Data Science & ML Agent Skills

OpenAlex Academic Database

Queries and analyzes over 240 million scholarly works, authors, and institutions using the OpenAlex API.

L-Space Narrative & Causality Analyzer

Extracts narrative arcs, measures token novelty, and generates causality graphs from text and code repositories.

COBRApy Metabolic Modeling

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

Invariant Measure Analysis

Analyzes dynamical systems to identify measures preserved by flow and evaluate qualitative stability behavior.

Matplotlib Data Visualization

Create publication-quality charts, graphs, and complex data visualizations using Python's foundational plotting library.

Dask Parallel Computing

Scales Python data workflows for parallel and distributed computing across larger-than-memory datasets.

Single-Cell Genomics Analysis (scvi-tools)

Analyzes single-cell omics data using probabilistic models for tasks like batch correction, dimensionality reduction, and differential expression.

Louisville Quantum Gravity

Analyzes and implements stationary measures for the KPZ equation using Liouville quantum gravity and matrix product ansatz.

DisCoPy Categorical Computing

Implements compositional string diagrams and operadic structures for categorical computing and active inference.

Meta Prompt Creator

Generates high-performance, structured prompts for LLMs using research-backed techniques like XML tagging, few-shot examples, and chain-of-thought reasoning.

Scikit-Survival Analysis

Performs advanced survival analysis and time-to-event modeling using the scikit-survival Python library.

UniProt Protein Database Access

Accesses the UniProt REST API to perform comprehensive protein searches, sequence retrieval, and cross-database identifier mapping.

Hypogenic AI Hypothesis Generator

Automates scientific hypothesis generation and empirical testing using large language models and research literature integration.

Senior Data Scientist

Empowers developers with expert-level statistical modeling, experiment design, and production-grade machine learning workflows.

Geniml Genomic ML

Applies machine learning to genomic interval data for training region embeddings, analyzing scATAC-seq, and building consensus peak universes.

PufferLib Reinforcement Learning

Accelerates reinforcement learning workflows through high-performance parallel environment simulation and optimized PPO training.

Chaotic Attractor Dynamics

Analyzes complex dynamical systems and strange attractors with sensitive dependence on initial conditions.

PyDESeq2 Gene Expression Analysis

Performs comprehensive differential gene expression analysis on bulk RNA-seq data using the PyDESeq2 framework.

GMRA Multi-Resolution Analysis

Performs high-dimensional geometric multi-resolution analysis with deterministic local reconstructability across MATLAB, Julia, and Python.

Algorithm Extraction & Documentation

Extracts and structures algorithm pseudocode from academic research papers into actionable implementation plans.

Haskell Diagrams DSL

Generates complex declarative vector graphics and scientific visualizations using the Haskell Diagrams embedded domain-specific language.

Replicate CLI

Interacts with the Replicate AI platform to run models, manage deployments, and perform fine-tuning directly from the command line.

Hylang Message Regime Analyzer

Analyzes and predicts message stream patterns using triadic GF(3) classification and Hylang-based regime detection.

scikit-bio Bioinformatics Toolkit

Processes and analyzes biological data using scikit-bio for sequence alignment, phylogenetics, and microbiome diversity studies.

Biopython Molecular Biology

Automates biological computation tasks including sequence analysis, structural bioinformatics, and programmatic NCBI database access.

Bioinformatics & Genomic Data (gget)

Provides unified access to over 20 genomic databases for sequence analysis, protein structure prediction, and gene expression queries.

Bifurcation Generator

Generates visual bifurcation diagrams to analyze parameter-dependent transitions in dynamical systems.

Transcritical Dynamics

Models and analyzes dynamical systems where stability exchanges between equilibria during bifurcation events.

Lyapunov Function Analysis

Analyzes the stability and qualitative behavior of dynamical systems using scalar functions that decrease along trajectories.

Pysam Genomic Toolkit

Manipulates and analyzes genomic datasets including SAM, BAM, VCF, and FASTA files using a Pythonic interface to htslib.