Data Science & ML Agent Skills

Senior Data Scientist

Empowers Claude to design rigorous statistical experiments, build predictive models, and implement production-grade MLOps pipelines.

ClinicalTrials.gov Database

Queries the ClinicalTrials.gov API v2 to search, filter, and export comprehensive clinical trial data for research and analysis.

LangChain4j RAG Implementation Patterns

Implements robust Retrieval-Augmented Generation (RAG) systems using the LangChain4j framework to enhance Java-based AI applications with external knowledge.

Similarity Search Patterns

Implements high-performance similarity search and vector retrieval patterns for RAG and semantic search applications.

LLM Embedding Strategies

Optimizes vector search and RAG applications through strategic embedding model selection, chunking, and pipeline implementation.

Vector Index Tuning

Optimizes vector database performance by tuning HNSW parameters, implementing quantization, and balancing latency against recall.

Pymoo Optimization Framework

Solves complex single and multi-objective optimization problems using state-of-the-art evolutionary algorithms and visualization tools.

PyTorch Lightning Deep Learning

Simplifies and scales neural network development by organizing PyTorch code into modular, production-ready structures.

LangChain4j Tool & Function Calling

Implements robust tool and function calling patterns for Java-based AI agents using the LangChain4j framework.

Pysam Genomic Toolkit

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

ClinVar Database Integration

Queries and interprets NCBI ClinVar data to evaluate genetic variant pathogenicity and clinical significance for genomic medicine.

gget Bioinformatics Toolkit

Enables rapid bioinformatics queries and sequence analysis across 20+ genomic databases directly from your terminal or Python scripts.

Polars Data Engineering

Accelerates high-performance data processing and analysis using the Polars DataFrame library and Apache Arrow.

Seaborn Statistical Visualization

Generates professional, publication-quality statistical graphics and data visualizations directly from Python DataFrames.

Literature Review Assistant

Conducts systematic, academic-grade literature reviews and research syntheses across major scientific and technical databases.

Neuropixels Data Analysis

Streamlines high-density extracellular electrophysiology workflows from raw recording ingestion to publication-ready unit curation.

LabArchives Integration

Automates Electronic Lab Notebook workflows through the LabArchives REST API for research data management and backup.

Scientific Brainstorming

Empowers researchers to generate novel hypotheses, explore interdisciplinary connections, and overcome creative blocks through collaborative ideation.

PubChem Chemical Informatics

Queries the PubChem database to retrieve chemical structures, molecular properties, and bioactivity data for cheminformatics workflows.

Scientific Compute Resource Analyzer

Detects and analyzes system hardware to provide optimized strategic recommendations for scientific computing and data processing tasks.

RAG Chunking Strategy

Implements advanced document chunking strategies to optimize retrieval-augmented generation (RAG) performance and embedding accuracy.

Cirq Quantum Computing

Builds, simulates, and optimizes quantum circuits for various quantum hardware platforms using Google's Cirq framework.

OMERO Microscopy Integration

Manages and analyzes microscopy data using the OMERO Python API for advanced bioimage informatics workflows.

Genomic Tools and Analysis in Rust (Gtars)

Provides high-performance tools for genomic interval analysis, interval overlap detection, and machine learning tokenization using Rust.

Prompt Engineering Patterns

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

SHAP Model Interpretability

Simplifies machine learning model interpretation by generating SHAP values and visualizations for model transparency and debugging.

FDA Regulatory Data Access

Queries and analyzes openFDA data for drugs, medical devices, food safety, and adverse events using a standardized Python interface.

PDF Processing Pro

Automates production-grade PDF workflows including form filling, table extraction, and OCR processing.

Therapeutics Data Commons (PyTDC)

Facilitates drug discovery and therapeutic machine learning by providing AI-ready datasets, benchmarks, and molecular evaluation oracles.

LangChain Architecture Pro

Architects sophisticated LLM applications using LangChain's agents, memory systems, and complex chain integration patterns.