Data Science & ML Claude 技能

Advanced Excel & Spreadsheet Automation

Automates professional spreadsheet creation, data analysis, and financial modeling with rigorous formula validation.

PennyLane Quantum Computing

Builds, trains, and optimizes quantum circuits with hardware-agnostic execution and deep integration with popular machine learning frameworks.

KEGG Database Connector

Accesses the Kyoto Encyclopedia of Genes and Genomes (KEGG) REST API for biological pathway analysis and molecular interaction networks.

Pydicom Medical Imaging

Processes and manipulates DICOM medical imaging data for analysis, anonymization, and format conversion.

LaminDB Data Framework

Manages biological data and workflows with integrated lineage tracking, ontology validation, and FAIR compliance.

PyOpenMS Mass Spectrometry

Analyzes mass spectrometry data for proteomics and metabolomics using the PyOpenMS library.

Polars Data Processing

Performs high-performance data manipulation and analysis using the lightning-fast Polars DataFrame library and Apache Arrow.

ESM Protein Modeling

Enables advanced protein sequence generation, structure prediction, and representation learning using Evolutionary Scale Modeling.

Agilab Streamlit Pages

Enforces robust Streamlit authoring patterns for session state management, widget key hygiene, and high-performance UI development within the AGILAB framework.

USPTO Database & IP Analysis

Interfaces with United States Patent and Trademark Office (USPTO) APIs to perform advanced patent searches, trademark tracking, and intellectual property analysis.

Machine Learning Model Evaluation Suite

Analyzes and benchmarks machine learning models using a comprehensive suite of performance metrics and validation tools.

ChEMBL Database Explorer

Queries the ChEMBL database to retrieve bioactive molecule data, drug targets, and bioactivity measurements for medicinal chemistry research.

PathML Pathology Analysis

Analyzes whole-slide images and multiparametric data using specialized computational pathology workflows and machine learning models.

LLM Evaluation & Metrics

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

RAG Implementation Expert

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

Machine Learning Model Evaluation Suite

Assesses machine learning model performance using comprehensive metrics to facilitate validation, testing, and optimization workflows.

Data Visualization Creator

Generates professional plots, charts, and graphs from raw data with intelligent, automatic visualization type selection.

AI Recommendation Engine Builder

Builds sophisticated recommendation systems using collaborative filtering, content-based algorithms, and hybrid machine learning models.

Vaex Big Data Analysis

Processes and analyzes massive tabular datasets exceeding RAM limits using high-performance out-of-core DataFrames.

CZ CELLxGENE Census Data Analysis

Enables programmatic access and analysis of the CZ CELLxGENE Census, a collection of over 61 million standardized single-cell genomics records.

Statsmodels Statistical Analysis

Performs rigorous statistical modeling and econometric analysis using Python's statsmodels library for deep data insights.

NetworkX Graph Analysis

Analyzes, visualizes, and manipulates complex network structures and graph data using the NetworkX Python library.

Model Explainability Tool

Provides deep interpretability and explainability for machine learning models using advanced techniques like SHAP and LIME.

PyLabRobot Lab Automation

Automates laboratory workflows and controls liquid handling robots and analytical equipment through a hardware-agnostic Python interface.

Codex CLI Integration

Integrates Codex CLI command patterns into Claude Code to enable advanced multi-agent planning and high-reasoning execution.

Excel Variance Analyzer

Automates budget vs. actual financial variance analysis with professional reporting, materiality flagging, and executive summaries.

Model Versioning Tracker

Tracks and manages AI/ML model versions, performance metrics, and lineage for streamlined model registry management.

Scientific Critical Thinking

Evaluates research rigor and methodology through systematic assessment of statistical validity, biases, and evidence quality.

Machine Learning Feature Engineering

Optimizes machine learning model performance by automating feature creation, selection, and complex data transformations.

ClinVar Database Assistant

Queries and interprets NCBI ClinVar data to provide standardized genetic variant classifications and clinical significance evidence.