Data Science & ML Claude 스킬

Trading Position Sizing & Action Space

Implements a 7-action space with integrated position sizing and small account simulation for reinforcement learning trading models.

Notebook-to-Module Refactoring

Refactors Jupyter notebook code into reusable Python modules while preserving critical variable definitions and configuration.

Jupyter Autoreload Awareness

Optimizes Jupyter notebook workflows by preventing unnecessary kernel restarts when using the IPython autoreload extension.

Trading Model Post-Training Workflow

Validates and assesses reinforcement learning trading models through systematic gating, backtesting, and walk-forward validation.

GPU Correlation Accelerator & Cache

Accelerates financial correlation matrix computations using GPU-vectorized PyTorch operations and persistent SQLite caching.

Persistent Market Data Cache & Gap-Filling

Optimizes historical market data retrieval by eliminating redundant downloads through persistent caching and incremental gap-filling.

Trading Gates & Pattern Filter

Implements a multi-stage validation system for algorithmic trading that filters signals through pattern-matching and risk-management gates.

Trading Dual-Folder Workflow

Manages separate development and production environments for private repository trading models and Colab training.

Notebook Checkpoint Pattern

Implements a structured checkpointing system for connecting multiple Jupyter notebooks into robust, memory-efficient data pipelines.

Dotted Symbol Exclusion for Trading Data

Optimizes financial data pipelines by automatically filtering non-standard ticker symbols that cause API errors during sector lookups.

Claude Batch Processing

Optimizes high-volume workloads by leveraging Anthropic's Message Batches API for 50% cost savings on non-time-sensitive tasks.

Alpaca Trading Order Limitations

Enforces Alpaca broker-specific constraints by filtering unsupported crypto short orders while maintaining valid equity shorting capabilities.

Parallel Universe Selection Optimizer

Accelerates quantitative trading universe selection by 3-4x through parallel processing and optimized caching strategies.

Interactive Plotly FigureWidget Fix

Resolves KeyError: 'uid' errors when updating interactive Plotly FigureWidget shapes and sliders in VS Code.

Alpaca Algo Trader Plus Data Connector

Leverages the Alpaca Algo Trader Plus subscription to fetch extended historical market data for training robust trading models.

Copper Resilience & Cross-Asset Analyst

Evaluates copper price breakout and pullback scenarios by analyzing cross-asset signals like global equity resilience and Chinese interest rate environments.

Lightsheet PSF Deconvolution

Eliminates horizontal banding artifacts in microscopy data by implementing true lightsheet Point Spread Function (PSF) calculations.

Per-Sector Trading Candidate Filter

Optimizes trading universe selection by applying sector-specific volume filters to ensure a diverse and manageable pool of candidates.

Trading Selection Diversity Validation

Enforces strict portfolio diversity constraints and correlation limits in trading systems using the Fail Loudly pattern.

Pixi Package Manager

Manages fast, reproducible scientific Python environments by unifying the conda and PyPI ecosystems.

Hugging Face Transformers

Simplifies working with pre-trained transformer models for NLP, computer vision, and audio tasks within Claude Code.

Benchmark Report Creator

Orchestrates the end-to-end creation of publication-quality AI/ML benchmark reports with high-resolution diagrams and PDF export.

Marimo Notebook Essentials

Develops reactive Python notebooks and interactive dashboards using the marimo framework.

Seaborn Statistical Visualization

Creates publication-quality statistical graphics and complex data visualizations using a high-level Python interface.

Research Lookup

Automates academic literature search and technical research using Perplexity's Sonar models with intelligent reasoning selection.

Systematic Literature Review

Conducts comprehensive, multi-database literature searches and synthesizes findings into professionally formatted research documents with verified citations.

RAG Implementation Guide

Builds high-performance Retrieval-Augmented Generation (RAG) systems to ground LLM responses with proprietary or external data.

Vector Index Tuning & Optimization

Optimizes vector search performance by tuning index parameters, quantization strategies, and memory usage for production-grade AI applications.

Scientific Critical Thinking

Evaluates the rigor of scientific claims by assessing methodology, identifying biases, and grading evidence quality using standardized frameworks.

LangChain Architecture & Design

Builds sophisticated LLM applications using the LangChain framework with agents, memory systems, and complex workflows.