Data Science & ML Claudeスキル

RAG Implementation Guide

Builds sophisticated Retrieval-Augmented Generation systems to ground LLM responses with external knowledge and semantic search.

OpenDART Korean Corporate Data

Retrieves and analyzes South Korean corporate disclosures, financial statements, and shareholder reports via the OpenDART REST API.

AI Agent Prompt Patterns

Provides structured patterns and best practices for crafting reliable system prompts for AI agents.

Treasure Data Agent Development

Develops and manages sophisticated LLM agents within the Treasure Data ecosystem using a YAML-based configuration workflow.

R Development Style Guide

Enforces professional R coding standards, naming conventions, and Tidyverse-aligned function design patterns.

R Performance Optimizer

Optimizes R code through professional profiling, benchmarking, and implementation of high-performance backend patterns.

R Package Development Guide

Provides expert guidance and implementation patterns for building robust, CRAN-compliant R packages.

Bayesian Inference in R

Performs advanced Bayesian statistical modeling and causal inference using the brms and Stan ecosystem in R.

ML & AI Benchmarking

Facilitates methodologically rigorous ML and AI benchmarking experiments using xetrack and DuckDB.

arXiv Research Assistant

Searches and downloads arXiv paper source code and LaTeX files for scientific research and analysis.

Git + DVC Experiment Versioning

Manages machine learning experiment versioning and reproducibility using Git, DVC, and xetrack.

NASA ADS Search & BibTeX

Accesses the NASA Astrophysics Data System (ADS) to search for literature, retrieve BibTeX citations, and track paper metadata.

OpenAI Prompt Engineer

Generates and optimizes high-quality prompts for modern large language models using advanced techniques like chain-of-thought, few-shot learning, and structured formatting.

Python Execution & Management

Executes Python scripts and manages local Anaconda environments with integrated support for organized file structures and Chinese language visualization.

Xarray for Multidimensional Data

Simplifies scientific data analysis by managing labeled multidimensional arrays with Xarray's powerful indexing and metadata features.

HPC Context for Mycelia

Optimizes Mycelia multiomic analysis workflows for High Performance Computing (HPC) environments and SLURM workload managers.

AI Vendor Evaluation

Evaluates AI vendor proposals and solutions through a structured framework to mitigate risks, analyze pricing models, and guide strategic build-versus-buy decisions.

Mycelia Planning Scope

Standardizes the auditing of planning documents for the Mycelia multiomics platform by cross-referencing source code, tests, and infrastructure.

Anthropic Prompt Engineer

Implements Anthropic's official prompt engineering techniques to generate, optimize, and refine prompts for high-performance Claude AI interactions.

PydanticAI Agent Framework

Builds production-grade Python agents using Pydantic for strict type validation and dependency injection.

Bioinformatics Tool Integration

Standardizes the integration, citation, and testing of external bioinformatics tools within the Mycelia multiomic framework.

LLM Router

Routes AI requests to various LLM providers including OpenAI, Grok, Groq, and DeepSeek using the SwiftOpenAI-CLI agent mode.

Deep Reinforcement Learning (RL) Meta-Skill

Routes reinforcement learning problems to specialized algorithms and implementation strategies based on task characteristics and environmental constraints.

LLM Engineering Specialist

Guides and routes LLM-related development tasks toward specialized patterns for prompt engineering, RAG, fine-tuning, and model optimization.

Agno AI Agent Framework

Builds production-grade multi-agent systems, AgentOS runtimes, and complex agentic workflows with native MCP integration.

Pixi Package Manager

Manages fast, reproducible scientific Python environments by unifying conda and PyPI ecosystems within a single workflow.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling and systems biology simulations to analyze cellular metabolism and phenotype predictions.

PDF Text Extraction & Conversion

Extracts and converts PDF content into clean, LLM-ready markdown or text using AI-powered and high-fidelity local tools.

Excel Analysis & Data Automation

Streamlines the analysis, transformation, and visualization of Excel spreadsheets using advanced Python libraries within Claude Code.

Logit Lens Interpretability

Decodes intermediate transformer layer activations into human-readable vocabulary predictions to visualize model processing.