Data Science & ML Claudeスキル

FluidSim CFD Framework

Performs high-performance computational fluid dynamics simulations and spectral analysis using Python.

DiffDock Molecular Docking

Performs state-of-the-art diffusion-based molecular docking to predict 3D binding poses of small molecule ligands to protein targets.

Scientific Analysis & Reporting

Generates structured, data-driven scientific research reports by analyzing repository data and verifying metrics against technical standards.

MLOps Pipeline Workflow

Orchestrates end-to-end machine learning pipelines from automated data preparation through model training, validation, and production deployment.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling and systems biology simulations using the COBRApy Python library.

DeepChem Molecular ML

Streamlines molecular machine learning workflows for drug discovery, property prediction, and materials science using the DeepChem library.

Tripartite Problem Decompositions

Decomposes complex computational problems into three balanced, parallel components using GF(3) conservation and sheaf-theoretic gluing.

Adaptyv Cloud Protein Lab

Facilitates automated protein design, sequence optimization, and wet-lab validation via a cloud-based laboratory platform.

RDKit Cheminformatics Toolkit

Provides specialized guidance for molecular analysis, structural manipulation, and chemical property calculation using RDKit.

Context Engineering

Optimizes LLM context windows to maximize reasoning quality while minimizing token costs and latency.

Google ADK Python Agent Toolkit

Simplifies the creation, orchestration, and deployment of production-grade AI agents using Google's Agent Development Kit.

Excel & Spreadsheet Power Suite

Automates complex spreadsheet creation, financial modeling, and data analysis with formula integrity and industry-standard formatting.

Research Evaluation & Visualization

Generates standardized Python scripts for analyzing model performance and creating publication-ready LaTeX tables and figures.

Neural Network Model Tuner

Standardizes machine learning model wrappers to provide a uniform interface for training, inference, and automated hyperparameter tuning.

Recipes Feature Engineering

Streamlines machine learning data preprocessing in R using standardized Tidymodels recipes patterns.

Python Analysis Pipeline

Manages a complete 4-stage pipeline from Python scripts to interactive notebooks and automated markdown documentation.

Haipipe Data Pipeline Manager

Manages end-to-end data pipelines across four stages from raw source ingestion to AI-ready datasets.

Paper Incubator

Facilitates the interactive drafting and refinement of LaTeX research papers through structured incubator documents and canonical data tracking.

Prompt Engineering Patterns

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

Bodhi React SDK Integration

Integrates React and Vite applications with the Bodhi JS SDK to enable local LLM chat capabilities and seamless authentication.

Badminton Rankings Analyzer

Analyzes German U19 badminton ranking data from the DBV directly within Claude Code.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

Haipipe Endpoint Deployment

Streamlines machine learning model endpoint deployment through unified packaging, inference function design, and multi-target deployment.

OpenAI Agents Orchestrator

Develops production-grade AI applications using the OpenAI Agents SDK with multi-agent handoffs, voice integration, and robust error prevention.

Haipipe NN Pipeline Manager

Manages and orchestrates end-to-end neural network pipelines across algorithmic, tuning, and deployment layers.

Gemini AI Orchestrator

Integrates Google's Gemini-3-pro-preview model into Claude Code for multimodal analysis, massive context processing, and real-time grounding.

Marimo Reactive Notebooks

Develops and manages reactive Python notebooks that function as pure-code files, interactive data apps, and reproducible scripts.

Antahkarana Cognitive Reasoning

Facilitates complex decision-making through a multi-agent debate simulation that analyzes problems from diverse cognitive perspectives.

Excel & Spreadsheet Professional

Manages complex spreadsheet tasks including professional financial modeling, data cleaning, and automated formula validation.

LangChain Architecture

Designs and implements sophisticated LLM applications using the LangChain framework for complex AI workflows.