Data Science & ML Claude 技能

Universal Data Transformation

Transforms, cleans, and reshapes complex datasets locally using industry-standard Python libraries like pandas and numpy.

RDKit Cheminformatics

Provides comprehensive cheminformatics capabilities for molecular analysis, property calculation, and 3D coordinate generation.

Gtars Genomic Toolkit

Accelerates genomic interval analysis and machine learning preprocessing using a high-performance Rust-based toolkit with Python bindings.

AgentDB Vector Search

Implement high-performance semantic search and vector storage for intelligent document retrieval and RAG systems.

Excel Data Analysis & Reporting

Automates Excel spreadsheet analysis, data manipulation, and visual reporting using Python-based data science libraries.

Gtars Genomic Analysis Toolkit

Processes and analyzes high-performance genomic interval data using Rust-powered algorithms and Python bindings.

Scientific Critical Thinking

Evaluates research rigor and methodology to provide deep critical analysis of scientific claims and evidence quality.

Universal Data Transformation

Transforms, cleans, and reshapes complex datasets locally using industry-standard Python libraries like pandas and numpy.

HMDB Metabolome Database

Accesses and analyzes the Human Metabolome Database to retrieve detailed metabolite information, chemical properties, and clinical biomarkers.

HMDB Metabolome Database Access

Accesses and analyzes the Human Metabolome Database to retrieve metabolite data, chemical properties, and clinical biomarkers.

GWAS Database Explorer

Facilitates programmatic access and querying of the NHGRI-EBI GWAS Catalog for genetic variant and trait associations.

NCBI Gene Database Integration

Queries the NCBI Gene database to retrieve comprehensive genetic information, metadata, and sequences for annotation and functional analysis.

NCBI Gene Database Skill

Queries NCBI Gene databases to retrieve comprehensive genomic data, including sequences, annotations, and functional pathways.

AI Multimodal Processing

Processes and generates multimedia content including audio, video, images, and documents using the Google Gemini API.

NeuroKit2 Biosignal Analysis

Processes and analyzes physiological signals like ECG, EEG, and EDA using the NeuroKit2 Python library.

ETE Phylogenetic Toolkit

Manipulates, analyzes, and visualizes phylogenetic and hierarchical tree structures for phylogenomics and clustering research.

Adaptyv Protein Engineering

Automates protein sequence optimization and experimental validation through cloud-based laboratory testing.

Denario AI Research Orchestrator

Automates end-to-end scientific research workflows from initial data analysis and hypothesis generation to the production of publication-ready LaTeX manuscripts.

ENA Bioinformatics Database

Accesses and retrieves genomic data from the European Nucleotide Archive (ENA) via REST APIs and FTP for bioinformatics pipelines.

Benchling Integration

Automates life sciences R&D workflows by integrating Benchling's registry, inventory, and electronic lab notebook via API and Python SDK.

DiffDock Molecular Docking

Predicts 3D protein-ligand binding poses using diffusion-based deep learning for structure-based drug design.

PyTorch Geometric (PyG) for Claude

Implements high-performance Graph Neural Networks and geometric deep learning architectures using the PyTorch Geometric library.

Modal Cloud Computing

Executes Python code in serverless cloud containers with automatic scaling and high-performance GPU support.

Financial Statement Analysis

Calculates and interprets comprehensive financial ratios from balance sheets and income statements to provide actionable investment insights.

Model Registry Maintainer

Maintains and updates model registries, pricing, and capabilities for AI providers within the MassGen ecosystem.

Prompt Engineering

Implements advanced prompting patterns and psychological persuasion principles to maximize LLM performance, reliability, and controllability.

Dagster Expert

Provides expert guidance for building, managing, and orchestrating data pipelines with Dagster and the dg CLI.

LTV Predictor & RFM Analytics

Predicts customer lifetime value and performs RFM analysis using regression algorithms for e-commerce and retail data.

Funnel Analysis

Analyzes multi-step user conversion journeys to identify bottlenecks and optimize business growth metrics.

RFM Customer Segmentation Analyst

Performs automated RFM analysis and K-means clustering on e-commerce transaction data to identify and rank high-value customer segments.