No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by funboy322 · Claude Skill · ★ 80
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is avoid-ai-design safe to install? View the security audit →
avoid-ai-design A Claude Code skill that audits AI-generated frontend code and rewrites it so it stops looking AI-generated. One real site, run through the skill. Same product, same sections, same copy, only the design changed. The pages and the full audit live in examples/demo/. Ask Claude, Codex, or any model to "build a landing page" and you get the same page every time: a purple-to-blue gradient on white,
| Stars | 80 |
| Forks | 4 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.3562478341997/100 |
| Last Updated | 2026-09-24 |
| Created | 2026-05-30 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~15k |
Looking for a avoid-ai-design alternative? If you're comparing avoid-ai-design with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflo
UI/UX system for Claude Code: 71 plugins, 93 agents, 74 skills. Design mastery, archetypal design, accessibili
Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop lin
Design engineering system for AI coding agents — ship UI with craft-level quality. Install as an agent skill.
Skills for AI coding agents — Laravel, PHP, React, TypeScript, testing, security, and code quality.
Production-grade design context for AI coding workflows. Extract a real design system from any URL — colors, t
Explore other popular claude skill tools:
avoid-ai-design is Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracotta, mono chrome). Zero-dependency scanner included. The desi. It is categorized as a Claude Skill with 80 GitHub stars.
avoid-ai-design is primarily written in JavaScript. It covers topics such as agent-skills, ai-design, ai-slop.
You can find installation instructions and usage details in the avoid-ai-design GitHub repository at github.com/funboy322/avoid-ai-design. The project has 80 stars and 4 forks, indicating an active community.
avoid-ai-design is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to avoid-ai-design on Agent Skills Hub include Codex-Skills, LibreUIUX-Claude-Code, ux-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: