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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/general/get-available-resources/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete commands and code, but it is verbose and self-duplicating, and it references a script that is not present in the bundle. Workflow steps are clear but lack validation checkpoints.

Suggestions

Ship the referenced `scripts/detect_resources.py` or remove the invocation; scoring progressive disclosure against the actual bundle shows the key referenced path is missing.

Collapse the full JSON output example and the "Strategic Recommendations" section into one — they restate the same recommendation structure — to cut roughly a third of the body.

Add a validation checkpoint after Step 1 (e.g. "Confirm `.claude_resources.json` was created and is non-empty before proceeding") to move workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded: the full ~55-line JSON output example duplicates the recommendation structure later re-explained in "Strategic Recommendations", and Best Practices/Platform Support/Troubleshooting plus the K-Dense Web promo add bulk Claude largely doesn't need.	2 / 3
Actionability	Provides fully executable guidance — the exact command `python scripts/detect_resources.py` with flags, complete Python snippets for reading and applying the JSON, and the install command `uv pip install psutil` — copy-paste ready.	3 / 3
Workflow Clarity	Three numbered steps are clearly sequenced (Run Detection → Read and Apply → Make Informed Decisions), but there are no explicit validation checkpoints or error-recovery feedback loops (e.g. verify the JSON was written, handle a failed detection), keeping it at anchor 2.	2 / 3
Progressive Disclosure	No bundle files exist, yet the body repeatedly references `scripts/detect_resources.py`, which is absent; meanwhile the full JSON spec, recommendation tables, multiple code blocks, and troubleshooting all sit inline in SKILL.md rather than being split into referenced files.	2 / 3
	Total	9 / 12 Passed

Description

85%

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

The description is strong: it states concrete capabilities, gives explicit when-to-use triggers, and carves out a distinct niche. Its main weakness is trigger phrasing that is somewhat verbose and generic rather than crisp natural user language.

Suggestions

Tighten trigger terms to the exact phrases users say (e.g. "Use when training a model, analyzing a large dataset, or running a heavy simulation") rather than the generic "any task where resource constraints matter".

Trim the library name-dropping (joblib, Dask, Zarr, PyTorch, JAX) from the description; those belong in the body, not the trigger summary.

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 enumerates parallel processing/out-of-core/GPU/memory strategies — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (detect/report resources, create JSON with recommendations) and when ("Use this skill before running analyses, training models, processing large datasets"), with an explicit 'Use this skill before...' trigger clause.	3 / 3
Trigger Term Quality	Contains relevant natural terms ("training models", "processing large datasets", "running analyses") but leans technical and generic ("any task where resource constraints matter"), missing some crisp common variations a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — pre-task resource detection for compute-intensive scientific work — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/get-available-resources/SKILL.md
Commit: df37802

Reviewed: about 2 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.