Data Science & ML Agent Skills

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling and simulation for systems biology and metabolic engineering applications.

Hypogenic Scientific Hypothesis Generator

Automates the generation, refinement, and testing of scientific hypotheses using data-driven insights and literature integration.

Plotly Data Visualization

Generates interactive, publication-quality data visualizations and dashboards using the Plotly Python library.

NeuroKit2 Biosignal Analysis

Processes and analyzes complex physiological signals including ECG, EEG, and EDA using a comprehensive Python toolkit.

Metabolomics Workbench Database

Accesses the NIH Metabolomics Workbench to query metabolite data, study metadata, and standardized chemical nomenclature.

NCBI GEO Genomics Database

Accesses and analyzes gene expression and functional genomics data from the NCBI Gene Expression Omnibus repository.

Scientific Literature Review

Conducts systematic, comprehensive literature reviews across major scientific databases with verified citations and professional document generation.

Pymatgen Materials Genomics

Enables comprehensive materials analysis, crystal structure manipulation, and Materials Project database integration for computational materials science.

scvi-tools Assistant

Analyzes single-cell omics data using the scvi-tools framework for probabilistic modeling and batch correction.

Qiskit Quantum Computing

Builds, optimizes, and executes quantum circuits and algorithms across various hardware backends and simulators.

Biopython Molecular Biology

Streamlines computational molecular biology tasks including sequence analysis, NCBI database queries, and structural bioinformatics using the Biopython toolkit.

SimPy Simulation Engine

Builds complex discrete-event simulations in Python for modeling processes, resource contention, and time-based systems.

SymPy Symbolic Math

Performs exact symbolic mathematical computations including algebra, calculus, and equation solving using the SymPy library.

Histolab Pathology Toolkit

Processes and prepares gigapixel whole slide images for digital pathology and machine learning workflows.

AgentDB Vector Search

Implements high-performance semantic vector search and intelligent document retrieval using AgentDB's optimized vector engine.

arXiv Research Search

Searches the arXiv repository to retrieve and summarize the latest scholarly articles in STEM fields.

ESM Protein Design & Modeling

Enables advanced protein engineering through generative design, structure prediction, and high-performance embeddings using ESM3 and ESM C models.

Adaptyv Protein Validation

Automates the submission and validation of protein designs to a cloud-based wet-lab for experimental testing and sequence optimization.

Adaptyv Protein Lab

Streamlines protein sequence design and wet-lab validation through automated cloud laboratory testing and sequence optimization.

Financial Modeling Suite

Builds advanced financial models including DCF analysis, sensitivity testing, and Monte Carlo simulations for data-driven investment decisions.

DrugBank Database Analysis

Accesses and analyzes comprehensive pharmaceutical data from the DrugBank database for drug discovery, pharmacology, and interaction research.

DeepChem Molecular ML

Applies machine learning to chemistry, materials science, and biology for drug discovery and molecular property prediction.

COBRApy Metabolic Modeling

Performs constraint-based reconstruction and analysis of metabolic models for systems biology and metabolic engineering.

FlowIO Flow Cytometry Handler

Parses and writes Flow Cytometry Standard (FCS) files, enabling seamless conversion of biological data into NumPy arrays and dataframes for scientific analysis.

AnnData Scientific Data Management

Manages annotated data matrices and single-cell genomics datasets using the AnnData Python framework and scverse ecosystem.

Financial Statement Analysis

Calculates and interprets key financial ratios from company statements to facilitate investment analysis and performance benchmarking.

Moon Dev AI Trading Agents

Orchestrates 48+ specialized AI agents for autonomous cryptocurrency trading, market analysis, and backtesting across multiple exchanges.

DeepChem Molecular ML

Enables advanced molecular machine learning and drug discovery workflows using specialized featurizers and graph neural networks.

COSMIC Cancer Database Integration

Access and download somatic mutation data from the COSMIC database for cancer research and bioinformatics pipelines.

ClinicalTrials.gov Data Integrator

Queries and analyzes clinical trial data from the official ClinicalTrials.gov API v2 for research and patient matching.