Data Science & ML Claude 스킬

Multi-Provider Model Orchestrator

Orchestrates multiple AI model providers to optimize development workflows for cost, latency, and reasoning capability.

Sentiment Analysis Tool

Analyzes text data to identify emotional tone and classify sentiment as positive, negative, or neutral.

LLM Embedding Strategies

Optimizes vector search and RAG applications through strategic embedding model selection, chunking, and pipeline implementation.

Vector Index Tuning

Optimizes vector database performance by tuning HNSW parameters, implementing quantization, and balancing latency against recall.

Hydrological Forecasting Suite

Performs hydrological modeling and streamflow forecasting using Julia-based classical and machine learning models.

AI Prompting Standards

Optimizes AI agent performance through Anthropic-based context engineering and prompt structure standards.

Kokoro Local Text-to-Speech

Converts text and long-form markdown documents into high-quality audio locally using the Kokoro-82M model optimized for Apple Silicon.

LangChain4j Tool & Function Calling

Implements robust tool and function calling patterns for Java-based AI agents using the LangChain4j framework.

AI Prompt Engineering & Optimization

Optimizes LLM prompts to minimize token usage, reduce operational costs, and enhance model response quality through automated refinement.

Prompt Optimizer for AI & ML

Refines and compresses LLM prompts to minimize token usage, lower operational costs, and maximize response quality.

Julia HydroTools

Provides specialized functions for hydrological modeling and climate data processing within the Julia environment.

Hypothesis Testing Framework

Guides users through a scientifically rigorous five-phase hypothesis testing process to eliminate bias and p-hacking in data analysis.

AI Ethics & Fairness Validator

Validates the ethical implications and fairness of AI/ML models and datasets to ensure responsible development and bias mitigation.

Scientific Exploratory Data Analysis

Performs automated exploratory data analysis and generates comprehensive markdown reports for over 200 scientific file formats.

Prompt Engineer

Engineers and optimizes high-quality LLM prompts across multiple models using established best practices and systematic refinement techniques.

Data Science Tools

Equips Claude with specialized knowledge for statistical analysis, regression modeling, and reproducible data science script organization.

Advanced XLSX Spreadsheet Automation

Automates professional-grade spreadsheet creation, editing, and analysis with a focus on formula integrity and financial modeling standards.

Hugging Face Space Deployer

Automates the creation, configuration, and deployment of machine learning demos on Hugging Face Spaces using Gradio, Streamlit, and ZeroGPU.

Data Gouv France

Accesses, downloads, and analyzes French public open data from data.gouv.fr using a specialized Python library and integrated documentation.

Scientific Brainstorming

Empowers researchers to generate novel hypotheses, explore interdisciplinary connections, and overcome creative blocks through collaborative ideation.

Experiment Design Checklist

Generates rigorous experimental frameworks to validate research hypotheses with statistical significance and comprehensive baseline comparisons.

JAX Scientific Computing

Applies idiomatic JAX patterns and best practices to optimize scientific computing and machine learning workflows in Python.

DrugBank Database Integration

Provides programmatic access and analysis of comprehensive pharmaceutical data from the DrugBank database for drug discovery and pharmacology research.

Scientific Publication Plotting

Generates publication-quality scientific visualizations using TMLR styling and LaTeX rendering for research and academic reports.

Excel Data Analysis

Simplifies complex data analysis in Excel using advanced formulas, Pivot Tables, and Power Query automation.

XGBoost & LightGBM ML Toolkit

Implements industry-standard gradient boosting algorithms for high-performance machine learning on tabular and structured datasets.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompt engineering techniques and structured reasoning patterns.

Genomic Tools and Analysis in Rust (Gtars)

Provides high-performance tools for genomic interval analysis, interval overlap detection, and machine learning tokenization using Rust.

HPC Batch Staging & Rsync Patterns

Optimizes large-scale data staging on HPC environments using rsync, bash, and SLURM to ensure data integrity and script reliability.

CODEX Experiment JSON Parser

Translates CODEX/Akoya experiment.json metadata into the KINTSUGI ExperimentConfig format with precise field and wavelength mapping.