Data Science & ML Claudeスキル

Business Analytics Reporter

Generates comprehensive business performance reports and strategic recommendations from sales and revenue data.

Vector Index Tuning

Optimizes vector search performance and resource efficiency for production-scale LLM applications.

AI Embedding Strategies

Optimizes vector search and RAG applications by implementing advanced embedding model selection and chunking strategies.

Data Quality Frameworks

Implements robust data validation and quality assurance using Great Expectations, dbt tests, and data contracts.

Paper Finder

Streamlines academic literature review and research paper discovery with automated prioritization and screening workflows.

ML Pipeline Workflow

Build and automate end-to-end MLOps pipelines from data preparation and model training to production deployment.

RAG Implementation Guide

Builds sophisticated Retrieval-Augmented Generation (RAG) systems to ground LLM responses in external knowledge bases and private documentation.

Advanced Excel & Spreadsheet Automation

Automates professional-grade spreadsheet creation, financial modeling, and data analysis with formula preservation and industry-standard formatting.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to improve retrieval accuracy and recall in RAG systems.

Quantitative Risk Metrics Calculation

Calculates comprehensive portfolio risk metrics and performance indicators to enhance financial risk management and reporting.

AI Agent Orchestration

Orchestrates complex multi-agent systems using specialized patterns for dynamic reasoning and deterministic workflows.

Vertex AI RAG Patterns

Implements Retrieval-Augmented Generation (RAG) using the Vertex AI Engine to ground agent responses in private data sources.

ADK Fundamentals

Accelerates Google Agent Development Kit (ADK) projects with standardized environment setup, Vertex AI configuration, and robust agent scaffolding.

ADK Agent Fundamentals

Streamlines the creation and configuration of production-grade AI agents using the Google Agent Development Kit (ADK) and Vertex AI.

Intelligent RAG Ingestion

Optimizes document chunking and embedding workflows for high-performance RAG systems using Vertex AI.

Research Brief Architect

Generates comprehensive multi-LLM research strategies and model-optimized prompts for systematic analysis and strategic planning.

Gödel Machine Self-Optimizer

Implements self-improving code architectures that use formal proofs and evolutionary search to safely enhance system utility.

Scientific PDF & Schematic Toolkit

Automates PDF manipulation and generates publication-quality scientific diagrams for advanced technical documentation.

Sibyl Optimist Analyst

Analyzes experimental results from a positive perspective to identify growth opportunities and successful patterns.

Sibyl Methodologist

Evaluates the internal validity, external validity, and reproducibility of experimental methodologies within research and data science workflows.

Sibyl Revisionist Agent

Refines technical hypotheses and proposes strategic modifications based on experimental outcomes and system data.

Sibyl Experiment Planner

Generates rigorous, reproducible experimental plans and resolves GPU infrastructure issues for data science workflows.

Sibyl Result Synthesizer

Synthesizes multi-perspective debate results into unified assessments and actionable plans.

Oxy Workflow Builder

Builds structured data pipelines, SQL queries, and AI agents using the Oxy framework's hierarchical logic.

Sibyl Theoretical Researcher

Conducts rigorous academic research and generates theoretical proposals with strong mathematical foundations.

Sibyl LaTeX Writer

Converts research papers into NeurIPS LaTeX format and automates the document compilation process.

Sibyl Supervisor Decision

Analyzes AI experiment results and expert debates to determine whether a project should pivot or proceed.

Sibyl Contrarian

Challenges mainstream assumptions and identifies project blind spots by uncovering counter-evidence through deep academic and web research.

Sibyl Final Critic

Provides rigorous, conference-grade peer reviews for machine learning research papers targeting NeurIPS and ICML standards.

Sibyl Comparative Analyst

Conducts deep comparative research against State-of-the-Art (SOTA) works to define and position project contributions.