edit a local Word file, and it will route the request to the appropriate module.

Frequently Asked Questions about lark-doc

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

FAQPage Schema
How do I edit a Lark online document with lark-cli?

Use lark-cli docs +update with commands like str_replace for direct text replacement or block_insert_after for block-level edits. Fetch the document first with docs +fetch to locate content, and use XML format for precise local edits.

How to replace text in a Word document without losing formatting?

Use the docx_edit.py replace command with a replacements.json file listing find/replace pairs. It modifies only the text inside w:t elements while preserving all w:rPr formatting properties, and optionally supports tracked changes.

Can this skill extract text from PDF files?

Yes, extract_pdf.py uses pdfplumber to pull text from PDFs, including two-column layout detection and table extraction. The extract_text.py script also handles PDF via pdftotext or pandoc, plus .docx, .doc, .txt, .md, and .html formats.

When are tasks routed away from this document skill?

Spreadsheet and Excel operations go to lark-sheets, Bitable data operations go to lark-base, and slide or PowerPoint tasks go to lark-slides. Document comments, file uploads, and permission management are handled by lark-drive.

How do I count words in a Lark document?

Use the doc_word_stat.py script, which parses the document's XML or Markdown content and counts Han characters, English words, numbers, and punctuation according to a defined statistical standard.