Data Science & ML Claudeスキル

Macro Fiscal & Labor Scenario Analyzer

Analyzes US fiscal deficit expansion and Treasury risk scenarios during periods of rising unemployment and high GDP growth.

LLM Application Development

Builds robust AI-powered applications using advanced prompt engineering, RAG patterns, and multi-provider LLM integrations.

Data Import and Profiling

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

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

AI Model Validation

Validates AI model checkpoints against datasets to measure performance and benchmark key metrics.

arXiv Daily Paper Reader

Automates the discovery and retrieval of the latest research papers from arXiv across multiple scientific categories.

Hyperparameter Sweep

Systematically optimizes machine learning model performance by searching for the ideal hyperparameter configurations.

Neural Network Trainer

Executes and monitors neural network training runs using best-practice configurations and mandatory logging backends.

Training Curve Interpreter

Analyzes machine learning training logs to visualize loss curves, detect training issues, and provide diagnostic insights.

Scaling Analysis & Law Investigation

Analyzes and predicts AI model performance by empirically testing relationships between model size, dataset volume, and compute budget.

Experiment Design Coach

Guides the creation of rigorous, well-controlled experiments for machine learning and data science projects.

AI Training Diagnostics

Diagnoses and fixes machine learning training issues including loss plateaus, gradient instabilities, and convergence failures.

Live Training Monitor

Monitors machine learning training progress in real-time by integrating with logging backends and visualization tools.

Climpt Agent Scaffolder

Automates the creation of standardized Climpt agent directories and configuration files to accelerate AI agent development.

Deep Research

Produces comprehensive, well-sourced research reports using an iterative diffusion-based refinement methodology.

LangChain Architecture & Agent Design

Architects sophisticated LLM applications using LangChain agents, multi-step workflows, and advanced memory management systems.

LLM Evaluation & Benchmarking

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

Amazon Bedrock Inference

Integrates Amazon Bedrock Runtime APIs for unified model inference, streaming, and safety guardrails across multiple foundation models.

MATLAB & Octave Scientific Computing

Performs complex numerical analysis and scientific computing using MATLAB and GNU Octave syntax for matrix operations and data visualization.

Spark Optimization

Optimizes Apache Spark data processing jobs through advanced partitioning, memory management, and shuffle tuning.

Platinum-to-Brazil Equity Transmission Analyzer

Quantifies and validates the long-cycle transmission relationship between Platinum futures and the Brazilian stock market (EWZ) using statistical cross-correlation.

US Equity Valuation Extremes Detector

Detects historical extremes in US equity valuations by normalizing metrics like CAPE and PE into percentile scores.

Data Science & Statistical Analysis

Empowers Claude to perform statistical modeling, design experiments, and build predictive machine learning pipelines using Python.

LLM Evaluation Suite

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

AI Ethics & Fairness Validator

Validates the ethical implications, fairness, and potential biases of AI models and datasets to ensure responsible development.

AI Ethics & Fairness Validator

Analyzes AI models and datasets to identify biases, evaluate fairness metrics, and ensure responsible AI development.

LLM Prompt Optimizer

Refines and compresses LLM prompts to minimize token usage, reduce costs, and maximize output quality.

LLM Prompt Optimizer

Optimizes LLM prompts to reduce token usage, lower operational costs, and improve response performance.

AI Agent Orchestrator

Orchestrates complex multi-agent systems and intelligent task routing using the AI SDK v5 across multiple LLM providers.

AI Agent Orchestrator

Orchestrates sophisticated multi-agent systems using the AI SDK v5 to manage agent handoffs, task routing, and complex collaborative workflows.