Site audit, content writing, and competitor analysis for organic search rankings.
Design & media
docx
Try itCreate, edit, read, and redline .docx and .dotx files with scripts and XML-level edits.
What it does
Handles Word documents three ways: generating new files with a docx (npm) script, editing existing ones by unpacking the ZIP, changing word/document.xml, and rezipping, and reading content via pandoc to markdown. It also covers tracked changes, comments, and verification by converting the result to PDF and rendering page images. Bundled helper scripts merge fragmented runs, validate against the XSD, accept tracked changes, and add comment files.
When to use it
- Generating a formatted report with headings, tables, a table of contents, and page numbers
- Redlining a contract so every edit is tracked with author and date
- Adding review comments anchored to specific text in a document
- Extracting and reorganizing content from an existing .docx or .dotx file
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
- Can it edit a document I already have, or only create new ones?
- Both, but through different paths. docx-js cannot open existing files, so edits go through unpacking the archive, editing word/document.xml in place, and rezipping. Legacy .doc files are converted to .docx first with the bundled LibreOffice script.
- How do I check the output actually looks right?
- The skill converts the .docx to PDF with headless LibreOffice, renders pages to JPEG with pdftoppm, and then you read the images. It also ships a validate.py that runs XSD checks and can auto-repair common issues.
- Does it support tracked changes and comments?
- Yes. Redlining uses w:ins and w:del runs with author and date attributes, and validate.py with --author "" flags any edit that was not tracked. Comments need six cross-linked XML files, which the comment.py helper writes for you, then you place the anchor markers it prints.
Related skills
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Read, extract, merge, split, rotate, watermark, encrypt, and create PDF files with Python and CLI recipes.
chatgpt-apps
OfficialScaffold and refactor ChatGPT Apps SDK projects that pair an MCP server with a widget UI, grounded in current OpenAI docs.
figma-generate-design
OfficialBuild or update full Figma screens using your published design system's components, variables, and styles instead of hardcoded values.
figma-generate-library
OfficialTurns a codebase into a Figma design system through phased, checkpointed build steps.
More from Anthropic
Browse all skillsdoc-coauthoring
OfficialTurns a rough idea into a finished doc through three guided stages: context gathering, section-by-section drafting, and reader testing.
Read, extract, merge, split, rotate, watermark, encrypt, and create PDF files with Python and CLI recipes.
pptx
OfficialCreate, edit, and read .pptx and .potx decks with pptxgenjs scripts, XML unpacking, and validation.
xlsx
OfficialCreate, edit, and verify Excel workbooks with real formulas, correct formatting, and zero formula errors.
algorithmic-art
OfficialTurn a short art request into a written generative-art philosophy plus a runnable p5.js sketch with seed and parameter controls.
skill-creator
OfficialDraft a new agent skill, test it against real prompts, and iterate on it using qualitative and quantitative eval results.