Specdd – Spec-driven development as a Claude/Codex/Cursor skill
Another spec framework competing with GitHub's spec-kit but as a skill file.
A docx plugin for Claude Cowork and Claude Code. Uses 2-5X fewer tokens compared to the Anthropic's docx skill.
Bidirectional docx-html conversion cuts token usage 2-5x versus Anthropic's built-in skill.
Legal professionals, Claude Cowork users working with documents
Anthropic Claude DOCX skill · Pandoc · Mammoth.js
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...
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...
Another spec framework competing with GitHub's spec-kit but as a skill file.
Nested agent summarization cuts token costs ~45% for command-heavy workflows.
ASCII art plugin with zero utility beyond the joke itself.
Blog post comparing AI reverse engineering skills, not an actual tool or product.
Mitmproxy capture shows why each turn costs without touching agent config.
Cross-agent skill sync is useful, but the audience is tiny right now.