Data Science & ML Agent Skills

Histolab Pathology Processing

Automates digital pathology image processing and tile extraction for whole slide images in deep learning pipelines.

Qiskit Quantum Computing

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

Plotly Visualization

Generates interactive, publication-quality scientific and statistical visualizations using the Plotly Python library.

Adaptyv Protein Engineering

Streamlines automated protein testing and validation through cloud-based laboratory workflows and sequence optimization tools.

Opentrons Lab Automation

Automates laboratory liquid handling by generating Python Protocol API v2 scripts for Flex and OT-2 robots.

Prompt Optimizer

Optimizes Large Language Model prompts to minimize token usage, reduce operational costs, and enhance response quality.

Metabolomics Workbench Database

Connects Claude to the NIH Metabolomics Workbench for comprehensive access to metabolite data, study metadata, and mass spectrometry search capabilities.

PyTorch Lightning ML Framework

Organizes and scales PyTorch code into modular, high-performance deep learning workflows with minimal boilerplate.

AI Model Version Tracker

Manages and tracks machine learning model versions, performance metrics, and lineage directly within Claude Code.

Pymatgen Materials Science Toolkit

Performs advanced materials analysis, crystal structure manipulation, and Materials Project database integration for computational scientists.

MedChem Molecular Triage

Applies medicinal chemistry rules and structural filters to prioritize and triage molecular libraries for drug discovery.

SymPy Symbolic Math

Performs exact symbolic mathematics in Python, including calculus, algebra, and complex equation solving.

Computer Vision Processor

Automates image analysis, object detection, and classification workflows directly within Claude Code.

ZINC Database Search

Accesses the ZINC repository of over 230 million purchasable compounds to streamline virtual screening and drug discovery workflows.

Clinical Report Writing

Generates standardized, regulatory-compliant clinical documentation and medical reports following global healthcare guidelines.

AI RAG Vectors & Semantic Search

Integrates a vector embedding layer into Next.js applications using pgvector and AI Gateway for high-performance semantic search and retrieval.

Excel Pivot Wizard

Generates professional Excel pivot tables and visualizations from raw data using simple natural language commands.

Regression Analysis & Modeling

Automates regression modeling and data analysis to identify relationships between variables and predict future trends.

Time Series Forecaster

Predicts future values and identifies patterns in historical time-dependent data using advanced statistical models.

Aeon Time Series ML

Provides a comprehensive toolkit for time series machine learning including classification, forecasting, and anomaly detection using scikit-learn compatible APIs.

AI RAG Chat

Implements a complete Retrieval-Augmented Generation (RAG) chat interface with vector search and document citations.

Senior ML Engineer

Productionizes machine learning models and builds scalable MLOps systems with world-class engineering standards.

Vertex AI Media Master

Automates complex Google Vertex AI multimodal operations for advanced video processing, high-fidelity image generation, and end-to-end marketing campaign orchestration.

ML Experiment Tracking Setup

Automates the integration and configuration of experiment tracking tools like MLflow and Weights & Biases for machine learning projects.

Transfer Learning Adapter

Automates the fine-tuning and adaptation of pre-trained machine learning models for specific tasks and new datasets.

Benchling R&D Integration

Integrates Claude with the Benchling R&D platform to automate lab data management, registry entities, and inventory workflows via Python SDK and REST API.

Arboreto Gene Network Inference

Infers large-scale gene regulatory networks from transcriptomics data using scalable algorithms like GRNBoost2 and GENIE3.

BioRxiv Scientific Database Search

Enables efficient searching, metadata retrieval, and PDF downloads from the bioRxiv preprint server for life sciences research.

Clinical Decision Support

Generates publication-ready clinical decision support documents, biomarker-stratified cohort analyses, and evidence-based treatment guidelines.

Data Preprocessing Pipeline

Builds and executes automated ETL pipelines for cleaning, validating, and transforming raw datasets into model-ready formats.