Tessl • The package manager for agent skills

SkillPublic

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

84%

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

67%Weight 40%Scale 1-5

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

Highly actionable content with a verified script, correct CLI documentation, and a clear usage sequence, but it is padded with a full example JSON output, duplicated recommendation thresholds, and code examples that teach familiar patterns. Trimming to the command, a condensed output schema, and one decision example would raise token efficiency substantially.

Suggestions

Replace the 57-line example JSON with a condensed schema showing the key fields (or move it to references/output-schema.md), keeping only the fields the usage snippets rely on.

Remove the Strategic Recommendations threshold tables — the script computes these, so Claude only needs the script's output, not a restatement of its branching logic.

Cut the three Step 2/3 code snippets down to one representative example; patterns like joblib Parallel and torch.device selection are already known, so one snippet plus the field names suffices.

Dimension	Reasoning	Score
Conciseness	Several padded sections: a 57-line example JSON dump, a full restatement of the script's recommendation thresholds (duplicating logic the script itself computes), three separate usage code snippets teaching patterns Claude already knows (joblib Parallel, torch.device), and generic best-practice/troubleshooting advice ("Close other applications before detection", "Memory readings are snapshots"). Accurate but noticeably verbose.	2 / 5
Actionability	Fully executable guidance: the exact command "python scripts/detect_resources.py" with documented -o/-v flags (verified against the script's argparse), the psutil install command, and copy-paste-ready snippets for reading the output JSON and selecting a device. Common cases are covered.	5 / 5
Workflow Clarity	A clear three-step sequence (run detection → read and apply recommendations → make informed decisions) with a troubleshooting section covering failure modes (GPU not detected, script failure, inaccurate readings). Not a destructive/batch operation, so no validation cap applies, but the main flow lacks an explicit checkpoint confirming the JSON was created and populated before decisions are based on it.	4 / 5
Progressive Disclosure	The single bundle file (scripts/detect_resources.py) is real, clearly referenced, and one level deep; sections are well organized with descriptive headers. Minor gap: the full output schema and threshold tables are inlined in SKILL.md when they could live in a references/ file, though for a one-script skill keeping them inline is defensible.	4 / 5
	Total	15 / 20 Passed

Description

96%Weight 40%Scale 1-5

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 explicitly states what the skill does, what it outputs, and when to use it, with concrete natural-language triggers. The only weakness is the broad "any task where resource constraints matter" clause, which slightly raises the chance of firing for the wrong skill.

Suggestions

Tighten the final trigger clause by dropping the open-ended "or any task where resource constraints matter" in favor of the already-specific list (analyses, model training, large datasets, simulations).

Dimension	Reasoning	Score
Specificity	Concrete actions are enumerated: "detect and report available system resources (CPU cores, GPUs, memory, disk space)" and "creates a JSON file with resource information and strategic recommendations", with named libraries (joblib, multiprocessing, Dask, Zarr, PyTorch, JAX) for each decision category. This matches the comprehensive-coverage anchor; the only generic verb ("report") is outweighed by the specific ones.	5 / 5
Completeness	Both what (detect CPU/GPU/memory/disk, write a JSON file with strategic recommendations) and when ("Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter") are explicit with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural user phrases are well covered: "running analyses", "training models", "processing large datasets", "computationally intensive", plus domain nouns users would actually say (CPU, GPU, memory, disk space, resource constraints). Matches the comprehensive natural-terms anchor; no file extensions apply to this domain.	5 / 5
Distinctiveness Conflict Risk	The niche (hardware/resource detection before compute tasks) is distinct, but the catch-all clause "or any task where resource constraints matter" is broad enough to overlap with profiling, benchmarking, or environment-setup skills. Mostly distinct with minor overlap risk — not the minimal-conflict top anchor.	4 / 5
	Total	19 / 20 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
Revision: 6a85742

Reviewed: 22 days ago

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.

get-available-resources

Table of Contents

Is this your skill?