Data Science & ML Claudeスキル

RAG Embedding Model Manager

Optimizes embedding model selection, configuration, and cost estimation for RAG pipelines.

Google File Search RAG

Implements managed Retrieval-Augmented Generation (RAG) using Google File Search and Gemini models for high-accuracy document retrieval and grounding.

ML Training Validation Scripts

Ensures the integrity of machine learning training workflows by validating datasets, model checkpoints, and system dependencies.

ML Training Cost Calculator

Calculates and compares machine learning training and inference costs across major cloud GPU platforms like Modal, Lambda Labs, and RunPod.

ML Training Monitoring Dashboard

Sets up comprehensive monitoring dashboards using TensorBoard and Weights & Biases to track machine learning experiments in real-time.

Google Cloud ML Configs

Configures and optimizes Google Cloud Platform environments for BigQuery ML and Vertex AI training workloads.

ML Training Examples

Provides production-ready machine learning templates and training workflows for classification, text generation, and financial analysis.

LangChain RAG Patterns

Implements production-ready RAG pipelines and multi-step agent workflows using LangChain, LangGraph, and LangSmith templates.

ElevenLabs Voice Processing

Manages high-fidelity voice cloning workflows, library organization, and audio optimization for synthetic speech generation.

LLM Chat Completions

Integrates Large Language Model chat completions into backend applications using the z-ai-web-dev-sdk for advanced conversational AI and text generation.

LangGraph AI Orchestration

Builds complex, stateful, and cyclic multi-actor AI agent workflows using the LangGraph framework.

LLM Chat Integration

Integrates sophisticated large language model chat completions into backend applications using the z-ai-web-dev-sdk.

RAG Implementation

Implements advanced Retrieval-Augmented Generation (RAG) workflows to build knowledge-grounded LLM applications and semantic search systems.

Claude Code Colab Customizer

Configures and personalizes your Claude Code Colab environment through interactive setup and automated notebook modification.

LangChain Architecture

Designs and implements sophisticated LLM applications using the LangChain framework for agents, memory management, and modular workflows.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques to optimize LLM performance, reliability, and output controllability in production environments.

LLM Evaluation & Testing

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and LLM-as-judge patterns.

LLM Auto-Update

Automatically synchronizes the latest LLM model specifications, pricing, and API documentation to ensure optimal architecture decisions.

ReasoningBank Agent Learning

Implements adaptive learning and high-speed memory patterns for self-improving Claude Code agents using AgentDB.

RAG Implementation

Builds production-ready Retrieval-Augmented Generation (RAG) systems for LLM applications using vector databases and semantic search.

SQL Data Analyst

Performs advanced data analysis and business intelligence using specialized SQL patterns for statistical and exploratory insights.

Workers AI Expert

Deploys and optimizes serverless AI models, embedding generation, and RAG architectures directly on Cloudflare’s edge network.

Demographic Predictor

Predicts age, gender, and ethnicity from person data and images to enrich datasets and customer profiles.

Marimo Development Server

Deploys and manages reactive Python notebooks with hot-reloading capabilities for interactive development.

Marimo Notebook Inspector

Inspects Marimo notebook execution results and HTML snapshots to debug errors and verify cell outputs.

Marimo Notebook Assistant

Streamlines the creation and management of reactive marimo notebooks for interactive data science and analytics workflows.

RLOO Policy Optimization

Implements Reinforcement Learning with Leave-One-Out estimation to stabilize model training and optimize policy performance.

ComfyUI Manager

Deploys and manages ComfyUI instances for node-based Stable Diffusion image generation with GPU acceleration and model lifecycle support.

Ollama Local LLM Manager

Manages local Ollama inference servers using Podman Quadlet to provide GPU-accelerated LLM capabilities.

LangChain Framework Support

Simplifies building LLM-powered applications by providing standardized abstractions for prompt engineering, model orchestration, and structured output parsing.