機器學習
1913 skills in 數據與 AI > 機器學習
ai-tutor
This skill should be used when the user asks to "explain", "break down", "help me understand", "teach me about", or requests clarification of technical concepts (AI, ML, software development, or other technical topics). Transforms complex ideas into clear, accessible explanations using narrative storytelling frameworks.
ui-design
XML layouts, ConstraintLayout, Jetpack Compose, Material Design 3. Use when building user interfaces and designing layouts.
policyengine-parameter-patterns
PolicyEngine parameter patterns - YAML structure, naming conventions, metadata requirements, federal/state separation
360-executive-project-tracker
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.
pca-ui-builder
Gera prototipos React (SPA) visuais completos num unico ficheiro HTML. Utiliza Tailwind e shadcn/ui. Ideal para visualizar dashboards do PCA Camocim.
oscal-parser
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.
a11y-self-check
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.
total-recall
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.
bpmn-xml-generator
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".
bpmn2skill
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.
html-to-pdf
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.
ml-antipattern-validator
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.
avalonia
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.
photo-content-recognition-curation-expert
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.
email-anti-slop
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.
manifest-validator
Validates Kubernetes manifests using kubeconform, kube-score, and custom homelab policies. Use when creating or modifying YAML files, Helm values, or ArgoCD applications.
frontend-components
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
ml-pipeline-workflow
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.
cpp-qml-coding
C++/QML 코딩 컨벤션 및 패턴. 코드 작성/리뷰 시 참조.
golden-dataset-management
Backup, restore, and validate golden datasets for AI/ML systems - ensuring test data integrity and preventing catastrophic data loss