Data Science & ML Claudeスキル

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment.

RAG Implementation Toolkit

Builds advanced Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search to ground AI responses in proprietary data.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

LLM Application Evaluation

Evaluates Large Language Model application performance using automated metrics, human feedback loops, and LLM-as-judge frameworks.

LangChain Architecture & LLM Development

Architects sophisticated LLM applications using LangChain's agent, memory, and tool integration patterns.

RAG Implementation Guide

Implements robust Retrieval-Augmented Generation systems to connect LLMs with external knowledge bases and vector databases.

Prompt Engineering Patterns

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

MLOps Pipeline Workflow

Builds production-grade MLOps pipelines by orchestrating data preparation, model training, validation, and automated deployment workflows.

Bulk RNA-seq Dataset Curator

Automates the end-to-end processing and curation of bulk RNA-seq datasets for VEuPathDB genomic resources.

Spark Fundamentals & PySpark

Streamlines distributed data processing by providing standardized PySpark patterns and performance best practices.

RAG System Implementation

Build production-grade Retrieval-Augmented Generation (RAG) systems to ground LLM applications in external knowledge.

Bayesian Regression Models

Implements diverse Bayesian regression techniques using Stan and JAGS for advanced statistical modeling and uncertainty quantification.

PyMC 5 Fundamentals

Facilitates the creation, review, and optimization of Bayesian statistical models using the PyMC 5 framework.

Bayesian Model Diagnostics

Evaluates Bayesian model convergence and sampling performance using MCMC diagnostics for Stan and JAGS frameworks.

Bayesian Time Series Models

Implements advanced Bayesian time series analysis using Stan and JAGS for probabilistic forecasting and state-space modeling.

Stan Fundamentals

Provides foundational knowledge for writing, reviewing, and optimizing high-performance Stan 2.37 Bayesian models.

BUGS & JAGS Bayesian Modeling Fundamentals

Master the foundational syntax and precision parameterization required for BUGS and JAGS statistical modeling.

Benchmark Report Creator

Orchestrates the creation of publication-quality AI and ML benchmark reports with high-resolution diagrams and professional PDF exports.

Notebook Creator

Generates standardized Jupyter notebooks for fantasy football data analysis, integrating DuckDB connections, dbt mart queries, and professional visualization patterns.

Advanced Prompt Engineering

Optimizes and orchestrates advanced prompt engineering workflows for Claude 4.5 using industry-best patterns, guardrails, and context management.

Sprint 1 Executor

Executes structured, atomic tasks for fantasy football analytics, FASA optimization, and trade intelligence within a standardized sprint framework.

Bioinformatics Experiment Manager

Manages end-to-end bioinformatics research by orchestrating hypothesis-driven experiment planning, execution, and standardized lab notebook documentation.

TRL Training on Hugging Face

Trains and fine-tunes language models using Transformer Reinforcement Learning methods on fully managed Hugging Face cloud GPU infrastructure.

scArches

Streamlines single-cell omics analysis through deep learning-based data integration, reference mapping, and model surgery techniques.

Scvitools

Analyzes single-cell omics data using deep probabilistic models for integration, batch correction, and differential expression.

CellPhoneDB Analysis

Facilitates single-cell RNA-seq analysis of cell-cell communication and ligand-receptor interactions using the CellPhoneDB framework.

CrewAI

Facilitates the development and orchestration of collaborative multi-agent AI systems and automated workflows.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and experience replay for AI agents using AgentDB's ultra-fast vector storage.

MetaNova NOVA Miner

Facilitates the setup, optimization, and management of molecular mining operations on Bittensor Subnet 68 for decentralized drug discovery.

DS-STAR Data Science Framework

Automates complex data science workflows using a multi-agent architecture and optimized model routing for efficient, iterative data analysis.