Read, create, merge, split, and modify PDF files using Python libraries and command-line tools.
Design & media
docx
Try itProgrammatically create, edit, and validate Word documents with correct formatting and tracked changes.
What it does
Creates, reads, and edits .docx and .dotx files using docx-js for generation and direct XML manipulation for modifications. Includes automated validation via XSD checks and visual verification through PDF rendering to ensure structural integrity. Handles complex formatting like tables of contents, tracked changes, comments, and image insertion while managing Word-specific XML constraints.
When to use it
- Generating formatted reports with TOCs and custom heading styles
- Redlining contracts with validated tracked changes
- Extracting or reorganizing content from legacy .doc files
- Batch-inserting images or performing find-and-replace in templates
The skill document
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 | unpack → 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
columnWidthson the table ANDwidthon every cell, both inWidthType.DXA(PERCENTAGE breaks in Google Docs). Column widths must sum to the table width. - Table shading: use
ShadingType.CLEAR, neverSOLID(renders black). - Lists: never insert
•literally; use anumberingconfig withLevelFormat.BULLET. ImageRunrequirestype:("png","jpg", …).PageBreakmust be inside aParagraph.- Never use
\n— use separateParagraphelements. - Headings: style every level you use (
title,heading1,heading2…) instyles.default:heading1: { run: { font: "Arial", size: 32, bold: true }, paragraph: { spacing: { before: 240, after: 120 }, keepNext: true } }. Every level needs its own font (even with a document default),beforeandafter(even if 0) andkeepNext: the built-in styles set none of them. - TOC: headings must use built-in
HeadingLevel.*; custom heading styles needoutlineLevelset 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 aTextRun, not literal.or space padding.
Verify the output
After writing a .docx, render it and look at it:
zip -d output.docx '*/' >/dev/null || true # drop the ZIP's folder entries: Word has refused a file that has them when opened through a cloud co-editing service
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.
python3 -c "import sys,zipfile; zipfile.ZipFile(sys.argv[1]).extractall('unpacked')" doc.docx # not unzip, which restores symlinks — 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 -XrDy ../out.docx .)
python scripts/office/validate.py out.docx --original doc.docx # XSD checks; --auto-repair fixes common issues
# redlining? add --author "" to check every edit is tracked
Word splits text across many `` 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 "" (needs --original) — it reports any text you changed without a / around it, which is easy to do by accident and invisible in the accepted view. Wrap runs in / with w:id, w:author, w:date attributes. Inside , the text element is , not . A deleted paragraph mark () means "merge this paragraph into the next" — so deleting a paragraph outright is that plus a around every run. The 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=acceptnever 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 //`` 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)
Questions people ask
- How does this handle editing existing Word documents versus creating new ones?
- Existing files are unpacked as ZIP archives to edit word/document.xml directly, since docx-js cannot open them. Adjacent text runs are merged before editing to ensure content is contiguous and findable in the XML.
- How is document correctness verified after generation or editing?
- The workflow converts the output to PDF and renders page images for visual inspection. It also runs XSD validation against the original file to catch schema violations and optionally auto-repair common issues.
- Can I add comments or tracked changes programmatically?
- A helper script manages the six required cross-linked XML files and generates the anchor snippets for document.xml. Comment IDs are auto-assigned, and markers must be placed in the document body for comments to be visible.
Related skills
chatgpt-apps
OfficialGenerates docs-aligned ChatGPT Apps SDK scaffolds combining MCP servers and widget UIs.
figma-generate-design
OfficialBuilds or updates full Figma screens using published design system components, variables, and styles instead of hardcoded primitives.
figma-generate-library
OfficialOrchestrates multi-phase Figma design system builds from codebases with mandatory validation checkpoints.
hatch-pet
OfficialGenerates Codex-compatible animated pet spritesheets and packaging from concepts, brand cues, or reference images.
winui-app
OfficialBootstraps, develops, and verifies WinUI 3 desktop apps using official Microsoft guidance and Windows App SDK patterns.
More from Anthropic
Browse all skillsdoc-coauthoring
OfficialStructured three-stage workflow for co-authoring documentation with context gathering, iterative drafting, and reader testing.
Read, create, merge, split, and modify PDF files using Python libraries and command-line tools.
pptx
OfficialCreate, edit, read, and validate .pptx and .potx files programmatically with built-in safety checks.
xlsx
OfficialCreate, edit, and analyze Excel and CSV files with verified formulas and professional formatting.
algorithmic-art
OfficialGenerates original p5.js algorithmic art with seeded randomness and interactive parameter controls from a custom computational philosophy.
skill-creator
OfficialCreate, test, and iteratively improve agent skills with built-in evaluation workflows.