shadcn-ui/lint
An agent-first linter for Tailwind design systems. Write design system rules that agents can verify.
Thành tựu nổi bật
Những danh hiệu mới nhất của dự án
#1 Repository Của Tuần
#1 Repository Của Tuần
#1 Repository Của Tuần
🧩 Rules agents can actually fix
Errors that say how to fix, not just what's wrong.
@shadcn/lint is an agent-first linter for Tailwind design systems. It lets teams define what is allowed without rewriting components or changing their API. When an agent breaks a rule, the error explains the issue and suggests a fix based on existing components, variants, and theme. It works with Tailwind v4 (shadcn/ui not required), available for both ESLint and Oxlint, and supports React, Svelte, and Vue.
✨ Highlights
- Agent-first errors: Each violation explains what is wrong and suggests a fix pulled from your design system.
- Component contracts: Set per-component rules to allow or deny specific categories like layout, spacing, typography, or font utilities.
- No component rewrites: Enforce policies without touching component props, types, or API.
- Theme-aware enforcement: Combine with rules like
shadcn/no-arbitrary-valuesto require values from your theme scale. - Custom messages and contracts: Add your own guidance so agents get your design system instructions directly in errors.
- Multi-framework support: Works with React, Svelte, and Vue via ESLint or Oxlint.
- Proven with agents: Tested across more than 150 task runs, reaching near-zero violations in one correction round.
💡 Why it matters
TypeScript can block disallowed props, but its errors rarely say how to use the design system to fix them. @shadcn/lint makes those policies programmable and actionable, giving agents concrete fixes instead of vague rejections. In Claude control runs, using lint feedback cut fix cost by 10% to 48% compared to rules alone, making it a strong fit for agent-driven UI work.
#Linter #DesignSystem #TailwindCSS #AI #TiniX
Dự án tương tự
Khám phá các dự án và mô hình AI khác có sự tương đồng.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Composable, accessible components with thoughtful defaults. Build your own component library with code you can customize, extend, and make your own.
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Knowledge infrastructure to make your agents smarter. Search, scrape and access 550+ data providers through one API.
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
An agentic skills framework & software development methodology that works.