Discover Agent Skills for data science & ml. Browse 61 skills for Claude, ChatGPT & Codex.
Simplifies molecular featurization by providing access to over 100 pre-trained embeddings and hand-crafted featurizers for machine learning.
Provides a comprehensive toolkit for creating, manipulating, and analyzing complex network structures and graph algorithms in Python.
Conducts systematic, multi-database literature searches and synthesizes research findings into professionally formatted documents with verified citations.
Processes genomic datasets including sequence alignments, variants, and reference sequences using a Pythonic interface to htslib.
Automates protein sequence optimization and experimental validation through a cloud-based wet-lab platform.
Applies medicinal chemistry filters, drug-likeness rules, and structural alerts for molecular prioritization in drug discovery.
Analyzes the asymptotic stability of dynamical systems using the LaSalle Invariance principle to determine long-term qualitative behavior.
Queries and interprets NCBI ClinVar genetic variant data to provide clinical significance classifications and genomic annotations.
Scales Python data workflows across multiple cores and machines for larger-than-RAM datasets using parallel and distributed computing.
Queries the openFDA API to retrieve comprehensive data on drugs, medical devices, foods, and regulatory actions for safety research and analysis.
Queries the NHGRI-EBI GWAS Catalog to retrieve genetic variants, SNP-trait associations, and comprehensive genomic summary statistics.
Implements advanced survival analysis and time-to-event modeling using the scikit-survival library in Python.
Enables high-performance analysis and visualization of tabular datasets with billions of rows using lazy, out-of-core DataFrames.
Streamlines the implementation, evaluation, and deployment of classical machine learning models using the scikit-learn library.
Accesses and processes NCBI Gene Expression Omnibus (GEO) datasets for transcriptomics and functional genomics analysis.
Enables seamless programmatic access to UniProt for protein sequence retrieval, functional annotation, and biological database ID mapping.
Generates publication-quality static, animated, and interactive visualizations using Python's foundational plotting library.
Provides AI-ready datasets, benchmarks, and molecular oracles for drug discovery and therapeutic machine learning.
Accesses and queries the Catalogue of Somatic Mutations in Cancer (COSMIC) to retrieve genomic data, mutational signatures, and cancer gene census information.
Accesses over 600 scientific tools and datasets to automate research workflows across bioinformatics, genomics, and drug discovery.
Processes and analyzes physiological signals including ECG, EEG, and EDA for psychophysiology research and clinical applications.
Accesses the Kyoto Encyclopedia of Genes and Genomes (KEGG) REST API for biological pathway analysis and molecular interaction mapping.
Transforms academic papers into interactive websites, professional presentation videos, and print-ready conference posters.
Processes and visualizes high-throughput sequencing data (NGS) including ChIP-seq, RNA-seq, and ATAC-seq workflows.
Performs advanced biological computation and molecular biology workflows using the Biopython toolkit.
Manipulates, analyzes, and visualizes phylogenetic trees with support for evolutionary event detection and NCBI taxonomy integration.
Analyzes biological data using specialized tools for sequence manipulation, phylogenetics, and microbial ecology metrics.
Performs constraint-based metabolic modeling and systems biology simulations using the COBRApy Python library.
Enables high-performance data manipulation and analysis using the Polars DataFrame library's lightning-fast expression API.
Performs robust differential gene expression analysis on bulk RNA-seq data using the PyDESeq2 framework.
Scroll for more results...