Data Science & ML Claudeスキル

Veo 3.1 Video Interpolation

Generates cinematic video transitions and morphing animations between two keyframe images using Google’s Veo 3.1 via fal.ai.

PubMed Research Assistant

Accesses and queries the PubMed database for biomedical literature, systematic reviews, and citation management.

Advanced XLSX Spreadsheet Manager

Creates, edits, and analyzes sophisticated Excel workbooks with a focus on dynamic formulas, financial modeling standards, and automated recalculation.

Autonomous Trading

Orchestrates end-to-end stock trading operations by performing automated screening, multi-model AI analysis, and order execution via Alpaca.

LangChain Architecture

Architects and implements sophisticated LLM applications using LangChain agents, chains, and memory patterns.

Embedding Strategies for RAG

Optimizes text embedding selection and chunking strategies to enhance semantic search and RAG application performance.

DS-STAR Data Science Framework

Automates complex data science workflows using a multi-agent architecture and optimized model routing for efficient, iterative data analysis.

Vector Index Tuning

Optimizes vector database performance by tuning HNSW parameters and implementing advanced quantization strategies for AI applications.

Aeon Time Series ML

Empowers Claude to perform advanced time series machine learning, including classification, forecasting, and anomaly detection using the specialized aeon toolkit.

Hybrid Search Implementation

Implements robust hybrid search systems by combining vector similarity and keyword-based retrieval for enhanced RAG performance.

Arxiv Research Digest

Automates the discovery and summarization of relevant arXiv research papers based on specific interests in physics and machine learning.

Similarity Search Patterns

Implements high-performance similarity search and vector database patterns for AI-driven applications.

Zarr Python Data Storage

Manages large-scale N-dimensional arrays with chunked storage, compression, and seamless cloud integration for scientific computing pipelines.

LLM Performance Evaluation

Implement comprehensive evaluation frameworks for AI applications using automated metrics, human feedback, and LLM-as-judge patterns.

Quantitative Risk Metrics Calculation

Calculates comprehensive portfolio risk metrics and performance indicators for quantitative trading strategies.

LangChain & LangGraph Architecture

Designs and implements sophisticated LLM applications using LangChain 1.x and LangGraph for advanced agent orchestration and state management.

LLM Evaluation Suite

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

JSON Repair & Formatting

Automatically fixes malformed or incomplete JSON strings generated by AI models to ensure reliable data parsing.

Quantitative Backtesting Frameworks

Builds robust, production-grade backtesting systems to validate trading strategies while eliminating common statistical biases.

MLOps Pipeline & Workflow Orchestration

Builds and automates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

LLM Evaluation Framework

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

RAG Implementation Suite

Builds robust Retrieval-Augmented Generation systems using vector databases, semantic search, and advanced retrieval patterns for LLM applications.

Prompt Engineering Patterns

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

Seaborn Statistical Visualization

Generates high-quality statistical graphics and data visualizations with seamless Pandas integration.

RAG Pipeline Architect

Implements end-to-end Retrieval-Augmented Generation workflows to enable accurate AI querying of specialized documentation and technical textbooks.

Vector Index Tuning Specialist

Optimizes vector database performance by tuning HNSW parameters, quantization strategies, and memory usage for efficient AI applications.

Advanced Prompt Engineering Patterns

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

PennyLane Quantum Machine Learning

Builds, trains, and optimizes hybrid quantum-classical models using automatic differentiation and hardware-agnostic circuit programming.

Embedding Strategies for RAG

Optimizes embedding model selection and chunking strategies to improve semantic search and RAG application performance.

Embedding & Chunking Strategies

Optimizes vector search and RAG applications through intelligent embedding model selection and advanced document chunking strategies.