VA

vanszs/anti-ai-ui

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

24 stars 品質 54 トレンド 15MIT

Anti-AI Slop UI/UX steering skills — filter, palette, and research tool for Kiro, Claude Code, Cursor, Windsurf, Copilot, and more. Build intentional, branded, accessible interfaces.

概要

A comprehensive steering suite for Kiro that eliminates AI slop and produces intentional, branded, accessible UI/UX — not the statistical-mean design defaults that make AI-generated interfaces instantly recognizable. LLMs generate UI by averaging across training data dominated by Tailwind docs, shadcn/ui examples, abandoned repos with unchanged defaults, and 2020–2024 Dribbble SaaS shots. The output (arXiv:2603.13036, "Interrogating Design Homogenization in Web Vibe Coding"). Every AI-generated landing page has purple/indigo gradients, Inter everywhere, centered dual-CTA heroes, 3-card feature grids, glassmorphism navbars, and hype copy like "Supercharge your workflow." If you could swap the logo with a competitor and nobody would notice — it's slop. provides three complementary steering skills that work together: Filter out slop → Build from proven patterns → Research industry-specific solutions.

README

以下は原文 README の抜粋です。原文を見る。

Anti-AI-UI/UX

A comprehensive steering suite for Kiro that eliminates AI slop and produces intentional, branded, accessible UI/UX — not the statistical-mean design defaults that make AI-generated interfaces instantly recognizable.

The Problem

LLMs generate UI by averaging across training data dominated by Tailwind docs, shadcn/ui examples, abandoned repos with unchanged defaults, and 2020–2024 Dribbble SaaS shots. The output collapses toward the visual mean (arXiv:2603.13036, “Interrogating Design Homogenization in Web Vibe Coding”).

The result: Every AI-generated landing page has purple/indigo gradients, Inter everywhere, centered dual-CTA heroes, 3-card feature grids, glassmorphism navbars, and hype copy like “Supercharge your workflow.”

If you could swap the logo with a competitor and nobody would notice — it’s slop.

The Solution

Anti-AI-UI/UX provides three complementary steering skills that work together:

┌─────────────────────────────────────────────────────────────────┐
│  FILTER: Anti-AI-Slop                                          │
│  What to AVOID — hard bans on purple gradients, Inter-everywhere,│
│  glassmorphism, emoji icons, hype copy, no reduced-motion       │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│  PALETTE: Component Reference Design                           │
│  What to BUILD — curated patterns from MUI, shadcn, Radix,     │
│  MD3, Apple HIG, IBM Carbon, NNG, Refactoring UI               │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│  RESEARCH: UI/UX Pro Max                                       │
│  Design intelligence — 161 reasoning rules, 67 UI styles,      │
│  57 font pairings, industry-specific design system generator   │
└─────────────────────────────────────────────────────────────────┘

Together: Filter out slop → Build from proven patterns → Research industry-specific solutions.

Features

🛡️ Anti-AI-Slop — The Filter

Detect and ban the statistical-mean design defaults LLMs emit.

GitHub で README 全文を見る

推奨ツール

別のキーワードを試すか、フィルタを外してください。

インストール

npx skillfish add vanszs/anti-ai-ui
MCP 初心者?mcpskill.org のガイドから始めましょう →