Docx

This is a serious toolkit for programmatic Word document manipulation. It gives Claude three different workflows depending on what you're doing: pandoc for quick text extraction, docx-js for creating new documents from scratch, and a Python OOXML library for editing existing files. The real value is in the redlining workflow, which lets you implement tracked changes properly by working at the XML level. If you're dealing with legal contracts, academic papers, or any document where you need professional change tracking instead of just overwriting content, this handles the messy OOXML details. The documentation emphasizes precision, like only marking text that actually changed rather than replacing entire sentences, which matters when humans review your edits.

GitHub stars: 6K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add thinkinaixyz/deepchat --skill docx --agent claude-code

Installs into .claude/skills of the current project.

Files

DOCX creation, editing, and analysis

Overview

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Workflow Decision Tree

Reading/Analyzing Content

Use "Text extraction" or "Raw XML access" sections below

Creating New Document

Use "Creating a new Word document" workflow

Editing Existing Document

Your own document + simple changes Use "Basic OOXML editing" workflow
Someone else's document Use "Redlining workflow" (recommended default)
Legal, academic, business, or government docs Use "Redlining workflow" (required)

Reading and analyzing content

Text extraction

If you just need to read the text contents of a document, you should convert the document to markdown using pandoc. Pandoc provides excellent support for preserving document structure and can show tracked changes:

SKILL.md on GitHub