What problem does it solve?
This Skill streamlines creating, editing, and repairing Microsoft Word (.docx) documents by operating on their underlying OOXML content, so you can produce consistent layouts and apply structured changes without breaking document integrity.
Core Features & Use Cases
- Read, analyze, and repair DOCX content: Unpack DOCX into XML, pretty-print XML, preserve whitespace rules, and support tracked-change cleanup.
- Create professional DOCX from scratch (docx-js): Generate documents programmatically with correct page sizing, styles, tables, images, hyperlinks, footnotes, and table of contents constraints.
- Edit existing DOCX at the XML level: Unpack → carefully edit
word/ XML (including revisions/comments markers) → repack with validation and auto-repair for common ID/whitespace issues.
- Convert formats for inspection: Use Pandoc for text extraction and LibreOffice to convert to PDF/images for downstream review.
- Validate against OOXML schemas: Run schema validation (DOCX XSD + structural checks) and enforce tracked-change and ID constraints, including comment marker pairing.
Quick Start
Use the docx skill to convert the attached file 'report.docx' into an unpacked, editable XML directory for safe inspection: python scripts/office/unpack.py report.docx unpacked/