Data Science & ML Claude 스킬

LLM Application Evaluation

Implement comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and benchmarking.

RAG Implementation & Vector Search

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

Prompt Engineering Patterns

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

MLOps Pipeline Workflow

Orchestrates end-to-end machine learning pipelines from data preparation and training to production deployment and monitoring.

LangChain Architecture

Builds sophisticated LLM applications using LangChain's agents, memory management, and complex chain patterns.

Flow Nexus Neural Networks

Trains and deploys complex neural networks across distributed E2B sandbox environments using custom architectures or pre-built templates.

DBF Data Analysis & Conversion

Analyzes legacy Thai DBF accounting databases by converting them to Parquet for high-performance DuckDB querying.

LLM Evaluation & Benchmarking

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

ReasoningBank Intelligence

Empowers AI agents with adaptive learning and pattern recognition to optimize workflows and decision-making strategies through experience.

Advanced Excel & Spreadsheet Manager

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and industry-standard financial modeling.

NCI Manipulation Analysis

Detects narrative manipulation and propaganda patterns in text and URLs using the Narrative Credibility Index (NCI) Protocol.

Vector Awkward HEP Analysis

Simplifies High Energy Physics analysis by integrating Python vector libraries with Awkward Arrays for efficient kinematic calculations.

Databento Market Data Analysis

Accesses and analyzes ES/NQ futures market data using Databento's high-fidelity platform with a cost-optimized workflow.

Prompt Engineering Expert

Crafts production-ready LLM prompts, agent definitions, and system instructions optimized for Claude and GPT models.

Excel Analysis

Analyzes, cleans, and visualizes Excel spreadsheet data using Python libraries like pandas and openpyxl.

ML-NMR Methodology Specialist

Provides expert methodological guidance and implementation patterns for Multilevel Network Meta-Regression (ML-NMR) in evidence synthesis.

LangGraph Patterns Expert

Optimizes LangGraph agent architectures by implementing explicit state management, granular node design, and robust transition patterns.

Privacy Checker & Anonymizer

Detects PII, anonymizes sensitive information, and ensures regulatory compliance during synthetic data generation and processing.

R Data Science & Testing

Streamlines R development using modern data analysis patterns, automated testing with testthat, and strict linting standards.

Lab Notebook Manager

Manages structured bioinformatics lab notebooks through interactive dialogue to ensure high-quality, reproducible research documentation.

Scientific Experiment Reporter

Generates and refines structured scientific reports from bioinformatics lab notebooks with integrated figure support and professional PDF export.

ML API Endpoint Expert

Streamlines the design and deployment of production-grade machine learning inference endpoints using FastAPI and Docker.

RDKit Cheminformatics

Performs advanced molecular modeling and cheminformatics tasks including descriptor calculation, fingerprinting, and substructure searching.

LLM Evaluation Framework

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and comparative benchmarking.

Data Visualization

Generates insightful, professional-grade charts and interactive dashboards using industry-standard libraries and design principles.

Multi-Agent Coordination Framework

Orchestrates complex multi-agent AI systems and human-AI teams using advanced communication patterns and consensus mechanisms.

Python Data Reviewer

Optimizes Pandas and NumPy code for high-performance data processing, memory efficiency, and vectorization.

Statistical Trading Symbol Selection

Analyzes market data using Hurst exponent, GARCH models, and Markov regime detection to identify optimal trading symbols for quantitative strategies.

Backtest Datetime Visualization

Converts trading backtest charts from generic bar indices to precise datetime-based axes for improved temporal context.

ONT Align

Automates Oxford Nanopore sequence alignment, reference genome management, and edit distance computations for genomic data analysis.