Data Science & ML Claude 스킬

Benchling Integration

Automates Life Sciences R&D workflows by integrating Benchling registry, inventory, and notebook operations via Python SDK and REST API.

ML Pipeline Workflow

Automates the end-to-end MLOps lifecycle from data preparation and model training to production deployment and monitoring.

Jupyter Autoreload Awareness

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

Presenting Data

Generates professional, data-driven presentations and technical whitepapers with robust citation management and reproducibility standards.

Notebook-to-Module Refactoring

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

Creating Visualizations

Generates professional terminal-based and image-based visualizations to communicate data patterns and analytics results clearly.

Trading Position Sizing & Action Space

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

Cleaning Data

Implements a systematic data quality remediation process to detect duplicates, handle outliers, and standardize inconsistencies for reliable analysis.

Deconvolution Intensity Scaling

Ensures quantitative accuracy in microscopy deconvolution by preserving original intensity relationships across image channels.

Trading Model Training Gating

Automates the archival and quality classification of algorithmic trading models based on performance metrics and risk thresholds.

Colab Unzip Path Manager

Corrects file path errors and API key configurations in Google Colab environments after repository extraction.

Network Architecture Sizing for Trading RL

Optimizes PPO neural network dimensions to balance trading model capacity, inference speed, and hardware memory usage.

Multi-Agent Trading Integration

Integrates multi-agent Claude systems into algorithmic trading pipelines to optimize model training and manage live risk with automated oversight.

Selection Data Caching for Trading

Optimizes financial data retrieval by caching market symbol data to reduce API latency and avoid rate limits during trading bot development.

Sparse Expression Visualization

Optimizes the visualization of sparse single-cell gene expression data by implementing alternative plotting patterns that prevent boxplot collapse.

Trading Drawdown Guardrails

Implements standardized risk management and drawdown protection patterns for algorithmic trading systems.

Backtest Result Persistence

Persists trading backtest results to an SQLite database to enable historical performance comparison and model optimization.

Region-Aware Spatial Cell Matching

Optimizes CODEX and scRNAseq data integration by incorporating tissue heterogeneity into spatial cell matching workflows.

QC Plot PDF Export

Standardizes the generation and PDF archival of Quality Control (QC) heatmaps and profiles for microscopy quantification workflows.

Nixtla Liquidity Forecaster

Predicts market orderbook depth and bid-ask spreads to optimize trade execution timing using Nixtla TimeGPT and historical market data.

Capital Manager Proportional Limits

Implements percentage-based capital allocation and risk limits to ensure trading strategies scale effectively across all account sizes.

PPO RL Training Optimizer

Optimizes reinforcement learning training stability and monitoring through learning rate warmups, validation scheduling, and reward weight tuning.

Trading Asset Selection Filters

Optimizes financial asset selection by applying differentiated filtering logic for equities and cryptocurrencies within trading systems.

Empirical Config Builder

Derives trading selection thresholds from market data to replace hardcoded parameters with dynamic, data-driven values.

Notebook Configuration Auditor

Identifies and fixes hardcoded values in Jupyter notebooks that conflict with defined configuration constants.

Universal PDF Report Generator

Generates professional, locally-executed PDF reports featuring formatted text, data tables, and embedded visualizations using the reportlab library.

Senior Prompt Engineer

Optimizes LLM performance through advanced prompt engineering, RAG architecture design, and agentic system orchestration.

Nixtla TimeGPT Fine-Tuning Lab

Streamlines the fine-tuning of Nixtla TimeGPT models on custom datasets for high-precision, domain-specific forecasting.

LLM CLI

Interacts with diverse large language models through a command-line interface to perform tasks like prompt execution, data extraction, and embedding management.

deepTools NGS Analysis

Analyzes and visualizes high-throughput sequencing data including ChIP-seq, RNA-seq, and ATAC-seq.