draw-ui — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 oil-oil · Claude Skill · ★ 326

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is draw-ui safe to install? View the security audit →

About draw-ui

draw-ui — AI UI Design Skill A universal AI skill that generates UI design mockups and helps reconstruct generated UI screenshots into HTML/CSS. Prefer the runtime's built-in image generation when available; use GPT Image 2 via the ZenMux API for scripted local outputs. What it does Generates high-quality UI mockups from natural language descriptions Locks navigation/sidebar consistency across multiple screens using a reference image Uses proven prompt techniques (analogy-style or inventory-style) for better design quality Handles GPT Image 2's API quirks automatically (serial execution, retries) Guides HTML reconstruction with asset strategy, browser screenshot comparison, and background-removal rules for logos and illustrations Requirements An AI agent that supports the skills protocol (Claude Code, Cursor, etc.) For scripted image generation: a ZenMux API key — set as env var, in , or in Python 3 (auto-installs on first run) Installation Or clone manually: Usage Trigger by saying anything like: 帮我设计一个 Dashboard 页面 Design a user profile screen 出图,产品详情页 The agent will ask you a few questions first (what the page does, whether you have a reference screenshot, consistency...

Quick Facts

Stars326
Forks58
LanguagePython
CategoryClaude Skill
Quality Score64.3609453544535/100
Last Updated2026-07-26
Created2026-04-24
Platformsclaude-code, python
Est. Tokens~14k

Compatible Skills

These tools work well together with draw-ui for enhanced workflows:

  • image-gen-mcp — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (59%)
  • skills — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

draw-ui alternative? Top 4 similar tools

Looking for a draw-ui alternative? If you're comparing draw-ui with other claude skill tools, these 4 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • digital-marketing-pro by indranilbanerjee · ⭐ 846

    An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti

  • life-sciences by anthropics · ⭐ 608

    Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to ho

  • claude-ai-mcp by anthropics · ⭐ 484

    Report issues related to MCP integration with Claude here.

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is draw-ui?

draw-ui is Claude Code skill: generate UI design mockups with GPT Image 2 via ZenMux. It is categorized as a Claude Skill with 326 GitHub stars.

What programming language is draw-ui written in?

draw-ui is primarily written in Python.

How do I install or use draw-ui?

You can find installation instructions and usage details in the draw-ui GitHub repository at github.com/oil-oil/draw-ui. The project has 326 stars and 58 forks, indicating an active community.

What are the best alternatives to draw-ui?

The top alternatives to draw-ui on Agent Skills Hub include claude-codex-settings, digital-marketing-pro, life-sciences. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools