Skill UI

Molfeat is a comprehensive Python library designed for molecular featurization, providing over 100 pre-trained and hand-crafted featurizers. It unifies the process of converting chemical structures (SMILES strings or RDKit molecules) into robust numerical feature vectors. This capability is essential for advanced cheminformatics tasks, including Quantitative Structure-Activity Relationship (QSAR) modeling, virtual screening, similarity searching, and training deep learning models on molecular data.

PyMC is a powerful Python library designed for probabilistic programming and sophisticated Bayesian modeling. It enables users to build complex models, such as hierarchical structures and time series, and perform rigorous inference using methods like MCMC (NUTS) sampling and Variational Inference. Key features include model comparison (LOO, WAIC) and comprehensive diagnostic tools for uncertainty quantification.

A comprehensive toolkit for building, evaluating, and auditing survival models, specifically handling right-censored and competing-risk outcomes. It supports various models including Cox PH, survival forests, and SVMs, while providing best practices for leakage-safe preprocessing and robust performance evaluation in clinical or scientific ML workflows.

scvi-tools is a comprehensive Python framework utilizing deep generative models and variational inference for analyzing diverse single-cell data modalities. It excels in complex analyses such as probabilistic batch correction (scVI), multi-modal integration (MultiVI), and differential expression analysis with uncertainty. It supports single-cell RNA-seq, ATAC-seq, and various multi-omics datasets, providing advanced tools for modern genomic research.

SHAP (SHapley Additive exPlanations) is a powerful technique used to interpret and audit machine learning model predictions. It calculates feature attributions (SHAP values) to explain how input features map to model outputs. This skill guides users through selecting appropriate explainers, handling multi-output models, validating feature attributions, and generating visualizations for both local and global model understanding.

Statsmodels is a comprehensive Python library for rigorous statistical modeling, enabling deep inference, diagnostics, and advanced econometric analysis. Use it for tasks like linear regression (OLS), generalized linear models (GLM), time series forecasting (ARIMA), and hypothesis testing, providing detailed results for academic and scientific reporting.

This guide details how to set up and execute large-scale, distributed GPU training jobs on the CoreWeave platform. It covers both single-node multi-GPU setups and multi-node training utilizing PyTorch DDP and Kubernetes resources (A100/H100). This workflow is ideal for fine-tuning large language models (LLMs) or running complex deep learning models that require high-performance, shared-storage compute clusters.

A comprehensive tool for creating high-quality training datasets for custom object detection and segmentation models. It supports multiple advanced annotation methods including BBox drawing, SAM2 pixel-perfect segmentation, and DINOv3 visual grounding. Features include AI auto-detection, object tracking, and standardized COCO format export, streamlining the entire data pipeline from capture to training.

This guide provides a comprehensive reference architecture for building production-ready, enterprise-grade applications on Palantir Foundry. It covers the entire data lifecycle, detailing best practices for the standard data pipeline (Raw > Clean > Model), Ontology design, external API integration patterns, and robust multi-layered security models. Use it when designing, planning, or optimizing complex data infrastructure within Foundry.

Provides a systematic guide for diagnosing and improving poor search quality in vector databases like Qdrant. This guide covers troubleshooting issues such as low recall, when approximate search degrades, selecting optimal embedding models, and correctly tuning HNSW parameters, quantization, and filtering strategies. Essential for optimizing RAG and semantic search pipelines.

Master the creation of robust ELT (Extract, Load, Transform) data pipelines within Snowflake. This guide demonstrates advanced data orchestration using Snowflake Streams for Change Data Capture (CDC), Tasks for scheduled transformations and DAG management, and Dynamic Tables for declarative, auto-refreshing data models. Ideal for building sophisticated, scalable data warehousing solutions.

This skill provides comprehensive intelligence across finance and media. Users can search real-time news, analyze media bias across multiple dimensions, get live stock/crypto data with AI forecasts, price financial options using ML models, and synthesize balanced perspectives on current events. It is ideal for deep research, investment analysis, and media literacy.