Data Science & ML Claude 스킬

ML Pipeline Workflow

Builds and orchestrates end-to-end MLOps pipelines from data preparation through production deployment.

Scikit-bio Bioinformatics Toolkit

Analyzes biological data including sequences, phylogenetic trees, and microbial community diversity using the scikit-bio Python library.

Python Experiment Tracking

Organizes Python research code by implementing consistent logging, metadata tracking, and result comparison workflows.

RAG System Implementation

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

LangChain Architecture Design

Architects sophisticated LLM applications using the LangChain framework for agents, memory management, and complex tool integration.

Single-Cell Omics Analysis (scvi-tools)

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

ML Model Deployment Helper

Automates the productionization and deployment of machine learning models into scalable environments using FastAPI, Docker, and Kubernetes.

Classification Model Builder

Automates the end-to-end creation, evaluation, and deployment of machine learning classification models from natural language requests.

Airflow Workflow Architect

Designs, optimizes, and implements robust Apache Airflow DAGs using industry-standard operators and scheduling best practices.

OMERO Microscopy Integration

Manages microscopy data and metadata via the OMERO Python API for scientific imaging and high-content screening workflows.

Data Versioning Refactor

Implements lightweight dataset tracking and reproducibility patterns to ensure data changes are explicit and traceable.

FiftyOne Image Deduplication

Identifies and removes duplicate or visually similar images in FiftyOne datasets using deep learning embeddings.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and experience replay for AI agents using the AgentDB vector engine.

Scanpy Single-Cell Analysis

Performs comprehensive single-cell RNA-seq analysis workflows including quality control, clustering, and trajectory inference.

Prompt Engineering Patterns

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

Biopython Bioinformatics Toolkit

Automates computational molecular biology tasks including sequence manipulation, NCBI database queries, and structural analysis.

Advanced Excel & Spreadsheet Manager

Manages complex Excel workbooks with automated formula recalculation, professional financial modeling standards, and deep data analysis capabilities.

Denario Scientific Research Assistant

Automates the end-to-end scientific research lifecycle from initial data hypothesis to publication-ready LaTeX manuscripts.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques to optimize LLM performance, reliability, and structured output in production environments.

Oracle Agent Spec Expert

Designs framework-agnostic, portable AI agents and multi-agent workflows using Oracle's Open Agent Specification.

Prompt Engineering Patterns

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

Dask Parallel Computing

Enables parallel and distributed computing in Python to scale pandas and NumPy workflows across multiple cores or clusters for larger-than-memory datasets.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to improve retrieval accuracy in RAG systems and search engines.

Agent Workflow Patterns

Implements sophisticated autonomous agent architectures and workflow patterns using the Vercel AI SDK.

LangChain Application Architect

Designs and implements sophisticated LLM applications using LangChain's framework for agents, memory, and complex workflows.

PubChem Database Integration

Accesses the PubChem database to query over 110 million chemical compounds, retrieve molecular properties, and perform advanced structural searches.

Nixtla Research Assistant

Monitors and summarizes the Nixtla forecasting ecosystem to provide actionable updates on TimeGPT, StatsForecast, and MLForecast.

Vector Similarity Search Patterns

Implement high-performance similarity search and vector retrieval patterns across multiple database providers.

Medical Symptom Analysis

Transforms raw medical consultation data into structured health assessments and actionable care recommendations.

Portfolio Risk Metrics Calculation

Calculates comprehensive financial risk metrics including VaR, CVaR, Sharpe, and Sortino ratios for quantitative portfolio management.