Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
88
Quality
81%
Does it follow best practices?
Impact
100%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
New Word document creation with docx-js
Uses docx npm package
100%
100%
Document component used
100%
100%
Paragraph component used
100%
100%
TextRun component used
100%
100%
Packer.toBuffer export
100%
100%
Output is .docx file
100%
100%
No verbose variable names
100%
100%
No unnecessary print statements
100%
100%
JavaScript/TypeScript used
100%
100%
Without context: $0.3610 · 1m 27s · 23 turns · 29 in / 5,156 out tokens
With context: $0.5104 · 1m 39s · 26 turns · 277 in / 5,813 out tokens
Text extraction from .docx using pandoc
Uses pandoc for extraction
0%
100%
track-changes flag present
0%
100%
track-changes=all value
0%
100%
Markdown output format
100%
100%
extracted.md produced
100%
100%
extract.sh produced
100%
100%
Without context: $0.3068 · 1m 19s · 20 turns · 24 in / 4,363 out tokens
With context: $0.6142 · 2m 51s · 30 turns · 461 in / 6,401 out tokens
Document to JPEG image conversion
soffice used for PDF conversion
100%
100%
soffice headless flag
100%
100%
soffice convert-to pdf
100%
100%
pdftoppm used for image conversion
100%
100%
JPEG output flag
100%
100%
Resolution flag present
100%
100%
page prefix used
100%
100%
JPEG image produced
100%
100%
Without context: $0.4647 · 2m 36s · 35 turns · 37 in / 5,615 out tokens
With context: $0.7133 · 3m 37s · 35 turns · 285 in / 7,661 out tokens
2bbaa03
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.