DEV Community

Harsh Singh
Harsh Singh

Posted on

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

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.

  • Claude Code → Skills
  • Cursor → Rules
  • GitHub Copilot → Instructions
  • Codex → AGENTS.md
  • Windsurf → Workflows
  • Others → Yet another format

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:

  • 📦 Write a skill once and compile it for multiple AI coding assistants.
  • 🔒 Versioned installs with lockfiles instead of copying prompt files.
  • 🧪 Testable skills with evaluation suites.
  • 🔐 Permission manifests and context budgets.
  • 🔄 Composable workflows where skills exchange typed artifacts instead of giant prompt chains.
  • 🌍 A community ecosystem where anyone can publish reusable skills.

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/

💻 GitHub: https://github.com/singhharsh1708/kitbash

I'd love to hear your thoughts.

  • Is this solving a real pain point?
  • What features would you expect from something like this?
  • If you use multiple AI coding assistants, would you install a tool like this?

Top comments (0)