Data Science & ML Claudeスキル

ML Pipeline Workflow

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

LangChain Architecture

Designs and implements sophisticated LLM applications using the LangChain framework for complex AI workflows.

Hierarchical Bayesian Modeling

Implements and optimizes hierarchical Bayesian models with support for partial pooling and advanced parameterization techniques.

Bayesian Survival Models

Implements robust Bayesian survival analysis models including Weibull and Cox-like piecewise hazards with censoring support.

Bayesian Meta-Analysis

Implements robust Bayesian meta-analysis models using Stan and JAGS to synthesize data across multiple studies with advanced statistical precision.

Agent Builder

Orchestrates the development of complete, production-ready Claude Code agents using Anthropic's official best practices for context engineering and tool design.

Financial Time-Series Momentum

Implements professional-grade trend-following strategies, volatility targeting, and multi-scale momentum indicators for financial data analysis.

LA-Bench Procedure Generator

Generates detailed experimental procedures from LA-Bench datasets by orchestrating a multi-agent workflow for parsing, reference fetching, and quality validation.

LA-Bench Workflow

Orchestrates the end-to-end generation, validation, and iterative improvement of detailed laboratory experimental procedures using the LA-Bench framework.

TTS LiveKit Plugin

Deploys a self-hosted Text-to-Speech API using MeloTTS and integrates it with LiveKit voice agents for high-quality, low-latency speech synthesis.

AI Multimodal

Processes and generates multimedia content including audio, video, images, and documents using the Google Gemini API.

AI Multimodal Processing

Processes and generates complex multimedia content including audio, images, video, and documents using the Google Gemini API.

ML Pipeline Workflow

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

Swarm Orchestration

Orchestrates multi-agent swarms using dynamic topologies and automated task distribution for complex, parallel AI workflows.

ReasoningBank Intelligence

Implements adaptive learning systems to enable AI agents to recognize patterns, optimize strategies, and continuously improve through experience.

AgentDB Learning

Trains and deploys reinforcement learning models for autonomous agents using nine specialized algorithms including Decision Transformers and Q-Learning.

Phylogenetic Methods

Builds and analyzes phylogenetic trees using distance-based, maximum likelihood, and Bayesian inference methods.

AgentDB Memory Patterns

Implements persistent, high-performance memory and learning patterns for AI agents to maintain context across sessions.

Gemini Audio Integration

Implements comprehensive audio processing and text-to-speech generation using the Google Gemini API.

Workers AI

Provides expert guidance on implementing AI models, generating embeddings, and building Retrieval Augmented Generation (RAG) systems using Cloudflare’s serverless AI platform.

PyTorch Shape Validator

Validates and documents PyTorch tensor shapes through inline comments and runtime assertions to prevent common deep learning bugs.

Complex Tensor Handler

Manages complex-valued PyTorch tensors for astronomical imaging, signal processing, and frequency-domain neural networks.

Loop Vectorizer

Transforms inefficient Python loops into high-performance vectorized PyTorch operations to eliminate computational bottlenecks and optimize GPU utilization.

Physics Validator

Validates optical physics parameters for imaging simulations to ensure physically realistic instrument configurations and diffraction regimes.

LLM Integration

Configures and manages diverse LLM providers, streaming callbacks, and token optimization strategies for XSky-based agentic workflows.

Document Parser

Transforms oversized documents into structured, token-optimized hierarchical sections with extracted metadata to overcome context window limitations.

Technical Stock Indicators

Calculates core financial technical indicators including MA, MACD, RSI, and Bollinger Bands for stock market analysis and quantitative trading.

Consensus

Consults multiple AI models simultaneously and synthesizes their outputs using configurable strategies to improve accuracy and gather diverse perspectives.

Senior Prompt Engineer

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

PocketFlow

Orchestrates complex LLM applications using graph-based abstractions, agentic design patterns, and modular task decomposition.