Skill UI

PrimeKG is a comprehensive knowledge graph integrating over 20 primary databases to map complex biological relationships. It allows users to query multiscale data, including genes, drugs, diseases, and phenotypes. Ideal for drug discovery, identifying repurposing opportunities, and analyzing deep disease contexts in network pharmacology.

A powerful Python library for reading, writing, and manipulating DICOM files, the standard format for medical imaging data. Use it for extracting pixel data from various scans (CT, MRI, X-ray), managing complex metadata tags, handling data compression, performing patient data anonymization, and converting medical images to standard formats for research and clinical applications.

A comprehensive Python toolkit for analyzing single-cell RNA-seq data. This skill guides users through the entire workflow, including quality control (QC), normalization, dimensionality reduction (PCA, UMAP, t-SNE), robust cell clustering, and marker gene identification. Ideal for exploratory biological research and generating publication-quality visualizations.

UMAP (Uniform Manifold Approximation and Projection) is a powerful non-linear dimensionality reduction technique used for visualizing high-dimensional data and preprocessing for clustering. It preserves both local and global data structures, offering fast, scalable embeddings. Users can leverage its supervised capabilities by incorporating class labels, making it suitable for advanced machine learning pipelines and data exploration.

Access the U.S. Department of the Treasury's free, open REST API to retrieve comprehensive federal financial data. This tool allows users to query key metrics such as national debt, interest rates, exchange rates, daily treasury statements, and auction data. Built with Python and Pandas, it is perfect for financial analysis, economic monitoring, and tracking public sector finances without needing an API key.

Vaex is a high-performance Python library designed for lazy, out-of-core DataFrames. It enables processing and visualization of massive tabular datasets (billions of rows) that exceed available RAM. Users can perform fast statistics, aggregations, and build robust ML pipelines on big data files (CSV, Parquet, HDF5) without relying on distributed clusters, making it ideal for single-machine, large-scale analytics.

Zarr is a powerful Python library designed for storing large, chunked N-dimensional arrays. It enables efficient, parallel I/O operations, making it ideal for cloud-native and large-scale scientific computing pipelines. It supports seamless integration with established data science tools like NumPy, Dask, and Xarray, and handles remote storage via S3/GCS.

A comprehensive guide to reducing expenses on ClickHouse Cloud. Learn advanced techniques for storage optimization (compression, TTL), compute resource tuning (scaling, thread limits), and query efficiency improvements. Use this when managing data budgets or analyzing high ClickHouse billing charges.

A comprehensive guide and implementation template for building robust data ingestion pipelines into ClickHouse. Supports multiple sources including HTTP webhooks (with batching), Kafka streams, S3, and direct SQL inserts. Demonstrates best practices for data handling, such as deduplication using ReplacingMergeTree and monitoring query logs, ensuring reliable, scalable data analytics.

A robust scheduler designed for orchestrating large-scale, multi-stage Machine Learning experiments on remote GPU servers. It manages complex workflows such as multi-seed grid sweeps, wave transitions, and sequential job chains (e.g., teacher-student distillation). Key features include OOM-aware retries, stale screen cleanup, and race condition prevention, making it ideal when basic single-run scheduling is insufficient for complex batch processing.

This skill provides comprehensive methods and code examples for optimizing spending on Bright Data services. It covers product selection (Proxy vs. API), implementing caching strategies, bulk usage monitoring, and setting budget alerts, ensuring cost efficiency in large-scale web scraping projects.

This comprehensive guide provides advanced workflows for interacting with ClickHouse. It covers efficient bulk data insertion (CSV, JSON), complex analytical querying (funnel analysis, retention), implementing materialized views for pre-aggregation, and utilizing powerful window functions. Ideal for building high-performance OLAP dashboards and executing large-scale data transformations.