Machine Learning

Build professionally designed, multi-source project status trackers that consolidate information from Gmail, Google Calendar, Google Drive, and Asana into Excel dashboards and interactive HTML visualizations with automated updates, intelligent blocker detection, and category-based organization.

Gera prototipos React (SPA) visuais completos num unico ficheiro HTML. Utiliza Tailwind e shadcn/ui. Ideal para visualizar dashboards do PCA Camocim.

Parse OSCAL (Open Security Controls Assessment Language) documents in JSON, YAML, or XML formats and extract structured compliance data. Use this skill when working with security control catalogs, system security plans, component definitions, or other OSCAL document types.

Proactively validates Claude Code's own generated HTML/JSX/TSX output for accessibility before presenting to users. Use this skill automatically when generating UI code to ensure WCAG 2.1 AA compliance.

Memory preservation for Claude Code sessions. Use when approaching token limits, needing to /reset or /compact, switching between complex tasks, or preserving critical session state before context loss. Creates comprehensive memory dumps at /tmp/total-recall containing current state, decisions, artifacts, and next steps for seamless context restoration.

Generate BPMN 2.0 compliant XML files from natural language process descriptions. Use this skill when a user wants to create a BPMN workflow, convert a business process to BPMN XML, model a workflow diagram, or generate process definitions. Triggers on requests like "create a BPMN", "generate workflow XML", "model this process", "convert to BPMN 2.0", "create process diagram", or "build workflow".

Generate a complete SKILL.md by parsing a BPMN 2.0 XML process and translating tasks, gateways, and events into skill actions and orchestration logic.

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.

Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.

Expert guidance for developing cross-platform desktop applications with Avalonia UI framework. Use when building, debugging, or optimizing Avalonia apps including MVVM architecture, XAML design, data binding, styling, theming, custom controls, and cross-platform deployment for Windows, macOS, Linux, iOS, Android, and WebAssembly.

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.

Prevent generic AI-generated email aesthetics and enforce distinctive, handcrafted design quality. Use when generating HTML emails, email templates, newsletters, marketing emails, or any email content. Ensures emails look professionally designed, not machine-generated. Applies anti-pattern detection and distinctive design requirements.

Validates Kubernetes manifests using kubeconform, kube-score, and custom homelab policies. Use when creating or modifying YAML files, Helm values, or ArgoCD applications.

Design and build reusable, composable UI components with single responsibility, clear interfaces, proper encapsulation, and minimal props following component best practices. Use this skill when creating or modifying React component files (.jsx, .tsx), Vue single-file components (.vue), Angular component files (.component.ts, .component.html), Svelte components (.svelte), Web Components, or any frontend UI component files in directories like components/, src/components/, app/components/, lib/components/, or ui/components/. Use this when designing component APIs by defining explicit, well-documented props with TypeScript interfaces or PropTypes and providing sensible default values for optional props, implementing component composition patterns by combining smaller, simpler components into more complex UIs rather than building monolithic structures that are hard to maintain, ensuring each component has a single clear responsibility and does one thing well following the Single Responsibility Principle, managing

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

C++/QML 코딩 컨벤션 및 패턴. 코드 작성/리뷰 시 참조.

Backup, restore, and validate golden datasets for AI/ML systems - ensuring test data integrity and preventing catastrophic data loss

Build complex pipelines from reusable workflow components. Compose parent-child workflows, orchestrate multi-stage automation, and eliminate copy-paste YAML.

Standard Go security toolkit: race detector, golangci-lint, Trivy, govulncheck. Zero cost, seamless integration, and OpenSSF-certified security workflow patterns.

Create responsive, mobile-first user interfaces that adapt seamlessly across all device sizes using modern CSS techniques and responsive design patterns. Use this skill when implementing layouts, breakpoints, fluid typography, responsive images, or any UI that needs to work across mobile, tablet, and desktop viewports. Apply this skill when using CSS media queries, container queries, responsive utility classes (Tailwind's sm:, md:, lg:), flexible grid/flexbox layouts, relative units (rem, em, vw, vh), or when optimizing touch interactions for mobile devices. This skill ensures mobile-first development approach, consistent breakpoint usage, proper viewport configuration, touch-friendly target sizes (44x44px minimum), readable typography across all screen sizes, and optimized performance on mobile networks with responsive images and lazy loading.