Data Science & ML Agent Skills

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training through to production deployment and monitoring.

Matchms Mass Spectrometry Analysis

Processes, filters, and analyzes mass spectrometry data for metabolomics research and chemical identification.

RDKit Cheminformatics

Provides comprehensive tools for molecular analysis, chemical property calculation, and 3D structure generation within scientific research workflows.

Hypogenic Hypothesis Generation

Automates scientific hypothesis generation and testing by combining observational data with literature insights using large language models.

HMDB Scientific Database

Accesses the Human Metabolome Database to retrieve chemical properties, clinical biomarkers, and spectral data for metabolomics research.

Astropy for Astronomy

Provides comprehensive Python tools for astronomical data analysis, including celestial coordinates, physical units, and FITS file manipulation.

PyDESeq2 RNA-Seq Analysis

Performs differential gene expression analysis on bulk RNA-seq data using the Python implementation of DESeq2.

BioServices Bioinformatics

Accesses and integrates data from over 40 bioinformatics web services and databases using a unified Python API.

Context Retrieval for AI Memory

Retrieves relevant past episodes and patterns from episodic memory to inform AI decision-making and task execution.

Scientific Data Extractor

Extracts and validates structured data from scientific PDF collections for systematic reviews and meta-analyses.

Phylogenomics Workflow Generator

Automates the generation of scheduler-aware phylogenomic workflows from genome assemblies using single-copy orthologs.

LLM Evaluation Suite

Implements systematic evaluation strategies for Large Language Model applications using automated metrics, LLM-as-judge patterns, and statistical testing.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

LLM Performance Evaluation

Implements comprehensive evaluation frameworks for Large Language Model applications using automated metrics, human feedback, and LLM-as-judge patterns.

LangChain Architecture

Architects sophisticated LLM applications using LangChain patterns for agents, memory management, and retrieval-augmented generation.

Multi-Agent System Architecture

Designs and implements sophisticated multi-agent workflows using modular orchestration patterns, hierarchical delegation, and deterministic tool coordination.

BUSCO Phylogenomics Workflow Generator

Generates comprehensive, scheduler-aware phylogenomics pipelines from genome assemblies using single-copy orthologs.

RAG Implementation Expert

Builds sophisticated Retrieval-Augmented Generation (RAG) systems to ground LLM responses with external knowledge and proprietary data.

LLM Evaluation & Metrics

Implements rigorous evaluation frameworks for Large Language Model applications using automated metrics, LLM-as-judge patterns, and human feedback loops.

Gemini Consultant

Consults Google's Gemini 3 Pro with real-time web search and vision to provide Claude with verified facts and multimodal analysis.

FiftyOne Plugin Developer

Builds custom FiftyOne operators and interactive panels to extend computer vision data workflows.

FiftyOne Python Code Style

Enforces official Voxel51 and FiftyOne Python coding conventions for consistent and maintainable development.

FiftyOne Embeddings Visualization

Visualizes computer vision datasets in 2D using dimensionality reduction to explore data structure, clusters, and outliers.

FiftyOne Duplicate Finder

Detects and manages duplicate or near-duplicate images in FiftyOne datasets using advanced brain similarity computations.

Denario Research Assistant

Automates end-to-end scientific research workflows from data analysis and hypothesis generation to producing publication-ready LaTeX papers.

Matplotlib Visualization

Generates publication-quality scientific visualizations and complex multi-panel plots using Python's foundational Matplotlib library.

Medical Literature Review Assistant

Streamlines systematic literature searches and reference management using PubMed, PICO analysis, and citation metrics.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling, flux balance analysis, and gene knockout simulations for systems biology and metabolic engineering.

GEO Database Access

Accesses and analyzes NCBI Gene Expression Omnibus (GEO) data for transcriptomics and genomics research.

Data Commons Client

Accesses and analyzes global public statistical data from authoritative sources via the Data Commons knowledge graph.