Data Science & ML Claude 技能

Seaborn Statistical Visualization

Create publication-quality statistical graphics and complex data visualizations using the Seaborn Python library.

ADK Agent Builder

Architects production-ready autonomous AI agents and multi-agent systems using Google's Agent Development Kit and Claude.

Experiment Design Methodology

Standardizes the creation, execution, and analysis of A/B tests and product experiments to ensure statistical significance and actionable insights.

FlowIO FCS Handler

Parses and manages Flow Cytometry Standard (FCS) files to extract event data, metadata, and convert datasets for scientific analysis.

Multi-Agent System Architecture

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

BioGeoBEARS Biogeographic Analysis

Automates the setup, validation, and execution of phylogenetic ancestral range reconstruction using BioGeoBEARS in R.

Scholar Evaluation

Systematically evaluates research papers and scholarly work using the ScholarEval framework for rigorous academic assessment.

UMAP-Learn Dimensionality Reduction

Performs fast, nonlinear dimensionality reduction to visualize high-dimensional data and optimize machine learning clustering workflows.

ADK Agent Engineer

Engineers production-ready Agent Development Kit (ADK) applications with automated testing, multi-agent orchestration, and GCP deployment.

AGILab Runbook

Standardizes repository workflows for AGILab development, environment management, and AI engineering application deployment.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling and systems biology simulations using the COBRApy framework.

Astropy for Claude

Simplifies astronomical data analysis and astrophysical calculations using the comprehensive Astropy Python library.

Deep Learning Optimizer

Optimizes deep learning models by refining architectures and training parameters to enhance accuracy and reduce resource consumption.

LangChain Architecture

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

ElevenLabs Text-to-Speech

Converts text into high-quality audio files using the ElevenLabs API with customizable voice parameters and presets.

NeuroKit2 Biosignal Analysis

Processes and analyzes complex physiological signals including ECG, EEG, EDA, and more using the NeuroKit2 Python library.

LLM Performance Evaluation

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

Dask Parallel Computing

Scales Python data processing and scientific computing across multiple cores or clusters for datasets that exceed available memory.

Denario Scientific Research Assistant

Automates the complete scientific research lifecycle from initial data analysis to publication-ready LaTeX manuscripts.

Scientific Schematics

Generates publication-quality scientific diagrams and neural network architectures using AI-driven iterative refinement.

NLP Text Analyzer

Analyzes textual data using natural language processing to extract sentiment, keywords, and core topics.

BioServices Bioinformatics Toolbox

Provides programmatic access to over 40 bioinformatics web services and databases for integrated biological data analysis and workflow automation.

scvi-tools for Single-Cell Analysis

Implements probabilistic deep learning models for comprehensive single-cell omics data analysis and multimodal integration.

Matplotlib Scientific Visualization

Generates professional, publication-quality plots and charts using Python's foundational visualization library.

NCBI GEO Data Integration

Accesses and processes gene expression and functional genomics data from the NCBI Gene Expression Omnibus repository.

Data Commons Client

Provides programmatic access to global statistical datasets including demographic, economic, and environmental indicators via the Data Commons API.

Prompt Engineering Patterns

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

Gemini Embeddings Integration

Generates high-performance text embeddings via the Google Gemini API for semantic search, RAG, and data classification tasks.

LLM Evaluation Suite

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

LiteLLM Integration

Simplifies Python-based LLM interactions by providing a unified interface for over 100 cloud and local providers using the OpenAI format.