Data Science & ML Claude 스킬

Gemini 3 Pro API Integration

Integrates Google's Gemini 3 Pro API into Python and Node.js applications with advanced reasoning and streaming capabilities.

VCF Variant Analysis Toolkit

Analyzes, filters, and exports genomic variant data from VCF and BCF files for bioinformatics and sequencing workflows.

BAM Alignment Toolkit

Analyzes genomic alignment files to extract reads, identify insertions and deletions, and calculate coverage statistics for WGS and WES data.

RAG Implementation Guide

Builds high-performance Retrieval-Augmented Generation (RAG) systems using vector databases, semantic search, and advanced retrieval patterns.

Local BLAT DNA Alignment

Performs high-speed local DNA sequence alignment against hg38 and CHM13 genomic references without external API dependencies.

NCBI BLAST Search

Performs NCBI BLAST sequence similarity searches using BioPython to identify homologous DNA or protein sequences.

Biological Sequence I/O

Reads, writes, and manipulates biological sequence data formats like FASTA, FASTQ, and GenBank.

Amazon Bedrock Prompt Manager

Manages, versions, and tests Amazon Bedrock prompt templates to streamline enterprise-grade prompt engineering workflows.

Amazon Bedrock Agents

Builds and manages autonomous AI agents on Amazon Bedrock using foundation models, action groups, and knowledge bases.

Recursive String Diagrams

Generates and validates recursive string diagrams using category theory primitives for complex system modeling.

Gemini 3 Pro API Integration

Integrates Google's Gemini 3 Pro API and SDK into applications for advanced reasoning, streaming chat, and large-context processing.

Prompt Engineering Lab

Creates, optimizes, and debugs high-performing, production-ready prompts for Claude 4, GLM 4.7, and Gemini 3 using evidence-based techniques.

Amazon Bedrock Prompt Management

Streamlines the creation, versioning, and lifecycle management of Amazon Bedrock prompt templates with variable substitution and A/B testing.

LLM Evaluation Framework

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

Analyze Goodreads Export

Queries and analyzes personal book libraries from Goodreads CSV exports to provide reading insights and statistics.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to optimize retrieval accuracy in RAG systems and search engines.

Similarity Search Patterns

Implements high-performance similarity search and vector database patterns for semantic retrieval and RAG systems.

Prompt Engineering Patterns

Optimizes Large Language Model performance through advanced reasoning patterns, few-shot learning, and structured prompt templates.

Risk Metrics Calculation

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

Vercel AI SDK Integrator

Implements modern AI patterns including streaming responses, tool calling, and structured outputs using the Vercel AI SDK.

Quantitative Backtesting Frameworks

Builds production-grade backtesting systems for trading strategies while mitigating common biases and accounting for realistic market costs.

LangChain Architecture Design

Builds sophisticated LLM applications using the LangChain framework to implement autonomous agents, complex workflows, and persistent memory.

Vector Index Optimization

Optimizes vector database indexes for production performance by balancing search latency, recall accuracy, and memory consumption.

RAG Implementation Expert

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

Domain Advisor

Plans data science and hardware optimization experiments by analyzing historical project logs and domain-specific configurations.

GPU Memory Cleanup

Prevents Jupyter notebook hangs by explicitly managing CuPy GPU memory pools and Python garbage collection.

Moodle AI Subsystem Integration

Streamlines the development of AI-powered features within the Moodle LMS using the official AI Subsystem for version 4.5 and above.

MLOps Pipeline Orchestrator

Builds and automates end-to-end MLOps pipelines from data ingestion and preparation through model training, validation, and production deployment.

Embedding Strategies for RAG

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

Data Storytelling

Transforms complex datasets into persuasive narratives and executive-ready presentations using proven storytelling frameworks.