Does it support Apple Silicon Macs?

Yes, it is specifically optimized to detect M1, M2, M3, and M4 chips, identifying unified memory and recommending the Metal Performance Shaders (MPS) backend.

Why should I run this at the start of a project?

Running it early allows the AI to make informed architectural decisions, such as setting the correct number of parallel workers or choosing the right data loading strategy before execution starts.

How does it help with large datasets?

The skill analyzes available memory and recommends specific libraries like Dask, Zarr, or H5py if the dataset size is likely to cause out-of-memory errors.

What dependencies are required?

The skill primarily requires the psutil Python package to perform system-level hardware inspection.

What hardware does this skill detect?

It identifies logical and physical CPU cores, total and available RAM, disk space, and specific GPU hardware including NVIDIA (CUDA), AMD (ROCm), and Apple Silicon (Metal).

Scientific Resource Detector

Name: Scientific Resource Detector
Author: Yezez9

byYezez9

0•

データサイエンスとML

Analyzes system hardware to provide optimized strategy recommendations for high-performance scientific computing and data processing tasks.

Scientific Resource Detector is a specialized utility designed for computationally intensive workflows. It automatically audits system hardware—including CPU architecture, GPU backends (NVIDIA CUDA, AMD ROCm, Apple Silicon Metal), RAM, and disk availability—to generate a structured JSON report. Beyond simple detection, the skill provides actionable strategic recommendations, helping Claude determine whether to employ parallel processing, out-of-core computing, or specific GPU acceleration libraries. This ensures that data science and machine learning tasks are initialized with the most efficient architectural decisions based on actual environment constraints.

主な機能

01Detailed JSON reporting of CPU, RAM, and disk utilization

02Memory-efficient strategy suggestions for large-scale datasets

03Automated backend selection for PyTorch, JAX, and TensorFlow

040 GitHub stars

05Multi-platform GPU detection for NVIDIA, AMD, and Apple Silicon (Metal)

06Context-aware recommendations for parallel worker counts (joblib/Dask)

ユースケース

01Selecting the optimal number of parallel processes to maximize CPU throughput without system lag

02Determining if a multi-gigabyte dataset requires Dask/Zarr or can fit in local RAM

03Configuring deep learning frameworks to utilize the correct hardware acceleration backend automatically

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yezez9/research-agent get-available-resources

For use in Claude.ai and ChatGPT

主な機能

01Detailed JSON reporting of CPU, RAM, and disk utilization

02Memory-efficient strategy suggestions for large-scale datasets

03Automated backend selection for PyTorch, JAX, and TensorFlow

040 GitHub stars

05Multi-platform GPU detection for NVIDIA, AMD, and Apple Silicon (Metal)

06Context-aware recommendations for parallel worker counts (joblib/Dask)

ユースケース

01Selecting the optimal number of parallel processes to maximize CPU throughput without system lag

02Determining if a multi-gigabyte dataset requires Dask/Zarr or can fit in local RAM

03Configuring deep learning frameworks to utilize the correct hardware acceleration backend automatically