Generated banner for DOCX
Generated logo for DOCX

DOCX

AnthropicOfficialPublished by Anthropic

  • Skill
  • Tool integration
  • Documents and content
  • Apache-2.0
  • Low risk
  • Has scripts

From the author

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.
— the description by Anthropic

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured approach to working with Word documents by leveraging the docx-js library for creation and XML manipulation for editing. It includes specialized scripts for merging fragmented text runs, managing tracked changes, inserting comments, and validating document structure against XSD schemas. The skill also supports document conversion and visual verification using external tools like LibreOffice and Poppler.

What it does

  • Generates new .docx and .dotx files using the docx-js library.
  • Edits existing documents by manipulating underlying XML structures.
  • Merges fragmented text runs to facilitate accurate find-and-replace operations.
  • Manages tracked changes and redlining with validation support.
  • Inserts and anchors comments into document content.
  • Converts legacy .doc files and validates document integrity.

When to use it

  • When you need to generate professional documents like reports or letters programmatically.
  • When you must perform precise edits on existing Word files that require XML-level access.
  • When you need to automate the insertion of comments or track changes in a document.
  • When you need to convert or validate Word documents for specific formatting requirements.

Advantages

  • Provides programmatic control over complex Word document structures.
  • Includes helper scripts to handle common XML-related issues like fragmented text runs.
  • Supports automated validation of document structure and tracked changes.
  • Enables headless conversion and visual verification of document output.

Usage examples

“Create a new Word document with a table of contents and a custom letterhead.”
The agent uses the docx-js library to construct a document with defined headings and layout elements.
“Edit this contract.docx to add a comment on the payment clause.”
The agent uses the comment.py script to inject the comment and anchor it to the specified text.
“Merge the text runs in this document so I can perform a find-and-replace.”
The agent runs the merge_runs.py script to coalesce fragmented XML runs into contiguous strings.
“Convert this legacy .doc file to .docx and validate it.”
The agent uses soffice to convert the file and then runs the validation script to check for errors.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/anthropics/docx/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip docx.zip -d .agents/skills

Documentation by Anthropic

DOCX creation, editing, and analysis

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

TaskApproach
Create a new documentWrite a docx (npm) script — see gotchas below
Edit an existing documentunzip → edit word/document.xml → zip (docx-js cannot open existing files)
Read contentpandoc -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)

Files

scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd

<?xml version='1.0'?>
<xs:schema targetNamespace="http://www.w3.org/XML/1998/namespace" xmlns:xs="http://www.w3.org/2001/XMLSchema" xml:lang="en">

 <xs:annotation>
  <xs:documentation>
   See http://www.w3.org/XML/1998/namespace.html and
   http://www.w3.org/TR/REC-xml for information about this namespace.

    This schema document describes the XML namespace, in a form
    suitable for import by other schema documents.  

    Note that local names in this namespace are intended to be defined
    only by the World Wide Web Consortium or its subgroups.  The
    following names are currently defined in this namespace and should
    not be used with conflicting semantics by any Working Group,
    specification, or document instance:

    base (as an attribute name): denotes an attribute whose value
         provides a URI to be used as the base for interpreting any
         relative URIs in the scope of the element on which it
         appears; its value is inherited.  This name is reserved
         by virtue of its definition in the XML Base specification.

    lang (as an attribute name): denotes an attribute whose value
         is a language code for the natural language of the content of
         any element; its value is inherited.  This name is reserved
         by virtue of its definition in the XML specification.
  
    space (as an attribute name): denotes an attribute whose
         value is a keyword indicating what whitespace processing
         discipline is intended for the content of the element; its
         value is inherited.  This name is reserved by virtue of its
         definition in the XML specification.

    Father (in any context at all): denotes Jon Bosak, the chair of 
         the original XML Working Group.  This name is reserved by 
         the following decision of the W3C XML Plenary and 
         XML Coordination groups:

             In appreciation for his vision, leadership and dedication
             the W3C XML Plenary on this 10th day of February, 2000
             reserves for Jon Bosak in perpetuity the XML name
             xml:Father
  </xs:documentation>
 </xs:annotation>

 <xs:annotation>
  <xs:documentation>This schema defines attributes and an attribute group
        suitable for use by
        schemas wishing to allow xml:base, xml:lang or xml:space attributes
        on elements they define.

        To enable this, such a schema must import this schema
        for the XML namespace, e.g. as follows:
        &lt;schema . . .>
         . . .
         &lt;import namespace="http://www.w3.org/XML/1998/namespace"
                    schemaLocation="http://www.w3.org/2001/03/xml.xsd"/>

        Subsequently, qualified reference to any of the attributes
        or the group defined below will have the desired effect, e.g.

        &lt;type . . .>
         . . .
         &lt;attributeGroup ref="xml:specialAttrs"/>
 
         will define a type which will schema-validate an instance
         element with any of those attributes</xs:documentation>
 </xs:annotation>

 <xs:annotation>
  <xs:documentation>In keeping with the XML Schema WG's standard versioning
   policy, this schema document will persist at
   http://www.w3.org/2001/03/xml.xsd.
   At the date of issue it can also be found at
   http://www.w3.org/2001/xml.xsd.
   The schema document at that URI may however change in the future,
   in order to remain compatible with the latest version of XML Schema
   itself.  In other words, if the XML Schema namespace changes, the version
   of this document at
   http://www.w3.org/2001/xml.xsd will change
   accordingly; the version at
   http://www.w3.org/2001/03/xml.xsd will not change.
  </xs:documentation>
 </xs:annotation>

 <xs:attribute name="lang" type="xs:language">
  <xs:annotation>
   <xs:documentation>In due course, we should install the relevant ISO 2- and 3-letter
         codes as the enumerated possible values . . .</xs:documentation>
  </xs:annotation>
 </xs:attribute>

 <xs:attribute name="space" default="preserve">
  <xs:simpleType>
   <xs:restriction base="xs:NCName">
    <xs:enumeration value="default"/>
    <xs:enumeration value="preserve"/>
   </xs:restriction>
  </xs:simpleType>
 </xs:attribute>

 <xs:attribute name="base" type="xs:anyURI">
  <xs:annotation>
   <xs:documentation>See http://www.w3.org/TR/xmlbase/ for
                     information about this attribute.</xs:documentation>
  </xs:annotation>
 </xs:attribute>

 <xs:attributeGroup name="specialAttrs">
  <xs:attribute ref="xml:base"/>
  <xs:attribute ref="xml:lang"/>
  <xs:attribute ref="xml:space"/>
 </xs:attributeGroup>

</xs:schema>

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python, Needs Node.js

Security

What our scanner noticed· Low risk

  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Anthropic
Publisher
Anthropic (Official)
Source
anthropics/skills · skills/docx · commit 2c5958e
Licence
Apache License 2.0 (redistribution allowed)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Anthropic or Anthropic.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download docx.zip