Image Processing

Guide for using WebViewBridge Swift package to build WebPage (macOS 26.0+) bridges with JavaScript injection and bidirectional communication. Use when integrating WebPage with Swift, injecting JavaScript, or handling JS↔Swift messaging.

Extracts design tokens from images and generates CSS custom properties, atomic utility classes (Tailwind-style), and platform-specific formats following W3C standards and modern CSS best practices.

Generates Nano Banana Pro prompts for blog and YouTube thumbnail images. Use when user mentions "サムネイル作成", "サムネ", "YouTube用画像", or "ブログ画像".

C# best practices with .NET 8, ASP.NET Core, Entity Framework, and modern async programming for 2025

Manage media files (images, PDFs, videos) in Laravel using Spatie's Media Library. Handle file uploads, store files on any filesystem (S3, local), generate image conversions (thumbnails, responsive images), manage file metadata with custom properties, and serve files with automatic URL generation. Use when implementing file upload functionality, image processing, media collections, responsive images, or file management in Laravel applications.

Generates Nano Banana Pro prompts for 4-panel engineer humor comics. Use when user mentions "漫画作成", "エンジニア漫画", "4コマ", or "あるある". Requires character image attachment when using generated prompts.

Composable image and video thumbnail processing with PDF generation. Create review PDFs with annotation space, or use the lib modules in custom workflows like daily reports.

Break down, design, and structure features into implementable tasks for Photo Map MVP. Use when planning new features, creating user stories, defining API endpoints, structuring implementation phases, organizing project tasks, or designing feature breakdowns.

Build accessible user interfaces with semantic HTML, keyboard navigation, proper color contrast, ARIA attributes, and screen reader support. Use this skill when creating or modifying frontend UI components, HTML templates, JSX/TSX files, forms, interactive elements, modals, navigation menus, or any user-facing interface code. Use this when ensuring keyboard accessibility, adding ARIA labels and roles, providing alt text for images, managing focus states, implementing proper heading hierarchy, testing with screen readers, or ensuring sufficient color contrast ratios. Use this when working on .jsx, .tsx, .vue, .html, or component files that render UI elements.

Guide for using ImageMagick command-line tools to perform advanced image processing tasks including format conversion, resizing, cropping, effects, transformations, and batch operations. Use when manipulating images programmatically via shell commands.

Scrape content from RedNote/Xiaohongshu including posts, images, videos, and complete comment threads with nested replies. Use when researching topics on RedNote, extracting social media content for analysis, or gathering RedNote posts and discussions. Works with any remote browser providing a WebSocket URI (WSS).

Portfolio optimization using PyPortfolioOpt for mean-variance optimization, efficient frontier analysis, risk modeling, and discrete allocation. Use when building investment portfolios, calculating optimal weights, analyzing risk-return tradeoffs, maximizing Sharpe ratio, minimizing volatility, or converting weights to share allocations. Supports HRP, CVaR, semivariance, and custom objectives.

Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking uploaded images for brand consistency, providing quality feedback on visual assets, or deciding if an image is ready for publication. Returns pass/fail with specific actionable feedback.

Converts HTML files to PDF or PNG format. Use this skill when the user asks to convert, export, or generate PDF/PNG from HTML files, or when they want to create printable documents, presentations, or long-form images from web pages or HTML reports.

Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, screenshot/meme detection, burst photo selection, and quick indexing strategies. Activate on 'face recognition', 'face clustering', 'perceptual hash', 'near-duplicate', 'burst photo', 'screenshot detection', 'photo curation', 'photo indexing', 'NSFW detection', 'pet recognition', 'DINOHash', 'HDBSCAN faces'. NOT for GPS-based location clustering (use event-detection-temporal-intelligence-expert), color palette extraction (use color-theory-palette-harmony-expert), semantic image-text matching (use clip-aware-embeddings), or video analysis/frame extraction.

Image generation prompts

Web crawler that converts URLs to clean markdown for LLM consumption. Use when user wants to crawl a webpage, extract web content, convert URL to markdown, or scrape website content for AI processing.

Use when animating carousels, sliders, image galleries, or horizontally scrolling content for smooth navigation

Screenshot-based regression testing with Playwright. Compares rendered pixels against baseline PNGs. Use when working with stories, *.visual.spec.ts files, or baseline screenshots. Auto-apply when editing files in stories/ or *.visual.spec.ts.

Generate images and videos using Google GenAI models. Use when user asks to "generate image with Gemini/Nano Banana", "create video with Veo", "make an image using Imagen", or requests media generation with specific models like gemini-2.5-flash-image, gemini-3.0-pro-image, imagen-3.0, veo-3.1, or veo-3.0.