get-available-resources

Detect host CPU, GPU, memory, and disk resources into a .claude_resources.json file.

3|Updated Oct 26, 2025
One-click install
npx skills add https://github.com/xiechy/climate-ai --skill get-available-resources
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: get-available-resources
Source: https://github.com/xiechy/climate-ai/tree/main/scientific-helpers/get-available-resources
Command: npx skills add https://github.com/xiechy/climate-ai --skill get-available-resources

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires psutil, and includes scripts (resource) components.

What problem does it solve?

Scientific computing tasks often fail or run inefficiently due to unknown or mismanaged system resources. This skill proactively identifies available CPU, GPU, memory, and disk space, providing strategic recommendations to prevent resource bottlenecks and optimize computational approaches.

Core Features & Use Cases

  • Automated Resource Detection: Automatically identifies CPU cores, GPU availability (NVIDIA, AMD, Apple Silicon), total/available memory, and disk space.
  • Strategic Recommendations: Generates tailored advice for parallel processing, memory management, GPU acceleration, and large data handling.
  • Use Case: Before training a large neural network, use this skill to determine if a GPU is available and which backend (CUDA, Metal) to configure, ensuring optimal performance.

Quick Start

Run the resource detection script to get a .claude_resources.json file with system info and recommendations. python scripts/detect_resources.py

Frequently Asked Questions about get-available-resources

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect available CPU and GPU resources before running compute-intensive tasks?

Resource detection identifies your system's CPU cores, GPU availability (NVIDIA, AMD, Apple Silicon), memory, and disk space to inform parallelism and backend choices. Run the detection script to generate a .claude_resources.json file with system info and optimization recommendations for your workload.

Why does my model training or large-scale processing job fail or run slowly?

Unknown or mismanaged system resources cause inefficient execution. Resource detection proactively identifies CPU, GPU, and memory constraints, then generates tailored recommendations for parallel processing strategies, memory management, and backend selection to prevent bottlenecks.

How do I choose between CPU and GPU acceleration for my scientific computing task?

Resource detection automatically identifies GPU availability and type (CUDA, Metal, ROCm), then recommends the optimal backend. This lets you configure your framework correctly before training, ensuring you use available acceleration without manual hardware checking.

Can I use resource detection with out-of-core processing for large datasets?

Yes. Resource detection measures available memory and disk space, generating recommendations for out-of-core strategies and appropriate chunk sizes. This informs whether to use memory-mapped files, streaming, or distributed approaches for your data size.

What system information does resource detection capture?

The skill captures OS, CPU core count, total and available memory, disk space, and GPU details. It outputs a .claude_resources.json file with timestamp, hardware specs, and strategic recommendations for parallelism, memory usage, and backend selection.

Do I need to manually check system specs before running the detection script?

No. The script automatically detects all system resources using psutil without requiring manual intervention. Run it at the start of your analysis or training pipeline to generate configuration recommendations.