How do I install the DOCX skill?

Run npx skillmds@latest add carlheath/docx 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.

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?

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.

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

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

DOCX by carlheath — Agent Skill

Name: DOCX
Author: carlheath

DOCX

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

carlheath 75b127e 4 files · 21.2 KB Updated Sep 17, 2026

File contents

DOCX creation, editing, and analysis

Overview

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

Quick Reference

Task	Approach
Read/analyze content	`pandoc` or unpack for raw XML
Create new document	Use `docx-js` — see references/creating.md
Edit existing document	Unpack → edit XML → repack — see references/editing.md
Raw XML (tracked changes, comments, images)	See references/xml.md

Converting .doc to .docx

Legacy .doc files must be converted before editing:

python scripts/office/soffice.py --headless --convert-to docx document.doc

Reading Content

# Text extraction with tracked changes
pandoc --track-changes=all document.docx -o output.md

# Raw XML access
python scripts/office/unpack.py document.docx unpacked/

Converting to Images

python scripts/office/soffice.py --headless --convert-to pdf document.docx
pdftoppm -jpeg -r 150 document.pdf page

Accepting Tracked Changes

To produce a clean document with all tracked changes accepted (requires LibreOffice):

python scripts/accept_changes.py input.docx output.docx

Detailed references

Implementation details live in references/ (one level deep, loaded only when relevant):

references/creating.md (~340 lines) — Creating new .docx files with docx-js: setup, validation, page size, styles, lists, tables, images, page breaks, hyperlinks, footnotes, tab stops, multi-column layouts, table of contents, headers/footers, critical rules for docx-js.
references/editing.md (~60 lines) — Editing existing documents: the unpack → edit XML → repack workflow, common pitfalls.
references/xml.md (~130 lines) — Raw XML reference: schema compliance, tracked changes, comments, images.

When working on a creating or editing task, read the relevant reference file before generating code.

Dependencies

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

---name: docxdescription: Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.license: Proprietary. LICENSE.txt has complete terms---# DOCX creation, editing, and analysis## OverviewA .docx file is a ZIP archive containing XML files.## Quick Reference| Task | Approach ||------|----------|| Read/analyze content | `pandoc` or unpack for raw XML || Create new document | Use `docx-js` — see [references/creating.md](references/creating.md) || Edit existing document | Unpack → edit XML → repack — see [references/editing.md](references/editing.md) || Raw XML (tracked changes, comments, images) | See [references/xml.md](references/xml.md) |### Converting .doc to .docxLegacy `.doc` files must be converted before editing:```bashpython scripts/office/soffice.py --headless --convert-to docx document.doc```### Reading Content```bash# Text extraction with tracked changespandoc --track-changes=all document.docx -o output.md# Raw XML accesspython scripts/office/unpack.py document.docx unpacked/```### Converting to Images```bashpython scripts/office/soffice.py --headless --convert-to pdf document.docxpdftoppm -jpeg -r 150 document.pdf page```### Accepting Tracked ChangesTo produce a clean document with all tracked changes accepted (requires LibreOffice):```bashpython scripts/accept_changes.py input.docx output.docx```---## Detailed referencesImplementation details live in `references/` (one level deep, loaded only when relevant):- **[references/creating.md](references/creating.md)** (~340 lines) — Creating new .docx files with docx-js: setup, validation, page size, styles, lists, tables, images, page breaks, hyperlinks, footnotes, tab stops, multi-column layouts, table of contents, headers/footers, critical rules for docx-js.- **[references/editing.md](references/editing.md)** (~60 lines) — Editing existing documents: the unpack → edit XML → repack workflow, common pitfalls.- **[references/xml.md](references/xml.md)** (~130 lines) — Raw XML reference: schema compliance, tracked changes, comments, images.When working on a creating or editing task, read the relevant reference file before generating code.---## Dependencies- **pandoc**: Text extraction- **docx**: `npm install -g docx` (new documents)- **LibreOffice**: PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`)- **Poppler**: `pdftoppm` for images

Frequently asked questions