Data Science & ML Claude 技能

Prompt Optimizer Adapter

Refines and condenses AI prompts to minimize token consumption while maximizing output quality and performance.

AI Recommendation System Builder

Develops personalized recommendation engines using collaborative filtering, content-based analysis, and hybrid modeling techniques.

Tradovate Indicator Scaffolding

Generates standardized JavaScript scaffolds and implementation patterns for Tradovate trading indicators.

ML Model Trainer

Automates the end-to-end machine learning lifecycle from data analysis and model selection to training and performance evaluation.

Multi-Agent Systems Orchestrator

Orchestrates complex multi-agent workflows using AI SDK v5 to manage handoffs, intelligent routing, and cross-provider coordination.

Hypogenic Hypothesis Generation

Automates scientific hypothesis generation and testing by combining observational data with literature insights using large language models.

Lyra AI Prompt Optimizer

Transforms vague natural language inputs into precision-engineered prompts for Claude, ChatGPT, Gemini, and other large language models.

Data Commons Client

Accesses and analyzes global public statistical data from authoritative sources via the Data Commons knowledge graph.

CUDA Development Guide

Optimizes CUDA and GPU computing development with performance-focused guardrails and industry-standard implementation patterns.

RDKit Cheminformatics

Provides comprehensive tools for molecular analysis, chemical property calculation, and 3D structure generation within scientific research workflows.

Matchms Mass Spectrometry Analysis

Processes, filters, and analyzes mass spectrometry data for metabolomics research and chemical identification.

D3.js Data Visualization

Builds interactive, publication-quality data visualizations using the D3.js library for any JavaScript environment.

HMDB Scientific Database

Accesses the Human Metabolome Database to retrieve chemical properties, clinical biomarkers, and spectral data for metabolomics research.

LangChain Architecture & LLM Agents

Designs and implements sophisticated LLM applications using LangChain's modular framework for agents, memory, and multi-step workflows.

Clustering Algorithm Runner

Executes and visualizes machine learning clustering algorithms to discover patterns and groupings within complex datasets.

GEO Database Access

Accesses and analyzes NCBI Gene Expression Omnibus (GEO) data for transcriptomics and genomics research.

ElevenLabs Text-to-Speech

Converts text into high-quality audio files using the ElevenLabs API with customizable voice parameters and presets.

Research Superpowers Getting Started

Orchestrates systematic literature searches and reviews by finding, screening, and extracting data from scientific papers across PubMed and Semantic Scholar.

COBRApy Metabolic Modeling

Performs constraint-based metabolic modeling, flux balance analysis, and gene knockout simulations for systems biology and metabolic engineering.

Medical Literature Review Assistant

Streamlines systematic literature searches and reference management using PubMed, PICO analysis, and citation metrics.

Regression Analysis & Modeling

Performs advanced regression analysis and predictive modeling to identify variable relationships and forecast data trends using automated statistical tools.

Computer Vision Adapter

Processes and analyzes images using advanced computer vision techniques to identify objects, classify scenes, and segment visual data.

Matplotlib Visualization

Generates publication-quality scientific visualizations and complex multi-panel plots using Python's foundational Matplotlib library.

Denario Research Assistant

Automates end-to-end scientific research workflows from data analysis and hypothesis generation to producing publication-ready LaTeX papers.

FiftyOne Duplicate Finder

Detects and manages duplicate or near-duplicate images in FiftyOne datasets using advanced brain similarity computations.

FiftyOne Embeddings Visualization

Visualizes computer vision datasets in 2D using dimensionality reduction to explore data structure, clusters, and outliers.

FiftyOne Python Code Style

Enforces official Voxel51 and FiftyOne Python coding conventions for consistent and maintainable development.

Deep Learning Optimizer

Optimizes deep learning model performance by refining architectures, tuning hyperparameters, and implementing efficient training strategies.

ML Experiment Tracking Setup

Automates the configuration and initialization of machine learning experiment tracking tools like MLflow and Weights & Biases.

FiftyOne Plugin Developer

Builds custom FiftyOne operators and interactive panels to extend computer vision data workflows.