Data Science & ML Claude 스킬

AgentDB Memory Patterns

Manages persistent AI agent memory and reasoning patterns using high-performance vector storage and learning algorithms.

Flow Nexus Neural

Train, deploy, and manage distributed neural networks across sandboxed E2B environments using multiple architectures and federated learning.

Prompt Optimization Specialist

Refines and enhances AI prompts to improve model performance and output accuracy using a structured analysis framework.

Prompt Engineering Expert

Architects high-performance LLM prompts and multi-agent systems using advanced reasoning patterns and optimization techniques.

Academic Research Paper Finder

Finds and prioritizes academic research papers to streamline literature reviews and citation management directly within your workspace.

Docling Advanced Document Extraction

Extracts structured data from complex PDFs, scanned documents, and multi-column layouts using the advanced Docling engine and Granite vision-language models.

AgentDB Memory Patterns

Implements persistent, high-performance memory and learning patterns for AI agents using AgentDB.

Data Visualization Insight

Explores datasets and generates interactive visualizations in marimo notebooks using Polars and Plotly Graph Objects.

Data Import and Profiling

Systematizes the process of discovering, profiling, and importing CSV data into relational databases with comprehensive quality checks.

LLM Evaluation Framework

Implements rigorous evaluation strategies for LLM applications using automated metrics, human-in-the-loop feedback, and systematic benchmarking.

Claude Batch Processing

Optimizes high-volume workloads by leveraging Anthropic's Message Batches API for 50% cost savings on non-time-sensitive tasks.

Macro Trend Deviation Analyzer

Analyzes asset price deviations from long-term exponential trends to identify historical extremes and macro market regimes.

Market Analysis Frameworks

Conducts professional market research and competitive analysis using industry-standard McKinsey frameworks directly within your terminal.

Reducto Document Parsing

Parses complex documents, extracts structured data, and edits files using natural language instructions via the Reducto CLI.

GPT-5 Prompt Engineering

Optimizes and iterates high-signal prompts for OpenAI GPT-5 models to ensure structured, reliable, and hallucination-free outputs.

Weather Temperature Transformer

Applies automated mathematical transformations to temperature data based on dynamic orchestration rules.

Recommendation Engine Systems

Constructs personalized recommendation engines using collaborative and content-based filtering to deliver tailored user experiences.

Excel & Spreadsheet Management

Automates advanced spreadsheet creation, financial modeling, and data analysis with support for dynamic formulas and professional formatting.

Gemini Flash Integration

Enables high-speed multi-modal analysis and document summarization using Gemini Flash within the Claude Code environment.

Gemini Pro Reasoning Engine

Integrates Google's Gemini Pro into Claude Code for deep reasoning, complex architectural analysis, and specialized domain research.

Technical Stock Indicators

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

Advanced AI Reasoner

Enhances Claude's problem-solving capabilities using advanced search strategies like Beam Search and Monte Carlo Tree Search.

Audio Transcriber

Converts audio and video files into accurate text transcripts with precise word-level timestamps using WhisperX.

Python Experiment Tracking

Organizes Python research code by implementing consistent logging, metadata tracking, and result comparison workflows.

ML Model Deployment Helper

Automates the productionization and deployment of machine learning models into scalable environments using FastAPI, Docker, and Kubernetes.

Langfuse Experiment Runner

Executes and evaluates LLM experiments using Langfuse datasets and LLM-as-judge evaluators to measure prompt performance and model quality.

Optimization Craft

Refines AI agent performance through structured optimization loops, automated evaluation contracts, and persistent multi-lever tuning.

Langfuse Prompt Management

Streamlines the lifecycle of LLM prompts by enabling versioning, deployment, and management within the Langfuse observability platform.

Agentic Optimization Target

Defines precise optimization goals and regression guardrails for autonomous agent loops using normalized 0-1 scoring.

Agentic Optimization Loop

Automates the iterative refinement of AI agent performance through contract-driven evaluation and multi-lever optimization protocols.