Machine Learning

Expert frontend web development including HTML/CSS/JavaScript implementation, responsive design, accessibility improvements, and Playwright browser automation testing. Balances modern frameworks with pragmatic vanilla solutions. Use when working with web frontends.

Use when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure.

Effectively use Narwhals to write dataframe-agnostic code that works seamlessly across multiple Python dataframe libraries. Write correct type annotations for code using Narwhals.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.

Comprehensive ML model evaluation with multiple metrics, cross-validation, and statistical testing. Activates for "evaluate model", "model metrics", "model performance", "compare models", "validation metrics", "test accuracy", "precision recall", "ROC AUC". Generates detailed evaluation reports with visualizations and statistical significance tests, integrated with SpecWeave increment documentation.

Calculate and analyze Turkish electricity imbalance costs including KUPST (Kesinleşmiş Üretim Planından Sapma Tutarı/Production Plan Deviation Cost), positive/negative imbalance penalties, and DSG (Dengeden Sorumlu Grup) tolerance calculations. Use when asking about imbalance settlement, deviation costs, KUPST, energy surplus/deficit penalties, or imbalance calculations in Turkey. Triggers on: dengesizlik maliyeti, sapma tutarı, KUPST, KÜPST, enerji açığı, enerji fazlası, imbalance penalty.

Comprehensive feature engineering for ML pipelines: data quality assessment, feature creation, selection, transformation, and encoding. Activates for "feature engineering", "create features", "feature selection", "data preprocessing", "handle missing values", "encode categorical", "scale features", "feature importance". Ensures features are production-ready with automated validation, documentation, and integration with SpecWeave increments.

Converts Docker Compose configurations to NixOS modules using the dendritic pattern with Arion. Creates modules with system users, sops secrets, Arion docker-compose config, and Tailscale integration. Use when converting docker-compose.yaml files to NixOS modules or creating new Arion-based services.

Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track experiments", "MLflow", "wandb", "experiment logging", "compare experiments", "hyperparameter tracking". Automatically configures tracking tools to log to SpecWeave increment folders, ensuring all experiments are documented and reproducible. Integrates with SpecWeave's living docs for persistent experiment knowledge.

Orchestrates complete machine learning pipelines within SpecWeave increments. Activates when users request "ML pipeline", "train model", "build ML system", "end-to-end ML", "ML workflow", "model training pipeline", or similar. Guides users through data preprocessing, feature engineering, model training, evaluation, and deployment using SpecWeave's spec-driven approach. Integrates with increment lifecycle for reproducible ML development.

Detects when user reports issues with recently completed work and suggests reopening relevant tasks, user stories, or increments. Auto-activates on keywords: not working, broken, bug, issue, problem, failing, error, crash, regression, still broken, incorrect, missing, wrong. Scans active and recently completed (7 days) work to find related items. Provides smart suggestions with relevance scoring.

Guide for working with gomponents, a pure Go HTML component library. Use this skill when reading or writing gomponents code, or when building HTML views in Go applications.

Centralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "model staging", "deploy to production", "rollback model", "model metadata", "model lineage", "promote model", "model catalog". Manages ML model lifecycle from development through production with SpecWeave increment integration.

Comprehensive Playwright end-to-end testing expertise covering browser automation, cross-browser testing, visual regression, API testing, mobile emulation, accessibility testing, test architecture, page object models, fixtures, parallel execution, CI/CD integration, debugging strategies, and production-grade E2E test patterns. Activates for playwright, e2e testing, end-to-end testing, browser automation, cross-browser testing, visual testing, screenshot testing, API testing, mobile testing, accessibility testing, test fixtures, page object model, POM, test architecture, parallel testing, playwright config, trace viewer, codegen, test debugging, flaky tests, CI integration, playwright best practices.

Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl", "hyperparameter tuning", "optimize hyperparameters", "auto tune model", "neural architecture search", "automated ml". Systematically explores model and hyperparameter spaces, tracks all experiments, and finds optimal configurations with minimal manual intervention.

Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Activates for "deploy model", "production deployment", "model API", "containerize model", "docker ml", "serving ml model", "model monitoring", "A/B test model". Generates deployment artifacts and ensures models are production-ready with monitoring, versioning, and rollback capabilities.

Element is a zero dependency library to efficiently generate HTML programmatically, without templates in Go

Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.

동영상에서 자막을 자동 생성하고 발표자료 기반으로 교정하는 스킬. "자막 생성", "영상 자막", "STT", "subtitle" 요청에 사용. mlx-whisper로 추출 → 중복 정리 → 발표자료 기반 교정까지 자동화.