Data Science & ML Claude 스킬

ArXiv Research Assistant

Automates the retrieval, summarization, and downloading of scientific papers from arXiv for rapid literature reviews and academic research.

LangChain TypeScript Initializer

Bootstraps a production-ready LangChain TypeScript project with optimal configuration for AI agents and LangGraph.

Qualitative Research Specialist

Guides the design and execution of rigorous qualitative studies, thematic analysis, and coding schemes for non-numerical data.

Advanced AI Evaluation & LLM-as-a-Judge

Implements robust LLM-as-a-Judge evaluation techniques to measure, compare, and optimize the quality of AI-generated outputs.

Context Degradation Diagnostic & Mitigation

Diagnoses and mitigates performance loss in AI agents by identifying patterns like lost-in-middle, context poisoning, and distraction.

Context Engineering Fundamentals

Master the mechanics, constraints, and optimization strategies of context within AI agent architectures to improve performance and reduce costs.

AI Memory Systems Architect

Design and implement sophisticated memory architectures for AI agents to maintain state, consistency, and long-term knowledge.

Memory Systems for AI Agents

Design and implement advanced memory architectures to help AI agents persist state, maintain entity consistency, and reason over structured knowledge.

Advanced LLM Evaluation

Implements sophisticated LLM-as-a-Judge techniques to evaluate, compare, and benchmark AI model outputs with high precision.

Context Optimization for AI Agents

Optimizes AI agent context windows using advanced compaction, masking, and partitioning techniques to improve performance and reduce token costs.

Context Engineering Fundamentals

Masters the mechanics of LLM context to design efficient, high-performance agent architectures and debugging strategies.

LLM Benchmark & Prompt Optimization

Designs and executes rigorous LLM benchmark experiments to measure prompt performance and statistical significance.

Data Warehouse Discovery & Schema Mapper

Automates data warehouse schema discovery and enriches table metadata with codebase context for accurate AI-driven data analysis.

ML Experiment Summarizer

Generates lightweight, readable markdown summaries of machine learning fine-tuning and evaluation experiment results.

Seq Wrangler

Automates bioinformatics pipelines for sequence quality control, genome alignment, and BAM file processing.

Research Methodology Expert

Matches complex research questions to rigorous experimental designs, sampling strategies, and validity controls using PhD-level frameworks.

Model Council

Orchestrates parallel reasoning across multiple AI models to synthesize high-confidence solutions through consensus and architectural diversity.

Contextual Pattern Learning

Analyzes project architecture and coding patterns to automate learning and provide context-aware development assistance.

Model Intelligence & Detection

Optimizes agent behavior by automatically identifying the active LLM and adjusting execution configurations for maximum cross-model compatibility.

Honcho Memory Integration

Integrates Honcho’s open-source memory and social cognition layer into Python or TypeScript AI agent codebases.

Blood Panel Analyzer (Ray Peat Framework)

Interprets blood work through Ray Peat's bioenergetic framework to uncover the metabolic narrative behind laboratory values.

Cohere v2 Entity Extraction

Automates structured entity extraction and data validation using the Cohere v2 Python Chat API and strict JSON Schema enforcement.

Split Strategy Logic

Guides the selection and implementation of optimal train-validation-test split strategies based on specific data characteristics.

Pandas Pro

Provides expert pandas API patterns for high-performance data manipulation, cleaning, and aggregation within data science workflows.

Polars High-Performance DataFrames

Optimizes data processing workflows with Polars' expression API and lazy evaluation for lightning-fast manipulation of large-scale datasets.

SHAP Model Interpretability

Explains machine learning model outputs using Shapley values to provide feature importance, individual prediction breakdowns, and fairness analysis.

ML Environment Setup Validator

Validates and reports the status of Python libraries required for data science and machine learning workflows.

Reproducibility Checklist

Ensures machine learning experiments are fully reproducible by verifying random seeds, data hashes, and environment configurations.

Hyperparameter Tuning & Optimization

Optimizes machine learning model performance through structured hyperparameter tuning strategies and automated Bayesian search patterns.

Matplotlib Visualization

Generates publication-quality data visualizations and statistical plots using standardized Python plotting patterns.