I think AI coding assistants need an "npm" for reusable skills. I'm building one.

A developer is building Kitbash, an open standard for portable AI skills that works across multiple AI coding assistants. The project aims to solve the problem of having to rewrite and maintain skills separately for each assistant, similar to how npm standardized JavaScript packages. Kitbash is currently in pre-alpha and the developer is seeking feedback on the architecture.

I've been using multiple AI coding assistants Claude Code, Cursor, Codex, Copilot, Gemini CLI, Windsurf, etc. over the past few months, and I noticed the same problem everywhere. Every assistant has its own way of defining skills, rules, or prompts. If I build a useful skill for one assistant, I have to rewrite and maintain it separately for every other assistant. That feels a lot like JavaScript before npm or containers before Docker. So I started building Kitbash . It's not another AI coding assistant . The goal is to create an open standard for portable AI skills . Some ideas I'm exploring: It's still pre-alpha , so I'm mainly looking for feedback on the architecture and whether this is actually a problem worth solving. 🌐 Landing Page: https://singhharsh1708.github.io/kitbash/ https://singhharsh1708.github.io/kitbash/ 💻 GitHub: https://github.com/singhharsh1708/kitbash https://github.com/singhharsh1708/kitbash I'd love to hear your thoughts.