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 superdesigndev · Claude Skill · ★ 436
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is superdesign-skill safe to install? View the security audit →
Superdesign: the design skill for Claude Code, Cursor and any coding agent Stop shipping AI-slop UI. Coding agents write great code and mediocre interfaces: generic layouts, default shadcn everything, no taste. Superdesign is the skill that gives your agent design judgment, so the UI it ships actually looks considered. Install it once and your agent (Claude Code, Cursor, Codex, and 70+ others) can find real design direction, set up a design system, and generate + iterate high-quality UI drafts on an infinite canvas, all without leaving your terminal. Powered by superdesign.dev, the AI product design agent. ▶ Watch the skill in action. What is Superdesign? Superdesign is an AI product design agent. It gives coding agents (Claude Code, Cursor, Codex, and 70+ others) real design judgment, so the UI they ship looks considered instead of generic. What it does — finds design direction, sets up a design system from your codebase, and generates + iterates high-quality UI drafts on an infinite canvas, all from your terminal. Who it's for — developers, indie hackers, and product/UI designers who want to go from idea to shippable UI fast without leaving their coding agent.
| Stars | 436 |
| Forks | 29 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 76.6888404936583/100 |
| Open Issues | 4 |
| Last Updated | 2026-08-21 |
| Created | 2026-01-21 |
| Platforms | claude-code, node |
| Est. Tokens | ~16k |
These tools work well together with superdesign-skill for enhanced workflows:
Looking for a superdesign-skill alternative? If you're comparing superdesign-skill 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.
Open-source design-method engine for Claude Code, Codex & Cursor. 23 agent skills for fixed design judgment, m
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T
Design engineering system for AI coding agents — ship UI with craft-level quality. Install as an agent skill.
813 AI web design prompts — Generate stunning landing pages, 3D WebGL scenes, SuperDesign UI & components. Wor
Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized fo
Explore other popular claude skill tools:
superdesign-skill is The design skill for Claude Code, Cursor and any coding agent. Stop shipping AI-slop UI: turn it into shippable, tasteful frontend. Install: npx skills add superdesigndev/superdesign-skill. Powered by. It is categorized as a Claude Skill with 436 GitHub stars.
superdesign-skill is primarily written in JavaScript. It covers topics such as agent-skills, ai-design, claude-code.
You can find installation instructions and usage details in the superdesign-skill GitHub repository at github.com/superdesigndev/superdesign-skill. The project has 436 stars and 29 forks, indicating an active community.
superdesign-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to superdesign-skill on Agent Skills Hub include styleseed, modsearch, ai-skills. 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: