Data Science & ML Claude 스킬

Long Context Transformer Extension

Extends Transformer model context windows using RoPE, YaRN, and ALiBi techniques for processing massive documents and datasets.

Prompt Engineering Pro

Optimizes Claude's outputs and debugging capabilities using Anthropic's official prompt engineering best practices and techniques.

Pydantic AI Agent Creation

Streamlines the development of type-safe AI agents using the Pydantic AI framework for Python.

R Package Development

Provides expert guidance and automated workflows for building, testing, and documenting R packages using industry-standard tools like devtools and roxygen2.

ML Production Routing

Routes machine learning workflows to specialized guides for deployment, optimization, MLOps tooling, and production observability.

PyTorch Engineering Specialist

Routes PyTorch engineering challenges to specialized domain experts based on specific symptoms, performance bottlenecks, and implementation requirements.

Xarray for Multidimensional Data

Manages and analyzes labeled multidimensional arrays for complex scientific data workflows using Xarray.

MQL5-Python Workspace

Synchronizes MetaTrader 5 and Python environments to automate market data exports and translate MQL5 indicators into validated Python code.

Deep Agents Implementation

Simplifies the development and deployment of complex AI agents and multi-agent workflows using the LangGraph-based Deep Agents framework.

Deep Reinforcement Learning (RL) Meta-Skill

Routes reinforcement learning problems to specialized algorithms and implementation strategies based on task characteristics and environmental constraints.

LLM Engineering Specialist

Guides and routes LLM-related development tasks toward specialized patterns for prompt engineering, RAG, fine-tuning, and model optimization.

Stan Development

Provides expert guidance for writing high-performance Stan probabilistic programming models and integrating them with R or Python workflows.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling and systems biology simulations to analyze cellular metabolism and phenotype predictions.

Speech-to-Text

Implements high-performance, privacy-focused speech recognition systems using Faster Whisper for secure audio transcription and voice assistant integration.

Excel Variance Analyzer

Automates budget vs actual variance analysis in Excel to identify root causes and generate executive-ready financial reports.

Excel DCF Financial Modeler

Builds investment-grade discounted cash flow valuation models in Excel with automated projections and sensitivity analysis.

Excel Pivot Wizard

Generates sophisticated Excel pivot tables, calculated fields, and interactive slicers for rapid data analysis and reporting.

Excel LBO Modeler

Builds sophisticated leveraged buyout (LBO) models in Excel, complete with debt schedules and private equity return analysis.

Qwen Training Data Miner

Mines extensive decision logs to generate high-quality, structured instruction-tuning datasets for autonomous AI model training.

GreyCat SDK & GCL Reference

Provides a comprehensive reference for developing native C extensions and GCL applications within the GreyCat ecosystem.

Reactome Pathway Analysis

Performs comprehensive biological pathway analysis and gene-to-pathway mapping using the Reactome open-source database.

Research Synthesis

Synthesizes fragmented research findings into coherent, structured narratives with evidence-based uncertainty quantification.

Llama.cpp C/C++ Integration

Provides a comprehensive C/C++ API reference and implementation patterns for high-performance local LLM inference using llama.cpp.

Ontology Access Kit (OAK)

Queries and manipulates biological and medical ontologies using the powerful OAK library for complex semantic operations.

Gemma Domain Trainer

Automates the fine-tuning of Gemma 270M models using LoRA adapters for domain-specific tasks and autonomous operations.

Hypothesis Testing & Experiment Design

Standardizes the scientific research process by guiding users through rigorous hypothesis formulation, experimental design, and variable mapping.

Hugging Face Training Manager

Simplifies the deployment and management of Unsloth fine-tuning jobs on Hugging Face cloud GPUs.

Funsloth Local GPU Training

Manages local GPU fine-tuning workflows using Unsloth to optimize LLM training performance and resource utilization.

FunSloth Unsloth Training Generator

Generates optimized training notebooks and scripts for fine-tuning LLMs using the Unsloth framework.

scvi-tools Single-Cell Analysis

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