get-available-resources

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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is highly actionable with a clear three-step workflow and a real supporting script, but it is padded with a large inline JSON example and recommendation tables that duplicate the script's embedded logic, and it keeps reference-grade detail inline rather than splitting it out.

Suggestions

Move the full JSON output schema and the four recommendation matrices into a separate REFERENCE.md and reference it one level deep, keeping only a concise sample in SKILL.md.

Trim the Best Practices and Troubleshooting sections to a few essential bullets; the script and JSON are self-documenting for Claude.

Replace the static JSON example with a short excerpt plus a note to run the script, since the exact output is generated dynamically.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and executable, but the full ~55-line JSON example, the lengthy recommendation tables that duplicate logic already embedded in detect_resources.py, and sections like Best Practices/Troubleshooting add explanatory padding that Claude could derive from the script.	2 / 3
Actionability	It provides fully executable commands (`python scripts/detect_resources.py`), complete CLI flags, copy-paste-ready Python snippets that read the JSON and branch on recommendations, and the underlying script is real and complete.	3 / 3
Workflow Clarity	The process is clearly sequenced as three numbered steps (run detection → read JSON → make decisions), with the script serving as an implicit validation checkpoint and the JSON output providing feedback the user can act on; the single-task workflow is unambiguous.	3 / 3
Progressive Disclosure	Structure is well-organized with clear sections, but the bulk of detailed reference material (the full JSON schema and recommendation matrices) is inline in SKILL.md rather than split into a referenced file; only scripts/detect_resources.py is referenced one level deep.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly and concisely covers what the skill does, when to trigger it, and which library ecosystem it informs, using third person throughout. Trigger terms are natural and the niche is clearly distinguished.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions: 'detect and report available system resources (CPU cores, GPUs, memory, disk space)' and 'creates a JSON file with resource information and strategic recommendations', directly naming parallel processing, out-of-core computing, GPU acceleration, and memory-efficient strategies.	3 / 3
Completeness	It explicitly states what it does (detect/report resources, create JSON with recommendations) and when to use it ('Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter'), satisfying both the what and when with explicit triggers.	3 / 3
Trigger Term Quality	It includes natural terms users would say such as 'running analyses', 'training models', 'processing large datasets', alongside library keywords (joblib, Dask, PyTorch, JAX) that a user working with scientific computing would naturally mention.	3 / 3
Distinctiveness Conflict Risk	The niche — system resource detection at the start of computationally intensive scientific tasks — is distinct and unlikely to overlap with other skills; its 'start of any computationally intensive scientific task' trigger is specific.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/get-available-resources/SKILL.md
Commit: f627ab5

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.