This skill helps you build production-grade web interfaces with bold, memorable aesthetics. It guides creative choices for typography, color, motion, and spatial composition to avoid generic AI-generated designs.

Creating SVG vector graphics manually requires design software and technical skills. This skill uses AI to convert text descriptions into scalable vector graphics through Google Gemini and autotrace.

Design systems often drift without clear tokens and patterns. This skill provides Tailwind structures to standardize components, themes, and responsive layouts across your codebase.

Remove backgrounds from any image automatically to create professional transparent PNGs. Perfect for product photos, headshots, and design work without manual editing.

Claude can automatically review UI code against established web design guidelines, catching accessibility issues, usability problems, and best practice violations before deployment. This skill fetches the latest guidelines and performs static analysis to identify improvements.

Create modern AI chat interface components using pre-built, composable UI elements that follow shadcn/ui patterns and Vercel AI SDK conventions.

Transform React/Remotion TSX components into MP4 videos programmatically. Pass code, get video output with full control over resolution, FPS, duration, and animations.

Generate high-quality images using Google Gemini 3 Pro and Gemini 2.5 Flash models through the inference.sh CLI. Supports text-to-image generation, image editing with multiple inputs, custom aspect ratios, and up to 4K resolution output.

Create professional AI-generated videos from text prompts or images using Google Veo, Seedance, Wan, and other state-of-the-art models through a simple CLI interface.

Create professional AI images using FLUX, Gemini, Grok, and 50+ models directly from Claude or Codex via the inference.sh CLI.

Create stunning images using Google Gemini 3.1 Flash Image model through inference.sh CLI. Generate text-to-image, edit photos, and produce multiple variations with Google Search grounding for real-time context.

Generate images using Google Gemini 3 Pro and Gemini 2.5 Flash through Claude Code. This skill provides direct access to Google's native image generation models with support for text-to-image, image editing, and multi-image input workflows.

Creating videos manually is time-consuming and expensive. This skill provides access to 40+ AI video generation models through a simple CLI interface, enabling rapid video creation for social media, marketing, and content creation.

Create stunning AI-generated images using FLUX, Gemini, Grok, and more models through a simple CLI interface. Perfect for designers, marketers, and developers needing quick image generation.

Create professional images, product mockups, and marketing visuals using industry-leading AI models without expensive subscriptions. Access FLUX, Gemini, Grok, Seedream, and 50 more models through a single command-line interface.

You need consistent visual styling across documents and presentations. This skill provides 10 curated themes and can generate custom themes based on your requirements. Apply matching colors and fonts to slides, docs, and reports.

Ensure your UI code follows industry best practices and accessibility standards. This skill automatically checks your components against Vercel's Web Interface Guidelines and reports violations with specific line numbers and fix suggestions.

Web applications often exclude users with disabilities due to poor accessibility implementation. This skill provides WCAG 2.1 guidance for creating inclusive, screen-reader-friendly, keyboard-navigable interfaces.

Create websites that adapt beautifully to any screen size using mobile-first design principles, CSS Grid, Flexbox, and modern responsive techniques.

Need images but want to avoid paid APIs? This skill generates images through Pollinations.ai's free, open API with no signup required.