機器學習

Implement server-side rendering with template engines, view layers, and dynamic content generation. Use when building server-rendered applications, implementing MVC architectures, and generating HTML on the server.

Build binary and multiclass classification models using logistic regression, decision trees, and ensemble methods for categorical prediction and classification

Optimize hyperparameters using grid search, random search, Bayesian optimization, and automated ML frameworks like Optuna and Hyperopt

Implement WCAG compliance using semantic HTML, ARIA, keyboard navigation, and screen reader support. Use when building inclusive applications for all users.

Build and train machine learning models using scikit-learn, PyTorch, and TensorFlow for classification, regression, and clustering tasks

Create system architecture diagrams using Mermaid, PlantUML, C4 model, flowcharts, and sequence diagrams. Use when documenting architecture, system design, data flows, or technical workflows.

Design for mobile devices first, then scale up to larger screens. Create responsive interfaces that work seamlessly across all device sizes.

Monitor model performance, detect data drift, concept drift, and anomalies in production using Prometheus, Grafana, and MLflow

Build predictive models using linear regression, polynomial regression, and regularized regression for continuous prediction, trend forecasting, and relationship quantification

Interpret machine learning models using SHAP, LIME, feature importance, partial dependence, and attention visualization for explainability

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

Identify groups and patterns in data using k-means, hierarchical clustering, and DBSCAN for cluster discovery, customer segmentation, and unsupervised learning

Machine learning library. Use when building predictive models, classification, regression, or clustering.

Browser automation with Playwright for modern web scraping. Use this skill for scraping JavaScript-rendered pages, handling complex interactions, managing multiple browser contexts, or testing web applications. NOT needed for static HTML parsing or processing already-fetched content.

Generate documents from templates. Use for dynamic HTML, reports, emails, or any templated output.

YAML data serialization format. Use when reading/writing VM configuration files or structured data.

Automate browser interactions using Selenium WebDriver. Use this skill when you need to interact with dynamic JavaScript-heavy websites, fill forms, click buttons, handle authentication, or scrape content that requires browser rendering. NOT needed for static HTML parsing or processing already-fetched content.

JSON and YAML parsing, manipulation, and serialization. Use when reading configuration files, parsing API responses, or converting between data formats.

Browser automation with Puppeteer for Node.js/JavaScript environments. Use this skill for controlling Chrome/Chromium in JavaScript projects, generating PDFs, taking screenshots, or scraping JavaScript-rendered content in Node.js. NOT needed for Python projects, static HTML parsing, or processing already-fetched content.

Generate configuration files. Use for creating YAML, TOML, JSON, or INI config files.