Data Science & ML Agent Skills

PDF Report Generator

Generates professional, multi-page PDF reports with formatted tables, text, and embedded data visualizations using the reportlab library.

Matplotlib Visualization

Generates professional, publication-quality plots and data visualizations using Python's foundational plotting library.

Excel Analysis

Automates Excel spreadsheet manipulation, data analysis, and professional reporting using Python-based data science libraries.

AgentDB Vector Search

Implement high-performance semantic search and vector storage for intelligent document retrieval and RAG systems.

GEO Database Access

Access and analyze NCBI Gene Expression Omnibus (GEO) data for transcriptomics and functional genomics research.

FDA Database Access

Queries the openFDA API to retrieve and analyze data on drugs, medical devices, food safety, and adverse events.

scvi-tools Single-Cell Genomics Analysis

Analyzes single-cell omics data using deep generative models for batch correction, integration, and differential expression.

ToolUniverse Scientific Research

Accesses over 600 scientific tools and databases for bioinformatics, drug discovery, and computational biology research.

Bioinformatics Services (BioServices)

Accesses over 40 bioinformatics web services and databases through a unified Python interface for biological data retrieval and analysis.

ArXiv Research Search

Searches the arXiv preprint repository for scholarly articles in computer science, physics, mathematics, and quantitative biology.

Arboreto GRN Inference

Infers gene regulatory networks from transcriptomics data using scalable GRNBoost2 and GENIE3 algorithms.

Datamol Cheminformatics

Simplifies complex molecular informatics workflows by providing a Pythonic interface for RDKit with sensible defaults and built-in parallelization.

Datamol Cheminformatics

Simplifies molecular cheminformatics and drug discovery workflows with a Pythonic abstraction layer over RDKit.

Datamol Cheminformatics

Simplifies molecular cheminformatics and drug discovery workflows using a Pythonic interface for RDKit.

SimPy Simulation Modeling

Builds discrete-event simulation models in Python to analyze complex systems involving queues, resources, and time-based processes.

AgentDB Vector Search

Implement high-performance semantic vector search and intelligent document retrieval using AgentDB optimized HNSW indexing and quantization.

PyHealth Clinical AI Toolkit

Develops, tests, and deploys machine learning models for clinical healthcare data using standardized pipelines and specialized medical architectures.

Pinecone Vector Database

Integrates managed vector databases into AI applications for production-grade RAG, semantic search, and recommendation systems.

deepTools NGS Analysis

Analyzes high-throughput sequencing data to perform quality control, normalization, and publication-quality visualization for NGS experiments.

COBRApy Metabolic Modeling

Simulates and analyzes genome-scale metabolic models using constraint-based reconstruction and analysis (COBRA) techniques.

SimPy Simulation Engine

Builds process-based discrete-event simulations in Python for modeling complex systems like logistics, manufacturing, and networks.

Biomni Biomedical AI Agent

Executes complex autonomous research tasks across genomics, drug discovery, and clinical analysis using integrated biomedical databases.

ENA Bioinformatics Database

Accesses the European Nucleotide Archive (ENA) to retrieve genomic sequences, raw reads, and metadata for bioinformatics pipelines.

Cirq Quantum Computing

Builds, simulates, and executes quantum circuits using Google’s open-source framework for NISQ-era quantum computers.

Excel Analysis

Analyzes Excel spreadsheets, generates pivot tables, and creates data visualizations using Python libraries like pandas and openpyxl.

AgentDB Vector Search

Integrates high-performance semantic vector search and HNSW indexing for intelligent document retrieval and RAG systems.

AgentDB Vector Search

Implements ultra-high-performance semantic vector search and document retrieval for Claude-powered RAG systems and intelligent knowledge bases.

AI Multimodal Processing

Processes and generates audio, video, images, and complex documents using Google Gemini's advanced multimodal API capabilities.

Benchling Integration

Integrates Benchling’s R&D platform with Claude to automate life sciences workflows, manage biological registries, and streamline lab data operations.

Adaptyv Protein Engineering

Automates protein sequence optimization and experimental validation through cloud-based laboratory testing.