Modern responsive image techniques using picture element, srcset, sizes, and modern formats (AVIF, WebP). Optimizes image delivery for different screen sizes, resolutions, and devices with proper loading strategies and accessibility.

Search and download royalty-free images and videos from Pixabay's library of over 4 million assets. Supports advanced filtering by type, category, color, orientation, and more for finding the perfect stock media for any project.

Select appropriate Segoe MDL2 Assets icons for WinUI Windows applications. Provides icon recommendations with Unicode points, visual descriptions, and creative alternatives based on user needs and use cases.

A comprehensive image processing tool for basic editing operations and color adjustments. Supports resize, rotate, crop, flip, and color enhancements (brightness, contrast, saturation, sharpness) for both local files and images from URLs.

Optimize 3D Gaussian Splatting scenes for real-time rendering on Apple platforms (iOS, macOS, visionOS) using Metal. Provides pruning, LOD, compression strategies and Metal profiling tools to achieve target FPS on mobile and desktop GPUs.

A systematic 5-phase approach to debug visual and spatial bugs in Godot games through user observation, Godot-specific diagnosis, and test-driven fixes. Handles rendering, positioning, animation, and coordinate system issues where the developer cannot see the running game.

Image generation using Google's Imagen and Gemini native models. Supports text-to-image creation, image editing, iterative refinement, and multi-turn conversational generation with SynthID watermarks.

Intelligent game asset management system that searches and integrates 36,000+ Kenney CC0 assets with flat/vector style consistency. Automatically triggers on asset requests, prioritizes existing resources over generation, and ensures visual coherence across game projects.

Scaffolds new computer vision detector plugins for Bob The Skull's vision system. Supports creating detectors for object detection, pose estimation, gesture recognition, and custom detection algorithms following the established detector architecture.

Handle complex-valued tensors in PyTorch for astronomical imaging applications, including FFT operations, phase/amplitude conversions, and complex arithmetic for neural networks.

A comprehensive photo and image handling skill for Claude Code that enables users to upload, analyze, process, and manage visual content including screenshots, UI mockups, designs, and photos with support for OCR, format conversion, and visual debugging.

Generate minimalist static images from text prompts and animate them into short videos using Google's image and video models. Ideal for creating concept renders with simple, clear motions like rolling balls or waving flags.

Expert Android developer for motion detection applications using Camera2 API, real-time motion algorithms with tripwire functionality, and multi-device synchronization via LAN sockets and Supabase Realtime for sprint timing systems.

Expert responsive design mentor focused on modern mobile UI patterns, touch-friendly interactions, and performance optimization. Provides guidance on mobile-first layouts, accessibility standards, PWA implementation, and cross-device compatibility.

Create UI components and designs following Google Material Design 3 (Material You) guidelines. Implements Material theming, color systems, typography, elevation, motion, and accessibility standards for web and Android interfaces.

A comprehensive Gemini 3 Pro client with Thinking mode enabled. Supports text queries, multi-format file analysis (MP4, PDF, images), YouTube video analysis, image generation/editing, and Google Search grounding. Uses browser cookies for authentication without requiring API keys.

Build stunning component libraries with Storybook mastery. Expert in component documentation, visual testing, design systems, and UI development with isolated component building, interaction testing, and comprehensive documentation.

Pixel-perfect translation of Figma designs into production-ready React code. Expertly converts Figma's autolayout, variables, styles, and components into precise CSS and React implementations with mathematical accuracy.

Designs modern iOS screens and components for Expo React Native apps following Apple Human Interface Guidelines, with support for safe areas, Dynamic Type, dark mode, accessibility, Liquid Glass materials, and App Store readiness.

A comprehensive 80s Synthwave/Neon design system for React Native game UI, featuring dynamic hybrid aesthetics with crystal-clear interfaces layered over atmospheric backgrounds, complete with color palettes, typography, animations, and component styling guidelines.

Open-source framework for building AI agents that automate desktop applications through vision-based UI control. Supports multi-platform automation (Windows/Linux/macOS), 100+ LLM providers, and autonomous task execution with screenshot analysis, mouse/keyboard control, and cloud/local deployment options.

Analyzes UI design from image captures and automatically generates screen pages by combining existing Windows Forms-style Astro components. Reproduces layout, colors, sizes, and text from the original design.

Create stunning Apple-inspired UI designs with glassmorphism, smooth animations, and minimalist aesthetics. Perfect for building modern portfolio websites, landing pages, and product showcases with dark mode support and responsive layouts.

Generates premium dark-mode UI for Apex OS wellness app using React Native and Expo 54. Provides comprehensive design guidelines including color system, typography, component patterns, animations, and data visualizations for a Bloomberg-meets-Calm aesthetic targeting health-conscious professionals.

Computer vision library for PyTorch featuring pretrained models, advanced v2 image transforms, and utilities for handling complex data types like bounding boxes and masks. Supports standard CV tasks including classification, detection, and segmentation with performance-optimized augmentations.

Professional AI image generation using Google's Nano Banana models (Gemini 3 Pro Image and Gemini 2.5 Flash Image) via Gemini API. Generate images from text prompts, edit existing images, create visual assets like infographics, logos, product shots, and stickers with advanced features like character consistency and accurate text rendering.

Implement efficient image processing for photo uploads using Sharp library with streaming patterns. Handles thumbnail generation, EXIF orientation, ZIP extraction, and multi-size image optimization while managing memory constraints in serverless environments.

Generate new images from text prompts or edit existing images using OpenAI's GPT Image 1.5 model. Supports text-to-image generation with customizable quality, size, and background options, as well as full image editing and precise mask-based inpainting for targeted modifications.

Generate images using AI models via OpenRouter API. Supports text-to-image and image-to-image generation with customizable aspect ratios and multiple model options.

Automatically processes WhatsApp audio and image files in Gastrohem daily folders. Performs parallel audio transcription using insanely-fast-whisper to create JSON files, and OCR on images using Claude's vision capabilities to generate natural markdown summaries with business-relevant information.