docx

Extract, create, and edit Word .docx files via OOXML manipulation.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Euraxluo/skill-manager --skill docx-euraxluo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docx
Source: https://github.com/Euraxluo/skill-manager/tree/main/library/docx
Command: npx skills add https://github.com/Euraxluo/skill-manager --skill docx-euraxluo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defusedxml, and includes scripts (resource) components.

What problem does it solve?

Working with .docx files programmatically is notoriously difficult due to the complex OOXML specification. This Skill eliminates the need to manually parse ZIP archives, edit XML, and manage document relationships by providing high-level workflows for text extraction, document creation, and tracked changes.

Core Features & Use Cases

  • Text Extraction & Analysis: Convert .docx files to markdown using pandoc while preserving tracked changes, or unpack documents to access raw XML for comments, formatting, and embedded media.
  • Document Creation: Generate professional .docx files from scratch using docx-js with proper styling, tables, lists, and page layout.
  • Tracked Changes & Redlining: Implement comprehensive document review workflows with tracked changes, comments, and formatting preservation using the Document library for Python.
  • Use Case: A legal team needs to review a contract, mark up revisions with tracked changes, add comments, and export a clean version. This Skill handles the entire OOXML manipulation pipeline.

Quick Start

Use the docx skill to extract all text from the attached file 'contract.docx' and convert it to markdown for review.

Frequently Asked Questions about docx

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

FAQPage Schema
How do I programmatically extract text and track changes from a .docx file?

Extract text and tracked changes from a .docx file by converting it to markdown using pandoc, or unpack the document to parse raw OOXML for comments, formatting, and embedded media.

What is the best way to automate legal document review with tracked changes and comments?

Automate legal document review by manipulating OOXML to manage revision history, apply tracked changes, insert comments, and preserve formatting without manual intervention using the Document Python library.

Can I generate a Word document from scratch with tables and lists using docx-js?

Generate professional .docx files from scratch using docx-js, applying proper styling, tables, lists, and page layout directly through high-level workflows.

Does this approach require manually parsing ZIP archives to edit Word documents?

Editing Word documents does not require manually parsing ZIP archives, as this approach eliminates manual XML editing and document relationship management by providing high-level OOXML manipulation workflows.

Why is working with .docx files programmatically considered difficult?

Working with .docx files programmatically is difficult due to the complex OOXML specification, which requires unpacking ZIP archives and managing XML relationships to manipulate document content.

Do I need pandoc to convert .docx files to markdown for analysis?

You need pandoc to convert .docx files to markdown for analysis, specifically to preserve tracked changes and extract text efficiently during the conversion process.