Data Science & ML Claude 技能

Plotly Interactive Visualization

Generates interactive, publication-quality Python charts and dashboards for data exploration and presentation.

Prompt Engineering Patterns

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

PyTorch Geometric (PyG)

Develops and trains Graph Neural Networks (GNNs) for node classification, link prediction, and geometric deep learning tasks.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

LangChain Architecture

Designs and implements sophisticated LLM applications using the LangChain framework for complex AI workflows.

Morgus Research & Deep Analysis

Conducts systematic, high-rigor research and data synthesis to transform raw information into actionable insights and structured reports.

AgentDB Learning Plugins

Implements and trains advanced reinforcement learning algorithms to create autonomous agents that evolve through experience.

Scikit-learn Machine Learning

Builds, evaluates, and deploys production-ready machine learning models using the industry-standard scikit-learn library.

Flow Nexus Neural Networks

Trains and deploys complex neural network architectures within distributed E2B sandbox environments for scalable machine learning workflows.

SHAP Model Explainability

Explains machine learning model predictions and feature importance using SHAP values and comprehensive visualizations.

Bayesian Survival Models

Implements robust Bayesian survival analysis models including Weibull and Cox-like piecewise hazards with censoring support.

Polars Data Engineering

Accelerates data manipulation and ETL pipelines with the high-performance Polars DataFrame library.

Excel & Data Analysis Toolkit

Creates, edits, and analyzes Excel spreadsheets with professional formatting, automated formula recalculation, and integrated data visualization.

Bayesian Meta-Analysis

Implements robust Bayesian meta-analysis models using Stan and JAGS to synthesize data across multiple studies with advanced statistical precision.

RAG Implementation & Optimization

Builds and optimizes Retrieval-Augmented Generation (RAG) systems using advanced vector search, semantic chunking, and retrieval patterns.

ReasoningBank AgentDB Adaptive Learning

Implements high-performance adaptive learning and memory distillation for self-improving AI agents using AgentDB.

FRED Economic Data

Queries the Federal Reserve Economic Data (FRED) API to retrieve over 800,000 economic time series for financial research and macroeconomic analysis.

Embedding Comparison

Evaluates and benchmarks different embedding models to optimize semantic search and vector retrieval performance on your specific data.

PyMC Bayesian Modeling

Streamlines the creation, fitting, and validation of Bayesian models using PyMC's modern probabilistic programming interface.

Cirq Quantum Computing

Designs, simulates, and executes quantum circuits using Google's Cirq framework for NISQ-era hardware and noise-aware algorithms.

Data Commons Client

Provides programmatic access to global statistical data for demographic, economic, and environmental research.

Denario Scientific Research Assistant

Automates the end-to-end scientific research pipeline from hypothesis generation and data analysis to publication-ready LaTeX manuscripts.

Adaptyv Protein Design & Validation

Automates protein testing and validation through a cloud-based laboratory platform for accelerated biotechnological research and sequence optimization.

Agent Builder

Orchestrates the development of complete, production-ready Claude Code agents using Anthropic's official best practices for context engineering and tool design.

PyTDC (Therapeutics Data Commons)

Accesses AI-ready drug discovery datasets and benchmarks for therapeutic machine learning and pharmacological prediction.

ENA Database Access

Retrieves nucleotide sequences, raw sequencing reads, and metadata from the European Nucleotide Archive for genomics research.

Unsloth Model Inference

Deploys and optimizes fine-tuned LLMs using native Unsloth kernels, vLLM, or SGLang for high-performance production serving.

Advanced Excel & Financial Modeling

Creates, edits, and analyzes professional Excel workbooks with dynamic formulas, automated recalculation, and industry-standard formatting.

Modal Cloud Compute

Deploys and runs Python applications on serverless cloud infrastructure with automatic scaling and GPU acceleration.

PathML Computational Pathology

Processes and analyzes whole-slide pathology images using advanced machine learning, spatial graph construction, and multiparametric imaging workflows.