Does it support Apple Silicon (M1/M2/M3/M4)?

Yes, it detects Apple Silicon chips and provides recommendations for using the Metal Performance Shaders (MPS) backend in PyTorch or TensorFlow-Metal.

What hardware does this skill detect?

The skill identifies CPU cores/architecture, RAM availability, disk space, and specific GPU types including NVIDIA (via nvidia-smi), AMD (via rocm-smi), and Apple Silicon (via Metal).

How does it help with data science tasks?

It provides specific recommendations on whether to use in-memory processing or out-of-core libraries like Dask and Zarr based on your current memory constraints.

When is the best time to run this skill?

Run it at the start of any computationally intensive project, before training models, or when processing datasets larger than 2GB to ensure optimal resource utilization.

System Resource Analyzer

Name: System Resource Analyzer
Author: Microck

byMicrock

•

データサイエンスとML

Detects and reports available system hardware resources to provide strategic recommendations for computationally intensive tasks.

概要

The System Resource Analyzer is a specialized skill designed to audit your environment's hardware capabilities before executing resource-heavy operations. It automatically identifies CPU architecture, logical core counts, GPU availability (including NVIDIA, AMD, and Apple Silicon), RAM constraints, and disk space. By generating a standardized JSON report, the skill provides actionable strategies for parallel processing, memory management, and hardware acceleration, ensuring you select the most efficient libraries—such as Dask, PyTorch, or joblib—based on your specific machine constraints.

主な機能

81 GitHub stars
Strategic recommendations for parallel worker counts and memory-efficient computing
Standardized JSON output for programmatic integration with scripts
Comprehensive GPU detection for NVIDIA CUDA, AMD ROCm, and Apple Silicon Metal
Detailed CPU and memory usage snapshots for real-time resource awareness
Cross-platform support for macOS, Linux, and Windows environments

ユースケース

Selecting the correct GPU backend for machine learning model training
Determining if datasets require out-of-core computing strategies like Zarr or Dask
Optimizing parallel processing workers for large-scale data transformations

概要

主な機能

81 GitHub stars
Strategic recommendations for parallel worker counts and memory-efficient computing
Standardized JSON output for programmatic integration with scripts
Comprehensive GPU detection for NVIDIA CUDA, AMD ROCm, and Apple Silicon Metal
Detailed CPU and memory usage snapshots for real-time resource awareness
Cross-platform support for macOS, Linux, and Windows environments

ユースケース

Selecting the correct GPU backend for machine learning model training
Determining if datasets require out-of-core computing strategies like Zarr or Dask
Optimizing parallel processing workers for large-scale data transformations