docx-reader

Extract text, tables, images, metadata, and tracked changes from Word documents.

4|10|Updated Feb 20, 2026
One-click install
npx skills add https://github.com/Stratio/genai-agents --skill docx-reader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docx-reader
Source: https://github.com/Stratio/genai-agents/tree/main/shared-skills/docx-reader
Command: npx skills add https://github.com/Stratio/genai-agents --skill docx-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Ingest and extract content from Word documents to obtain prose, tables, images, metadata, comments, and tracked changes, enabling faster content analysis, indexing, and governance of documentation.

Core Features & Use Cases

  • Two-mode extraction: quick mode for fast, one-shot outputs with a deterministic fallback to a thorough deep mode when needed.
  • Rich content extraction: text, tables, images, core metadata, and surfaced tracked changes or comments when present.
  • Legacy support: converts older binary .doc files to modern .docx for reliable parsing.
  • Markdown output: produces Markdown-ready results suitable for feeding LLMs and downstream pipelines.
  • Use case: ingest policy documents or contracts into governance workflows with structured outputs.

Quick Start

Run the quick_extract.py script on a DOCX document to obtain a Markdown-formatted summary.

Frequently Asked Questions about docx-reader

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

FAQPage Schema
How do I extract text and tables from Word documents for downstream analysis?

To extract text and tables from Word documents, run a Python script that parses .docx files to return structured Markdown output. This process quickly ingests prose and tabular data into formats suitable for feeding LLMs and downstream pipelines.

Can I extract tracked changes and comments from a docx file?

Yes, you can extract tracked changes and comments from a docx file using deep analysis mode. This mode surfaces revisions and annotations present in the document, making it ideal for parsing heavily edited contracts and governance workflows.

What is the best way to parse legacy .doc files in Python?

The best way to parse legacy .doc files in Python is to convert them to modern .docx format first. This conversion ensures reliable parsing and content extraction using libraries like python-docx and lxml for stable structural analysis.

Does python-docx support extracting images and metadata from Word files?

python-docx supports extracting core metadata and images from Word files when combined with lxml. This combination allows you to retrieve document properties and media alongside text for comprehensive content indexing and analysis.

Why does quick text extraction from Word fail on complex contracts?

Quick text extraction from Word may fail on complex contracts due to heavy tracked changes or nested tables. A deterministic fallback to deep analysis mode thoroughly parses these complex structures to ensure accurate content retrieval.

How do I convert Word document content to Markdown for LLM ingestion?

You can convert Word document content to Markdown for LLM ingestion by running a quick extraction script on the .docx file. This produces Markdown-ready text and tables, bypassing binary formatting issues for clean downstream processing.