Skill UI

Automates sklearn pipeline builder tasks within ML training, activating on relevant triggers to guide data prep, model training, hyperparameter tuning, and experiment tracking with production-ready code and standards validation.

Automates splitting datasets into training, validation, and test subsets by generating and running Python code so you can quickly prepare data for machine learning model training and evaluation.

Auto-activating skill that guides tensorflow model trainer workflows, covering data preparation, model training, hyperparameter tuning, and experiment tracking with production-ready code and standards validation.

Automates the end-to-end training of machine learning models by analyzing datasets, selecting suitable algorithms, tuning parameters, performing cross-validated training, and emitting performance metrics plus a saved model artifact.

This advanced workflow orchestrates complex, multi-node GPU clusters on Vast.ai. It is designed for large-scale distributed machine learning training, automatically handling spot instance preemption and resuming jobs from checkpoints. Furthermore, it provides comprehensive cost analysis by tracking billing history, allowing users to optimize GPU spending and manage cluster teardown efficiently.

A comprehensive guide to optimizing deep learning workflows and maximizing efficiency on cloud GPU platforms like Vast.ai. Learn techniques for selecting optimal instances by performance-per-dollar, reducing startup latency, tuning data pipelines (DataLoader, pin_memory), and scaling multi-GPU training using PyTorch and Bash scripting.

Query and download the NCI Imaging Data Commons public cancer imaging datasets via idc-index, filter by metadata, fetch DICOM files, visualize series, and respect licensing details for AI training or research.

PathML is a Python toolkit for computational pathology workflows, loading 160+ slide formats, preprocessing H&E images, constructing spatial graphs, training HoVer-Net/HACTNet models, and analyzing multiplex imaging for ML-ready pathology data.

This skill provides zero-shot time series forecasting using Google's TimesFM foundation model. It forecasts any univariate time series (like sales, sensor data, or weather) without requiring custom model training. The model delivers point forecasts along with calibrated prediction intervals (quantiles), offering a robust and probabilistic view of future trends. It is ideal for rapid, reliable forecasting across diverse time-based datasets.

Analyzes comprehensive fitness logs to track quantitative trends in volume, intensity, and frequency. It tracks progress across multiple disciplines (running, strength) and correlates exercise metrics with vital health indicators like blood pressure and weight, providing personalized, science-backed training and recovery advice.

bdistill transforms AI interactions into a structured, queryable knowledge base. It extracts, structures, and quality-scores domain knowledge from both closed-source AI models (in-session) and local open-source models (via Ollama). Users can build comprehensive reference datasets, Q&A pairs, or generate structured training data for traditional machine learning, ensuring validated and exportable domain expertise.

Trackio is a comprehensive library for logging, visualizing, and managing ML experiment metrics and alerts. It allows developers to use a Python API to log metrics and set diagnostic alerts (INFO/WARN/ERROR) during training. Furthermore, a dedicated CLI enables metric retrieval and dashboard viewing, syncing data to Hugging Face Spaces for persistent, remote monitoring, making it ideal for autonomous ML agent workflows.