Discover Agent Skills for data science & ml. Browse 61 skills for Claude, ChatGPT & Codex.
Provides programmatic access and comprehensive analysis of the DrugBank database for pharmaceutical research and bioinformatics workflows.
Provides specialized algorithms and workflows for advanced time series tasks including forecasting, classification, and anomaly detection.
Accesses and interprets the NCBI ClinVar archive to identify genomic variant clinical significance and pathogenicity classifications.
Automates Next-Generation Sequencing (NGS) data processing, quality control, and publication-quality visualization.
Queries the ClinicalTrials.gov API to search for medical studies, retrieve trial details, and export structured clinical research data.
Accesses and analyzes comprehensive pharmaceutical data from DrugBank, including drug properties, interactions, targets, and chemical structures.
Processes and analyzes high-throughput sequencing data to generate publication-quality visualizations and quality control metrics for genomics research.
Provides unified access to 20+ genomic databases for sequence analysis, protein structure prediction, and rapid bioinformatics queries.
Queries and interprets genomic variant data from the NCBI ClinVar database to support clinical genetics and research workflows.
Generates publication-quality scientific visualizations and data plots locally using Python's Matplotlib and Seaborn libraries.
Builds high-performance Retrieval-Augmented Generation systems using vector databases, semantic search, and advanced retrieval patterns.
Queries the Ensembl REST API to retrieve gene annotations, sequences, variants, and comparative genomics data for over 250 species.
Interfaces with NCBI ClinVar to query, interpret, and process human genetic variant clinical significance data for genomic medicine.
Builds end-to-end MLOps pipelines for data preparation, model training, validation, and production deployment.
Trains and deploys sophisticated neural network architectures across distributed E2B sandbox environments.
Accesses and analyzes comprehensive pharmaceutical data from DrugBank including drug properties, interactions, and molecular structures.
Enables professional-grade spreadsheet creation, formula-driven financial modeling, and data analysis with automated error validation.
Performs differential gene expression analysis on bulk RNA-seq data using the PyDESeq2 framework.
Builds end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment.
Automates the end-to-end scientific research lifecycle from data analysis and hypothesis generation to publication-ready LaTeX manuscripts.
Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.
Integrates Reactome's open-source curated pathway database for biological pathway analysis, gene mapping, and systems biology research.
Queries and analyzes over 240 million scholarly works using the OpenAlex database for literature reviews and bibliometric studies.
Generates rigorous, testable scientific hypotheses and detailed experimental designs based on observations and existing literature.
Generates professional, multi-page PDF reports with formatted text, tables, and embedded visualizations using the ReportLab library.
Processes and analyzes mass spectrometry data using Python-based spectral similarity metrics and metadata harmonization.
Searches the arXiv preprint repository for scholarly articles across various scientific and technical domains.
Trains and deploys distributed neural networks within secure E2B sandbox environments using the Flow Nexus framework.
Infers large-scale gene regulatory networks from transcriptomics data using scalable machine learning algorithms like GRNBoost2 and GENIE3.
Provides comprehensive cheminformatics capabilities for molecular analysis, property calculation, and 3D coordinate generation.
Scroll for more results...