Data Science & ML Claude 스킬

Mem0 Memory Design Patterns

Architects scalable AI memory systems with optimized retention, storage backends, and multi-level context patterns.

LlamaIndex RAG Patterns

Implements production-ready RAG pipelines and advanced retrieval strategies using LlamaIndex templates and scripts.

Nixtla Time Series Model Selector

Automatically selects and executes the optimal forecasting engine between StatsForecast and TimeGPT based on your data's unique characteristics.

LangChain Architecture & Agent Design

Architects sophisticated LLM applications using LangChain patterns for autonomous agents, conversational memory, and complex workflow orchestration.

Nixtla Forecast Explainer

Generates plain-English narratives and executive summaries from TimeGPT forecast results to bridge the gap between data science and business stakeholders.

AgentDB Advanced Operations

Master advanced vector database operations, including distributed QUIC synchronization and hybrid search for high-performance AI applications.

LangChain Architecture Design

Architects and implements sophisticated LLM applications using the LangChain framework for agents, memory management, and complex AI workflows.

Feature Engineering Toolkit

Automates the creation, selection, and transformation of data features to optimize machine learning model performance.

Gemma 3 270M Integration Template

Streamlines the integration and testing of Gemma 3 270M models within the Claude Code environment.

ElevenLabs Speech-to-Text Integration

Integrates ElevenLabs Scribe v1 for high-accuracy speech-to-text transcription across 99 languages with speaker diarization.

Excel DCF Modeler

Builds professional investment banking-grade discounted cash flow (DCF) valuation models in Excel with automated financial projections and sensitivity analysis.

Document Parsing & Extraction

Extracts text, tables, and metadata from PDF, DOCX, and HTML documents to power RAG pipelines and data processing workflows.

RAG Retrieval Patterns

Implements and optimizes advanced search strategies including semantic, hybrid, and reranking for high-performance RAG systems.

Model Versioning Tracker

Tracks and manages AI/ML model versions, lineage, and performance metrics within your development workflow.

LLM Application Evaluation

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

RAG Implementation Patterns

Implements high-performance Retrieval Augmented Generation (RAG) pipelines including document chunking, vector database integration, and semantic search.

Excel Variance Analyzer

Automates financial budget vs. actual variance analysis in Excel with professional reporting, materiality flagging, and executive summaries.

LangChain Application Architect

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

Agent Workflow Patterns

Implements sophisticated autonomous agent architectures and workflow patterns using the Vercel AI SDK.

Prompt Engineering Patterns

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

Model Evaluation Benchmark

Automates comprehensive AI model evaluation benchmarks to measure efficiency, code quality, and workflow adherence.

Advanced Excel & Spreadsheet Manager

Manages complex Excel workbooks with automated formula recalculation, professional financial modeling standards, and deep data analysis capabilities.

TextCleaner Pipeline Manager

Manages and automates complex text transformation pipelines via the TextCleaner REPL interface.

RAG Pipeline Architect

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

RAG Implementation Guide

Builds advanced Retrieval-Augmented Generation (RAG) systems to ground LLM responses with external document knowledge and vector search.

LangChain Application Architecture

Architects and implements sophisticated LLM applications using LangChain for agents, memory management, and complex workflows.

Prompt Engineering Patterns

Optimizes Large Language Model performance through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

Deep Learning Optimizer

Optimizes neural network performance by automatically applying advanced training algorithms, learning rate schedules, and regularization techniques.

Nixtla Contract Schema Mapper

Transforms prediction market datasets into standardized Nixtla formats for seamless time-series forecasting.

Machine Learning Model Explainability

Provides deep interpretability for machine learning models using SHAP and LIME to explain predictions and feature importance.