data science & ml Claude 스킬을 발견하세요. 61개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Generates production-ready Dagster data assets and pipelines using natural language requirements and industry best practices.
Initializes and scaffolds organized multi-project environments for Dagster data orchestration using natural language.
Initializes new Dagster projects with a recommended structure using natural language commands.
Implements advanced Retrieval-Augmented Generation patterns, optimizing document chunking, embeddings, and search strategies for high-performance AI systems.
Builds reliable, production-ready autonomous AI systems using proven agentic patterns and strict reliability guardrails.
Creates, edits, and analyzes professional spreadsheets with industry-standard formatting, dynamic formulas, and automated recalculation.
Provides a comprehensive, categorized guide to over 82 Dagster integrations for data orchestration and engineering.
Builds and manages reliable AI agents using robust patterns like ReAct and Plan-Execute to ensure production-grade performance.
Analyzes high-dimensional single-cell gene expression data to identify cell types, states, and developmental trajectories.
Simplifies physical and analytical chemistry tasks by automating chemical equation balancing, kinetic modeling, and equilibrium calculations.
Simulates open and closed quantum system dynamics using the Quantum Toolbox in Python framework.
Provides a standardized framework for developing specialized scientific research and data analysis capabilities within Claude Code.
Performs advanced manipulation and analysis of 2D planar geometric objects using standardized algorithms.
Performs advanced geospatial data manipulation and spatial analysis using the familiar Pandas API in Python.
Accelerates Python and NumPy programs using composable transformations for high-performance machine learning and scientific simulations.
Analyzes and manipulates complex network structures and graph algorithms using Python's leading network science library.
Guides the step-by-step implementation of research papers from scratch to ensure deep understanding and technical reproducibility.
Analyzes protein dynamics, evolution, and structural flexibility using Elastic Network Models and structural ensemble analysis.
Manages and analyzes multi-dimensional labeled arrays and datasets for scientific computing and physical sciences.
Accelerates Python and NumPy code using Just-In-Time (JIT) compilation for machine-speed execution.
Integrates state-of-the-art machine learning models for natural language processing, computer vision, and scientific data analysis using the Hugging Face ecosystem.
Deploys scientific models and data applications using high-performance FastAPI backends and interactive Streamlit frontends.
Manipulates and analyzes genomic alignment and variant files using the pysam library for high-throughput sequencing pipelines.
Formulates and solves complex mathematical optimization problems using a natural Pythonic syntax for linear, integer, and non-linear models.
Simplifies scientific video analysis by providing a NumPy-based interface for FFmpeg, motion estimation, and video quality metrics.
Models complex real-world systems using process-based discrete-event simulation in Python.
Optimizes Dask distributed computing performance through advanced cluster tuning, memory management, and task graph refinement.
Develops the analytical intuition to distinguish high-impact, foundational research from incremental work and academic noise.
Manages large-scale numerical datasets using the HDF5 binary format and NumPy-compatible interfaces for high-performance data science.
Automates the creation of standardized Python-based AI agents for autonomous career-focused tasks.
Scroll for more results...