This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
8.3
Rating
0
Installs
Tools & Utilities
Category
Excellent skill with comprehensive documentation and clear utility. The description perfectly captures when and why to use this skill, making it easy for a CLI agent to invoke appropriately. Task knowledge is thorough with detailed explanations of resource detection, output format, strategic recommendations, and concrete usage examples across multiple scenarios (data loading, parallel processing, GPU acceleration). Structure is very clear with logical sections, though the SKILL.md is somewhat lengthy - minor details could potentially live in separate docs, but the content justifies the length. Novelty is strong: while resource detection itself is straightforward, the strategic recommendations layer (suggesting specific libraries, worker counts, and computational strategies based on detected resources) provides genuine value that would otherwise require significant agent reasoning and tokens. The skill effectively front-loads architectural decisions for scientific computing tasks, reducing repeated detection logic and enabling smarter resource-aware workflows. Minor deduction on novelty only because basic resource detection is relatively simple - the primary value is in the recommendation engine and workflow integration.
K-Dense-AI
Skill Author
Loading SKILL.md…
Skill Author
