Data Science & ML Claude 스킬

Trading Symbol Database Selection

Optimizes financial market universe selection using a multi-stage pipeline and SQLite-backed data management.

MaxFuse Notebook Import Conventions

Standardizes import patterns and file paths for MaxFuse Jupyter notebooks to ensure reliable package integration.

Model Version Protocol

Manages version compatibility between trained trading models and live trading environments by embedding metadata into checkpoints.

Training Code Verification

Validates machine learning training scripts and configurations to ensure path accuracy, weight consistency, and environment compatibility.

Trading Backtest Capital Accounting

Corrects financial logic in trading simulators to prevent inflated equity curves and inaccurate drawdown metrics.

Multi-Timeframe RL Training

Trains Reinforcement Learning models across multiple market timeframes with automated data resampling and professional market alignment.

Trading Prediction Outcome Tracker

Automates the recording of actual trading results against predicted signals to enable accurate performance metrics and model retraining.

RL Trading Reward Function Optimizer

Eliminates HOLD bias in reinforcement learning trading models by calibrating reward functions and slippage penalties.

Python Dataclass Optimizer

Optimizes Python dataclasses for memory efficiency, immutability, and validation using advanced PEP 557 patterns.

Multiplex Imaging Analysis

Optimizes segmentation, feature extraction, and spatial analysis workflows for high-dimensional multiplex immunofluorescence imaging data.

Google Veo Video Generation

Generates high-fidelity videos and synchronized audio using Google Veo 3.1 via the Vertex AI API.

Trust RL Model Predictions

Optimizes trading strategy execution by removing redundant heuristic pattern filters that conflict with Reinforcement Learning model signals.

ESM Protein Design & Modeling

Designs, analyzes, and generates protein sequences and structures using Evolutionary Scale Modeling (ESM3 and ESM C).

LLM Performance Evaluation

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.

Spark Optimization

Optimizes Apache Spark jobs through advanced partitioning, memory management, and shuffle performance tuning.

Data Storytelling

Transforms raw analytics into persuasive business narratives through structured storytelling, visualization techniques, and executive-ready frameworks.

ML Pipeline & MLOps Workflow

Orchestrates end-to-end MLOps pipelines from data ingestion and preparation to model training, validation, and production deployment.

Portfolio Risk Metrics Calculation

Calculates comprehensive financial risk metrics including VaR, CVaR, Sharpe, and Sortino ratios for quantitative portfolio management.

Vector Similarity Search Patterns

Implement high-performance similarity search and vector retrieval patterns across multiple database providers.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to improve retrieval accuracy in RAG systems and search engines.

Prompt Engineering Patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

Data Versioning Refactor

Implements lightweight dataset tracking and reproducibility patterns to ensure data changes are explicit and traceable.

Python Experiment Tracking

Organizes Python research code by implementing consistent logging, metadata tracking, and result comparison workflows.

AgentDB Memory Patterns

Manages persistent AI agent memory and reasoning patterns using high-performance vector storage and learning algorithms.

AgentDB Vector Search

Implements high-performance semantic vector search and intelligent document retrieval for RAG-based Claude Code workflows.

Agentica Multi-Agent Spawn

Instantiates sophisticated multi-agent architectures to handle complex reasoning, research, and implementation tasks.

ReasoningBank Intelligence

Implements adaptive learning and meta-cognitive capabilities to help AI agents optimize strategies through experience and pattern recognition.

DSPy.rb LLM Framework

Builds type-safe, composable, and optimized LLM applications using the programmatic DSPy paradigm in Ruby.

Agentica Multi-Agent Infrastructure

Orchestrates complex multi-agent AI workflows using standardized coordination patterns and robust infrastructure primitives.

Excel & Spreadsheet Power Tools

Automates the creation, editing, and analysis of professional Excel spreadsheets with dynamic formulas and industry-standard formatting.