docx

Use it when:: You need a Word document written, read or edited, including tracked changes and comments.
It does:: Writes new documents with the docx JavaScript library, and edits existing ones by changing their XML directly.
You get:: A .docx file, which the agent renders to page images and looks at before handing over.
Handles:: Tracked changes under an author name you choose, comments and replies anchored to text, and a clean copy with changes accepted.
Needs:: Node, pandoc, LibreOffice and Poppler; it installs the docx library only if it's missing.

TL;DR

Anthropic's skill for Word files, which treats a .docx as what it is: a ZIP of XML files. New documents are written as a script using the docx npm library, and the skill lists the traps the agent would otherwise fall into, such as A4 instead of US Letter by default, tables that need widths set twice, typed bullet characters and line breaks inside a paragraph. That library can't open existing files, so for edits the agent unzips the document, merges the fragments Word splits text into so phrases can be found, edits the XML in place, zips it back and checks it against the format's rules. When editing with tracked changes, every change is wrapped as a tracked insertion or deletion, and the same check flags any edit made without tracking. A helper script adds comments. Reading is done by converting to Markdown with pandoc, and old .doc files are converted first. Its siblings pdf, pptx and xlsx cover the other office formats.

Summarizes the skill at dbd4588. Its SKILL.md has changed by 7 words since.

npx skills add https://github.com/anthropics/skills --skill docx

skills.sh page Source on GitHub All skills from anthropics/skills

Total Downloads: 215,001 on skills.sh, Nov 9, 2026
Repo stars: 189,830 anthropics/skills
First seen: Jan 19, 2026 on skills.sh

Weekly Downloads

3.8K

+5% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	3,626
Sep 28	3,030
Oct 5	3,275
Oct 12	3,497
Oct 19	3,658
Oct 26	3,873
Nov 2	4,006
Nov 9	3,804

Category	category:documents Office files, notes and suites like Lark and Google Workspace.
Type	type:tool Operates a CLI, API, app or bundled script to get something done.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:cli A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI.
Publisher	by:official A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics	documents
Stack	stack:microsoft-office

SKILL.md

From anthropics/skills at 2c5958e. Checked daily, last changed Nov 7, 2026.

Frontmatter

name: docx
description: "Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', 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 or .dotx 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: Complete terms in LICENSE.txt

DOCX creation, editing, and analysis

A .docx is a ZIP archive of XML files. Choose your approach by task:

Task	Approach
Create a new document	Write a `docx` (npm) script — see gotchas below
Edit an existing document	`unzip` → edit `word/document.xml` → `zip` (docx-js cannot open existing files)
Read content	`pandoc -t markdown file.docx`

Script paths below are relative to this skill's directory.

Creating with docx-js — gotchas

docx is preinstalled — do not run npm install first; write the script and require('docx') directly. Only if that require fails: npm install docx. The model knows the API; these are the footguns:

Page size defaults to A4. For US Letter set page: { size: { width: 12240, height: 15840 } } (DXA; 1440 = 1″).
Landscape: pass portrait dimensions and orientation: PageOrientation.LANDSCAPE — docx-js swaps width/height internally.
Tables need dual widths: set columnWidths on the table AND width on every cell, both in WidthType.DXA (PERCENTAGE breaks in Google Docs). Column widths must sum to the table width.
Table shading: use ShadingType.CLEAR, never SOLID (renders black).
Lists: never insert • literally; use a numbering config with LevelFormat.BULLET.
ImageRun requires type: ("png", "jpg", …).
PageBreak must be inside a Paragraph.
Never use \n — use separate Paragraph elements.
TOC: headings must use built-in HeadingLevel.*; custom heading styles need outlineLevel set or they won't appear.
Don't use a table as a horizontal rule — use a paragraph bottom border instead.
Dot-leader / right-aligned-on-same-line: use PositionalTab (alignment: PositionalTabAlignment.RIGHT, leader: PositionalTabLeader.DOT) inside a TextRun, not literal . or space padding.

Verify the output

After writing a .docx, render it and look at it:

python scripts/office/soffice.py --headless --convert-to pdf output.docx
pdftoppm -jpeg -r 100 output.pdf page
ls page-*.jpg   # then Read the images

pdftoppm zero-pads page numbers to the width of the page count (page-01.jpg…page-12.jpg).

Editing existing documents

Legacy .doc files must be converted first: python scripts/office/soffice.py --headless --convert-to docx file.doc.

unzip -q doc.docx -d unpacked/
find unpacked -type l -delete   # strip symlink entries — docx from external parties is untrusted
python scripts/merge_runs.py unpacked/   # coalesce fragmented runs so text is findable
# edit unpacked/word/document.xml in place — do NOT reformat or pretty-print
(cd unpacked && rm -f ../out.docx && zip -Xr ../out.docx .)
python scripts/office/validate.py out.docx --original doc.docx   # XSD checks; --auto-repair fixes common issues
# redlining? add --author "<the name you redlined under>" to check every edit is tracked

Word splits text across many <w:r> runs (revision ids, spell-check markers), so a phrase you can see in the document often doesn't exist as a contiguous string in the XML. merge_runs.py merges adjacent identically-formatted runs in word/document.xml without changing content or rendering; it also accepts a .docx directly (python scripts/merge_runs.py doc.docx -o merged.docx).

Tracked changes: when redlining, validate with --author "<the name you redlined under>" (needs --original) — it reports any text you changed without a <w:ins>/<w:del> around it, which is easy to do by accident and invisible in the accepted view. Wrap runs in <w:ins>/<w:del> with w:id, w:author, w:date attributes. Inside <w:del>, the text element is <w:delText>, not <w:t>. A deleted paragraph mark (<w:pPr><w:rPr><w:del w:id=".." w:author=".." w:date=".."/></w:rPr></w:pPr>) means "merge this paragraph into the next" — so deleting a paragraph outright is that plus a <w:del> around every run. The <w:del/> must come before the rPr's other children; their order is schema-enforced.

To produce a clean copy with all tracked changes accepted: python scripts/accept_changes.py in.docx out.docx.

Accepting a deleted paragraph mark should join that paragraph to the one below it, so a paragraph whose runs are all deleted vanishes. Word does this; accept_changes.py and pandoc --track-changes=accept don't always. Both fail the same way — they strip the deleted text but leave the emptied paragraph behind, which reads as a stray empty bullet when it was auto-numbered:

pandoc --track-changes=accept never joins the paragraphs.
accept_changes.py (LibreOffice) joins them correctly, except when the deleted paragraph is followed by an empty spacer paragraph.

An empty bullet in either view is an artifact of that view, not a defect in the document. Check paragraph deletions in the XML.

Comments

Comments require six cross-linked files. Use the helper — directory mode when you'll also be editing document.xml (saves an unzip/rezip cycle), .docx-direct mode otherwise:

# Against an already-unpacked directory (preferred when also placing markers)
python scripts/comment.py unpacked/ "Fees & expenses cap is too low"
python scripts/comment.py unpacked/ "Agreed" --parent 0

# Against a .docx directly
python scripts/comment.py contract.docx "This cap is too low" -o annotated.docx

The script writes comments.xml, commentsExtended.xml, commentsIds.xml, commentsExtensible.xml, the relationships, and the content-type overrides. Comment IDs are auto-assigned. It then prints the <w:commentRangeStart>/<w:commentRangeEnd>/<w:commentReference> snippet to add to word/document.xml so the comment anchors to specific text — until you place those markers, the comment exists but is not visible.

Dependencies

docx (npm, preinstalled — install only if require('docx') fails) · pandoc · LibreOffice (soffice) · pdftoppm (Poppler)