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.

A thorough, actionable skill body with executable code and a clear sequenced workflow, weakened mainly by length and inline redundancy that could be moved to reference files. The detection script it depends on is present and correctly referenced.

Suggestions

Move the full .claude_resources.json output spec and/or the Strategic Recommendations threshold tables into a reference file (e.g. references/output_schema.md) and link to it from SKILL.md to reduce inline length and improve progressive_disclosure.

De-duplicate the recommendation thresholds: they currently appear both inside the JSON example and again as a bulleted 'Strategic Recommendations' section — keep one authoritative copy.

Trim the JSON example to the essential fields and note that the script emits the full schema, cutting the ~57-line block that largely restates output the user can inspect directly.

Dimension	Reasoning	Score
Conciseness	Mostly relevant and domain-specific (not explaining basics Claude knows), but ~260 lines with a full 57-line JSON output example plus a 'Strategic Recommendations' section that re-states thresholds already shown in the JSON — could be tightened. Not a 1 because it avoids basic-concept padding; not a 3 because of the redundancy and length.	2 / 3
Actionability	Provides fully executable guidance: 'python scripts/detect_resources.py', documented '-o/--output' and '-v/--verbose' flags, and copy-paste-ready snippets for reading the JSON, applying parallel workers, and selecting a torch device. Not a 2 because the code is real and complete rather than pseudocode.	3 / 3
Workflow Clarity	Clear Step 1 (run detection) → Step 2 (read and apply recommendations) → Step 3 (make informed decisions) sequence with concrete commands; the task is read-only/non-destructive so the destructive-validation cap does not apply, and the Troubleshooting section supplies error-recovery guidance.	3 / 3
Progressive Disclosure	Well-organized into clear sections and references one real bundle file (scripts/detect_resources.py), but it is monolithic — the full output JSON spec and recommendation threshold tables sit inline in SKILL.md with no reference docs to offload detail to. Not a 1 because structure and navigation are good; not a 3 because nothing is split into separate one-level-deep reference files.	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, specific description that clearly states what the skill does and gives explicit natural-language triggers for when to use it. It avoids vagueness and over-claims while naming concrete libraries and resource types.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'detect and report available system resources (CPU cores, GPUs, memory, disk space)', 'creates a JSON file', and informing decisions 'such as...parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX)' — matching the comprehensive-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('detect and report available system resources...creates a JSON file with resource information and strategic recommendations') and when ('Use this skill before running analyses, training models, processing large datasets...'), so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say — 'running analyses, training models, processing large datasets, or any task where resource constraints matter' — not just technical jargon, matching good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — pre-task system resource detection for compute-heavy work — with distinct triggers unlikely to fire for unrelated skills; not generic enough to conflict.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/other/get-available-resources/SKILL.md
Commit: 52845c3

Reviewed: about 10 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.