Show HN: Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill

A new DOCX plugin for Cowork and Codex uses 2-5x fewer tokens than traditional docx skills by converting documents bidirectionally between DOCX and HTML, enabling AI to operate on HTML. The plugin's novel html->docx conversion addresses a gap in existing libraries, and it has been used internally for redlining legal documents.

Hi HNers, I'd like to share our DOCX plugin for Cowork and Codex. It uses 2-5x fewer tokens compared to the traditional docx skill because it doesn't write any code nor execute python/node script. It is also much more reliable. Our DOCX plugin converts docx<- html bidirectionally. This means AI only operates on HTML. AI is excellent and very efficient when it comes to HTML. Most libraries if not all support docx- html, but none supports html- docx. This is what is novel about our approach. Here's the demo: https://drive.google.com/file/d/1UNlUJYwkNX3NiANDkLLb3UoRSms... https://drive.google.com/file/d/1UNlUJYwkNX3NiANDkLLb3UoRSms2dXCU/view?usp=drive link We've been using it in-house for redlining legal documents, and we love it. If you redline docx files, please give it a try: https://github.com/LegalRabbit-AI/legalrabbit-docx-claude-pl... https://github.com/LegalRabbit-AI/legalrabbit-docx-claude-plugin Comments URL: https://news.ycombinator.com/item?id=48579116 https://news.ycombinator.com/item?id=48579116 Points: 3 Comments: 0