How do I install the DOCX Word Processor skill?

Run npx skillmds@latest add shalomb/docx-word-processor in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is DOCX Word Processor safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with DOCX Word Processor?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is DOCX Word Processor free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Proprietary.

Who published DOCX Word Processor?

shalomb (@shalomb) published this skill. Their other Agent Skills are listed on their SkillMD profile.

DOCX Word Processor by shalomb — Agent Skill

Name: DOCX Word Processor
Author: shalomb

DOCX Word Processor

Use this skill whenever you need to create, read, edit, or manipulate Word documents (.docx files). Trigger this on any mention of 'Word doc', 'word document', '.docx', or requests to produce formatted deliverables like reports, memos, or letters. Use this for extracting text, inserting images, tracking changes, or converting content to Word format. Do NOT use for PDFs or spreadsheets.

shalomb b14f0cc 63 files · 1.1 MB Updated Sep 17, 2026

File contents

DOCX creation, editing, and analysis

Overview

A .docx file is a ZIP archive containing XML files.

Task Quick Start

Task	Approach
Analyze content	`pandoc document.docx -o output.md`
Convert .doc	`python scripts/office/soffice.py --convert-to docx document.doc`
Create new doc	Use `docx-js`. See references/creating.md
Edit existing doc	Unpack → edit XML → repack. See references/editing.md
Clean changes	`python scripts/accept_changes.py input.docx output.docx`
Convert to PDF	`python scripts/office/soffice.py --convert-to pdf document.docx`

Reference Materials

To ensure high-quality document manipulation, refer to these detailed guides:

Creating Documents: references/creating.md - Full guide for docx-js (JavaScript).
Editing Documents: references/editing.md - Detailed workflow for unpacking and editing XML directly.
XML Reference: references/editing.md#xml-reference - Patterns for tracked changes, comments, and images.

Critical Rules

For docx-js (Creating)

Set page size explicitly - Defaults to A4; use US Letter (12240 x 15840 DXA) for US documents.
Tables need dual widths - columnWidths array AND cell width, both must match in DXA.
Never use \n or unicode bullets - Use separate Paragraphs and LevelFormat.BULLET.

For XML Editing (Modifying)

Author Identity: Use "Claude" for tracked changes and comments.
Minimal edits - Only mark what actually changes in the XML.
Comment Markers: Siblings of <w:r>, never inside.

Dependencies

pandoc: Text extraction
docx: npm install -g docx (new documents)
LibreOffice: PDF conversion (scripts/office/soffice.py)
Poppler: pdftoppm for images

---name: docx-word-processordescription: Use this skill whenever you need to create, read, edit, or manipulate Word documents (.docx files). Trigger this on any mention of 'Word doc', 'word document', '.docx', or requests to produce formatted deliverables like reports, memos, or letters. Use this for extracting text, inserting images, tracking changes, or converting content to Word format. Do NOT use for PDFs or spreadsheets.license: Proprietary. LICENSE.txt has complete terms---# DOCX creation, editing, and analysis## OverviewA .docx file is a ZIP archive containing XML files.## Task Quick Start| Task | Approach ||------|----------|| **Analyze content** | `pandoc document.docx -o output.md` || **Convert .doc** | `python scripts/office/soffice.py --convert-to docx document.doc` || **Create new doc** | Use `docx-js`. See [references/creating.md](references/creating.md) || **Edit existing doc** | Unpack → edit XML → repack. See [references/editing.md](references/editing.md) || **Clean changes** | `python scripts/accept_changes.py input.docx output.docx` || **Convert to PDF** | `python scripts/office/soffice.py --convert-to pdf document.docx` |## Reference MaterialsTo ensure high-quality document manipulation, refer to these detailed guides:- **Creating Documents**: [references/creating.md](references/creating.md) - Full guide for `docx-js` (JavaScript).- **Editing Documents**: [references/editing.md](references/editing.md) - Detailed workflow for unpacking and editing XML directly.- **XML Reference**: [references/editing.md#xml-reference](references/editing.md#xml-reference) - Patterns for tracked changes, comments, and images.## Critical Rules### For docx-js (Creating)- **Set page size explicitly** - Defaults to A4; use US Letter (12240 x 15840 DXA) for US documents.- **Tables need dual widths** - `columnWidths` array AND cell `width`, both must match in DXA.- **Never use `\n` or unicode bullets** - Use separate Paragraphs and `LevelFormat.BULLET`.### For XML Editing (Modifying)- **Author Identity**: Use "Claude" for tracked changes and comments.- **Minimal edits** - Only mark what actually changes in the XML.- **Comment Markers**: Siblings of `<w:r>`, never inside.## Dependencies- **pandoc**: Text extraction- **docx**: `npm install -g docx` (new documents)- **LibreOffice**: PDF conversion (`scripts/office/soffice.py`)- **Poppler**: `pdftoppm` for images

Frequently asked questions