docx

Create and edit DOCX documents programmatically using the docx library.

9|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/Research-Equality/ResearchClaw --skill docx-research-equality
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docx
Source: https://github.com/Research-Equality/ResearchClaw/tree/main/src/researchclaw/agents/skills/docx
Command: npx skills add https://github.com/Research-Equality/ResearchClaw --skill docx-research-equality

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Researchers spend excessive time creating, formatting, and updating Word documents for papers, proposals, and reports. This Skill streamlines DOCX workflows, reducing manual repetitive formatting and enabling consistent styling across documents.

Core Features & Use Cases

  • Create new DOCX documents programmatically using docx libraries and templates (headers, footers, styles).
  • Read, edit, and update existing .docx files including text, tables, images, and metadata.
  • Convert legacy formats (e.g., .doc to .docx) and export PDFs where needed, with support for tracked changes and styling.
  • Quick scenario: generate a literature-review draft by assembling sections from templates and inserting figures and tables.

Quick Start

Create a new DOCX document from a template and add a title, abstract, and author metadata.

Frequently Asked Questions about docx

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

FAQPage Schema
How do I automate DOCX creation for research papers using templates?

Automate DOCX creation programmatically using the docx library to apply consistent headers, footers, and styles from templates. This streamlines paper drafting by assembling sections, inserting tables and figures, and generating literature-review drafts without manual formatting.

Can I read and edit existing .docx files programmatically?

Yes, you can read, edit, and update existing .docx files programmatically. The Skill modifies text, tables, images, and document metadata directly, maintaining tracked changes and styling to update research proposals and reports efficiently.

What is the best way to convert legacy .doc files to .docx format?

The best way to convert legacy .doc files to .docx format is using LibreOffice soffice for local conversions. This approach supports tracked changes and styling while also enabling PDF exports where needed for research documentation workflows.

Does this DOCX automation approach work with local environments and no external dependencies?

Yes, this DOCX automation works entirely within local environments. It uses the docx package, LibreOffice soffice for conversions, and pandoc for extraction, requiring no external dependencies to implement document creation, formatting, and conversion features.

How do I extract text and content from existing DOCX documents?

Extract text and content from existing DOCX documents using pandoc for local extraction. This allows you to pull structured content from research papers and reports, enabling further programmatic editing or format conversion within your document automation workflow.

What are the limitations of using docx-js for research document automation?

Using docx-js for research document automation requires local tooling like LibreOffice soffice and pandoc for conversions and extraction. It is designed for local environments where templates and styling must be applied consistently, limiting its use in cloud-native or serverless deployments.