Image Processing

Extract panel schedule data from images. Captures all user-visible load values, detects layout type, and outputs flat circuit-by-circuit JSON for post-processing.

Extract panel schedule data from images using flat slot-by-slot extraction. AI captures each slot as a row; post-processor groups breakers and assigns phases.

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.

REST API design patterns and MicroProfile OpenAPI documentation. Use when designing endpoints, choosing HTTP methods, status codes, or documenting APIs with OpenAPI annotations.

Provides guidance and templates for containerizing applications using Docker. Use when a user wants to create Dockerfiles, optimize images, set up multi-container applications with docker-compose, or follow best practices for containerization. Includes templates for frontend (Next.js), backend (FastAPI), workers, and databases.

Audit and optimize WordPress SEO (Yoast/Rank Math) - checks focus keywords, meta descriptions, featured images. Uses Unsplash API for missing images. Run on all pages/posts to identify and fix SEO issues.

Extract data from bill/receipt images and return JSON for lunch-splitter app

Export DOT/Graphviz diagrams from documents to SVG images. Use after creating documents with DOT code blocks when you need to render them as static images for distribution, GitHub, wikis, or static sites. Supports multiple layout engines (dot, neato, circo, fdp, twopi, osage, patchwork). Processes .md, .html, .mdx, .rst, .adoc files.

Use when discovering a useful technique, pattern, or insight during work - pause to capture it as a skill before the knowledge evaporates, preventing the "I'll remember this" trap that causes expertise loss

OPA Gatekeeper policy templates overview. 20 production-ready constraint templates for pod security, image validation, RBAC, and resource governance.

Build accessible user interfaces following WCAG guidelines with semantic HTML, keyboard navigation, and screen reader support. When creating or modifying UI components, pages, forms, or interactive elements. When working on files that render HTML, JSX, or template markup. When implementing keyboard navigation, focus management, or ARIA attributes. When adding form inputs, buttons, links, modals, or any interactive UI elements. When ensuring color contrast, alternative text for images, or proper heading structure. When building or testing components for screen reader compatibility.

Create and optimize Dockerfiles, docker-compose.yml files, multi-stage builds, and container configurations. Use when user mentions Docker, containers, Dockerfile, docker-compose, containerization, image optimization, or asks to dockerize an application.

Write and add new blog posts for this Next.js site by matching the existing BlogPost structure in `src/lib/blog-data.ts`. Use when asked to draft a new blog article, update blog content, or produce SEO metadata/slug/image details for a new post.

Research-powered creative strategy with visual previews. Use when you need to figure out WHAT to create before creating it. Researches competitors, captures references, generates visual direction previews, and outputs comprehensive briefs. Triggers on: creative strategy, what visuals should I create, creative brief, visual direction. Outputs briefs with actual preview images for feedback.

Security best practices for Dokploy templates: secrets management, network isolation, least privilege, image security, and hardening recommendations.

Scans containers and Dockerfiles for security issues. Wraps Hadolint for Dockerfile linting and Trivy for container image scanning. Use when user asks to "scan Dockerfile", "lint Dockerfile", "container security", "image scan", "Dockerセキュリティ", "コンテナスキャン".

Kindle Web Reader/Kindle macOSアプリからスクリーンショットをキャプチャしてPDF生成。書籍名やASIN指定でKindle本を自動PDF化。Kindleライブラリ検索、Playwrightでページ自動取得、PNG画像からPDF変換、レイアウト設定（single/double）、範囲指定、品質調整、リサイズに対応。タイトル取得に失敗した場合は表紙キャプチャをAIで視認して命名する。

Gemini APIを使用して画像を生成し、リポジトリに保存。ランディングページ、ヒーローイメージ、プロダクト画像、アバター、ダミー画像、プレースホルダー画像が必要なときに使用。画像生成、AI画像、自動生成。

Extract panel schedule data from images. Captures all user-visible load values, detects layout type, and outputs flat circuit-by-circuit JSON for post-processing.

Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model. Use when generating images, creating visual content, or implementing text-to-image features. Supports text-to-image, image editing, multi-image composition, and iterative refinement.