What software dependencies are required?

This skill requires Pandoc for text extraction, LibreOffice for PDF conversion, and Poppler-utils for image generation, along with Python and Node.js environments.

Can I create new documents from scratch?

Yes, the skill utilizes the docx-js library, enabling you to generate sophisticated Word documents with paragraphs, tables, and styling using JavaScript or TypeScript.

Is it suitable for legal or academic documents?

Absolutely. It is specifically designed for high-stakes editing in legal, academic, and government sectors where preserving document integrity and tracking every edit is mandatory.

Does it support reading images or complex formatting?

Yes, by unpacking the .docx ZIP archive, Claude can access raw XML files, comments, and the media directory to analyze embedded images and document structure.

How does this skill handle tracked changes?

It uses a professional redlining workflow that unpacks the OOXML structure and applies precise XML tags for insertions and deletions, ensuring changes appear as native tracked changes in Microsoft Word.

DOCX Management & Redlining

Name: DOCX Management & Redlining
Author: dev-jelly

bydev-jelly

生产力与工作流

Automates professional Microsoft Word document creation, editing, and redlining with precise tracked changes and XML-level control.

关于

This skill empowers Claude to interact deeply with .docx files, moving beyond simple text extraction to full-scale document engineering. It supports professional workflows such as legal redlining, where tracked changes are implemented with XML precision to preserve metadata and formatting. Whether you need to generate complex reports from scratch using JavaScript, batch-edit existing business documents, or perform visual analysis by converting pages to images, this skill provides the tools and structured workflows required for high-stakes document management.

主要功能

Deep XML analysis for comments, metadata, and complex formatting
High-fidelity text extraction and document-to-markdown conversion via Pandoc
Precision redlining with systematic tracked changes and RSID preservation
Programmable document creation via the docx-js library integration
Visual document inspection through automated DOCX-to-PDF-to-Image pipelines
0 GitHub stars

使用场景

Generating dynamic business reports or invoices from data using script-based templates
Auditing document metadata, comments, and internal structure for compliance or data extraction
Automating legal document reviews and applying tracked changes across complex contracts

关于

主要功能

Deep XML analysis for comments, metadata, and complex formatting
High-fidelity text extraction and document-to-markdown conversion via Pandoc
Precision redlining with systematic tracked changes and RSID preservation
Programmable document creation via the docx-js library integration
Visual document inspection through automated DOCX-to-PDF-to-Image pipelines
0 GitHub stars

使用场景

Generating dynamic business reports or invoices from data using script-based templates
Auditing document metadata, comments, and internal structure for compliance or data extraction
Automating legal document reviews and applying tracked changes across complex contracts