What dependencies are needed for resource detection?

The detection script requires the 'psutil' Python package; other functions utilize the standard Python library and system utilities like nvidia-smi.

Does this skill support Apple Silicon M-series chips?

Yes, it provides full support for Apple Silicon (M1/M2/M3/M4) and detects Metal support for unified memory GPU acceleration.

How does this help prevent memory errors during data analysis?

The skill identifies available RAM before task execution and recommends out-of-core libraries like Dask or Zarr if the dataset size exceeds safe memory thresholds.

Can I use the output of this skill directly in my Python code?

Yes, the skill generates a .claude_resources.json file that can be easily parsed by your scripts to dynamically set worker counts or device backends.

Scientific Computing Resource Detector

Name: Scientific Computing Resource Detector
Author: ricable

byricable

•

Ciencia de Datos y ML

Detects hardware resources and provides strategic recommendations for optimal scientific computing and data processing.

The Scientific Computing Resource Detector is a specialized skill designed to bridge the gap between AI development and physical hardware constraints. By automatically identifying CPU cores, GPU backends (including NVIDIA CUDA, AMD ROCm, and Apple Metal), and memory availability, it generates a structured JSON report with actionable strategic recommendations. This allows developers and AI agents to make informed architectural decisions—such as selecting between parallel processing, out-of-core computing, or GPU acceleration—before beginning resource-heavy tasks like model training or large-scale genomic analysis.

Características Principales

01Structured JSON output for programmatic optimization of scripts

021 GitHub stars

03Cross-platform support for macOS, Linux, and Windows environments

04Comprehensive hardware detection for CPU, RAM, and Disk space

05Strategic library recommendations for Dask, PyTorch, JAX, and Joblib

06Multi-backend GPU identification including NVIDIA, AMD, and Apple Silicon Metal

Casos de Uso

01Determining if massive datasets require memory-efficient, out-of-core strategies

02Detecting available GPU backends to select the correct ML framework configuration

03Optimizing worker counts for parallel data processing pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add ricable/ultimate-ai-agent get-available-resources

For use in Claude.ai and ChatGPT

Download Skill