Data Science & ML Claude 스킬

Advanced Prompt Engineering

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

Vector Search for Zettelkasten

Implements semantic search and AI-driven discovery for Obsidian vaults using vector embeddings and advanced chunking strategies.

Marimo Reactive Notebook Development

Builds reactive Python notebooks and interactive data applications using marimo's directed acyclic graph (DAG) execution model.

LLM Performance Evaluation

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

Context Optimization & Capacity Engineering

Optimizes AI context windows through strategic compression, masking, and partitioning to handle larger tasks and reduce operational costs.

Market Analyst Brief

Generates concise, 24-hour tactical financial market briefs across multiple asset classes using real-time global news.

AI Project Development

Architects and manages the end-to-end lifecycle of LLM-powered applications using agentic development methodologies.

ML Pipeline Workflow

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

Book Style-Transfer SFT Pipeline

Converts literary works into high-quality supervised fine-tuning (SFT) datasets to train AI models in specific authorial voices.

Prompt Engineering Patterns

Implement advanced LLM prompting techniques like few-shot learning and chain-of-thought to enhance production AI reliability and output quality.

RAG Implementation for LLM Apps

Builds high-performance Retrieval-Augmented Generation systems using vector databases and semantic search to ground AI responses in external knowledge.

Embedding Strategies for RAG

Optimizes embedding models and chunking strategies to enhance semantic search and RAG application performance.

MOVA AI Bootstrap Generator

Generates static bootstrap packages to initialize MOVA AI models and environments without requiring external LLM calls.

Multi-Agent Architecture Patterns

Designs and implements sophisticated multi-agent architectures to overcome context limitations and handle complex task decomposition.

Llama Stack Code Reviewer

Streamlines code reviews for the Llama Stack repository by focusing on distributed system patterns, API compatibility, and automated testing fixtures.

GPT-OSS & vLLM Troubleshooter

Diagnoses and resolves openai_harmony.HarmonyError and tool calling failures when using GPT-OSS models with vLLM.

Meta-Analysis Methods in R

Implements comprehensive meta-analysis workflows in R, including effect size calculation, heterogeneity assessment, and publication bias detection.

R Pharmacokinetics & PD Modeling

Streamlines pharmacokinetic and pharmacodynamic modeling in R using industry-standard packages and best practices.

Genomics & Bioinformatics Analysis

Performs comprehensive genomics and bioinformatics statistical analysis using R and Bioconductor packages.

R Causal Mediation Analysis

Performs advanced causal mediation analysis in R to decompose total effects into direct and indirect pathways across various statistical models.

Aeon Time Series Machine Learning

Provides specialized machine learning algorithms for time series tasks including forecasting, classification, and anomaly detection using scikit-learn compatible APIs.

LLM Fine-tuning Coach

Guides users through the end-to-end Large Language Model fine-tuning lifecycle using a coach-driven workflow.

Dask Parallel Computing

Scales Python workflows using parallel and distributed computing for datasets that exceed available memory.

PyMC Bayesian Modeling

Builds, fits, and validates sophisticated Bayesian models using PyMC's probabilistic programming interface.

PyTorch Lightning Assistant

Streamlines deep learning development by organizing PyTorch code into scalable, boilerplate-free Lightning modules and automated training workflows.

System Resource Detector & Advisor

Detects hardware resources and provides strategic architectural recommendations for computationally intensive scientific tasks.

Scientific Schematics

Generates publication-quality scientific diagrams and architectural schematics using AI-driven iterative refinement.

Scholar Evaluation Framework

Evaluates scholarly work using the ScholarEval framework to provide structured assessments, quantitative scoring, and actionable feedback across research dimensions.

GeoPandas Spatial Analysis

Performs advanced geospatial vector data analysis, coordinate transformations, and spatial mapping within Python environments.

Crypto Hard Filter Simplification

Streamlines cryptocurrency asset selection by bypassing irrelevant equity filters and handling data gaps in financial datasets.