docx Agent Skills - Data & Analytics

🎯 What is DOCX?

DOCX skill enables comprehensive handling of Microsoft Word documents (.docx) including creation, editing, analyzing, and managing tracked changes and comments. It’s designed for professional document workflows requiring precision and structure.

⚡ Key Features

• Create new .docx files via JavaScript/TypeScript
• Edit existing documents with Python OOXML libraries
• Support tracked changes and comments for collaborative editing
• Extract text and raw XML for deep analysis
• Convert DOCX to markdown or images for review

🛠️ Tech Stack

• docx-js (JavaScript/TypeScript) for document creation
• Python Document library for OOXML editing
• Pandoc for text extraction and markdown conversion
• LibreOffice & Poppler-utils for DOCX to PDF/image conversion

📋 Installation

Install dependencies: pandoc, docx (npm), LibreOffice, poppler-utils, defusedxml (Python)

⚠️ Important Notes

• Thoroughly read provided `docx-js.md` & `ooxml.md` guides before usage
• Use batching strategy for tracked changes to maintain accuracy
• Preserve original XML structure and RSID tags when editing

❓ Common Issues

• Incorrect batching of changes can cause errors
• Changing entire sentences unnecessarily affects review clarity
• XML line numbers shift after edits; always verify before scripting