Data Science & ML Claude 스킬

PyTorch Docstring Formatter

Generates and formats standardized PyTorch docstrings following Sphinx and reStructuredText conventions.

Tisane Automation

Automates advanced natural language processing tasks including text moderation, sentiment analysis, and language detection via the Tisane API.

ArXiv Research Assistant

Analyzes ArXiv papers by fetching LaTeX source code and generating project-specific summaries for technical implementation.

Streamlit Feature Implementation

Streamlines the addition of new elements, widgets, and cross-stack functionality to the Streamlit framework.

Financial Modeling Suite

Constructs advanced financial models including DCF analysis, sensitivity testing, and Monte Carlo simulations for professional investment valuation.

CrewAI Multi-Agent Orchestration

Builds and orchestrates collaborative multi-agent AI teams using the CrewAI framework and Composio toolkits.

Startup Financial Modeling

Builds comprehensive 3-5 year financial models with revenue projections, burn rate calculations, and scenario planning for early-stage startups.

GPT Researcher Development

Empowers developers to build, customize, and integrate autonomous AI research agents using the GPT Researcher framework.

Azure AI Voice Live for .NET

Enables real-time, bidirectional voice AI capabilities in .NET applications using Azure AI and WebSocket communication.

Business Analyst

Transforms complex data into actionable business intelligence through advanced analytics, KPI frameworks, and predictive modeling.

Excel & Spreadsheet Automation

Automates the creation, editing, and analysis of Excel spreadsheets with professional formatting, formula integrity, and financial modeling standards.

Apache Spark Optimization

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

Risk Metrics Calculation

Calculates comprehensive portfolio risk metrics and performance indicators for quantitative finance and investment management.

Vector Index Tuning

Optimizes vector index performance for production environments by balancing latency, recall, and memory usage.

LLM Evaluation Framework

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

Trading Backtesting Frameworks

Builds robust, bias-aware backtesting systems to validate quantitative trading strategies and produce reliable performance estimates.

Data Storytelling for Analytics

Transforms raw data and complex analytics into persuasive business narratives and structured executive presentations.

Hybrid Search Implementation

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

Vector Search & Similarity Patterns

Implements efficient similarity search and vector database patterns for semantic retrieval and RAG systems.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompting techniques like few-shot learning, chain-of-thought, and modular templates.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training through to production deployment and monitoring.

LangChain Architecture Design

Architects sophisticated LLM applications using LangChain's modular framework for agents, memory, and complex workflows.

RAG Implementation Framework

Builds robust Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search to ground AI responses in custom knowledge.

Embedding Strategies for RAG

Optimizes embedding model selection and chunking strategies for semantic search and Retrieval-Augmented Generation (RAG) applications.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced techniques like few-shot learning, chain-of-thought reasoning, and structured prompt templates.

Embedding Strategies

Optimizes semantic search and RAG applications through intelligent model selection, chunking strategies, and embedding quality evaluation.

LLM Evaluation

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

Spark Optimization

Optimizes Apache Spark workloads through advanced partitioning, memory management, and shuffle tuning strategies.

LangChain Architecture

Builds sophisticated LLM applications by architecting modular chains, autonomous agents, and robust memory management systems using the LangChain framework.

Hybrid Search Implementation

Implements search architectures that combine vector similarity and keyword matching to maximize retrieval precision and recall.