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 dembrandt · MCP Server · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dembrandt-skills safe to install? View the security audit →
dembrandt-skills UX and design-system skills for AI agents. Install once, and your agent knows how to design. installs every skill at once. They load only when a prompt needs them, so there is no runtime cost to having them all. Want to pick by hand? Drop for an interactive picker. Add to install across all your projects. How to use A skill is just instructions your agent reads. You don't run it. The agent reads each skill's description and loads the matching one when your request fits. Install with the command above, then start a new session. Skills load at session start. Ask in plain words. "What layout fits a list of orders?" or "Does this pass WCAG AA?" loads the right skill on its own. For a full pass, ask broadly ("review this screen", "build a UI from this brand") and the skill runs the whole pipeline. No special syntax. You can name a skill to force it ("use the layout skill"), but you rarely need to. Run to see what's installed. Connect the engine (optional) Most skills are pure knowledge and work on their own. Two of them, and , read real design tokens off a live website. That needs the [](https://n
| Stars | 65 |
| Forks | 11 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 68.3430501304586/100 |
| Last Updated | 2026-10-03 |
| Created | 2026-04-19 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~14k |
These tools work well together with dembrandt-skills for enhanced workflows:
Looking for a dembrandt-skills alternative? If you're comparing dembrandt-skills with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
A Claude skill that audits designs against 19 professional design rules.
A modular UX, design, and product optimisation system for turning AI-built interfaces into production-grade ap
On-demand design systems from any URL. Five surfaces, one agent: web, API, CLI, TypeScript SDK, and a portable
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Explore other popular mcp server tools:
dembrandt-skills is Senior-level UX and design-system knowledge, packaged so your AI agent applies it automatically.. It is categorized as a MCP Server with 65 GitHub stars.
dembrandt-skills is primarily written in JavaScript. It covers topics such as accessibility, agent-skills, ai-agents.
You can find installation instructions and usage details in the dembrandt-skills GitHub repository at github.com/dembrandt/dembrandt-skills. The project has 65 stars and 11 forks, indicating an active community.
dembrandt-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dembrandt-skills on Agent Skills Hub include extract-design-system, awesome-ai-agent-skills, claude-design-auditor-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: