Does this skill automatically install required libraries?

No, it identifies which libraries you SHOULD use (like PyTorch, Dask, or Zarr) based on your hardware, but you must install them yourself if they aren't present.

Why should I run this before starting a task?

Running this skill prevents resource-related crashes (OOM errors) and ensures you are using the most efficient processing strategy for your current hardware limitations.

Are there any external dependencies?

Yes, the detection script requires the 'psutil' Python package to accurately report memory and CPU statistics.

Which GPU architectures can this skill detect?

The skill supports NVIDIA GPUs via nvidia-smi, AMD GPUs via rocm-smi, and Apple Silicon (M1/M2/M3/M4) via the Metal backend and unified memory detection.

Resource Discovery & Strategy

Name: Resource Discovery & Strategy
Author: jimmc414

byjimmc414

•

324

•

数据科学与机器学习

Detects system hardware capabilities and provides optimized computational strategies for scientific and data-intensive tasks.

The Resource Discovery & Strategy skill acts as a pre-flight check for computationally intensive AI discovery and scientific tasks. It automatically scans your system for CPU cores, GPU backends (including NVIDIA CUDA, AMD ROCm, and Apple Silicon Metal), memory availability, and disk space. Based on this profile, it generates a JSON report with actionable recommendations—such as suggesting specific libraries like Dask for out-of-core computing or PyTorch-MPS for Apple hardware—ensuring that Claude-driven workflows are optimized for your specific hardware environment.

主要功能

01324 GitHub stars

02Cross-platform hardware detection for Linux, macOS, and Windows

03GPU backend identification for NVIDIA, AMD, and Apple Silicon (M1-M4)

04JSON-formatted output for easy programmatic integration with other scripts

05Automated parallel processing recommendations using joblib or Dask

06Strategic memory management advice based on available RAM vs. dataset size

使用场景

01Identifying the optimal number of worker cores for large-scale parallel simulations

02Selecting between Pandas and Dask before analyzing multi-gigabyte genomics or physics datasets

03Configuring deep learning frameworks to use the correct local hardware acceleration backend

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jimmc414/kosmos get-available-resources

For use in Claude.ai and ChatGPT

Download Skill