get-available-resources

Detect host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a clearly resource-sensitive local workload. Produces a redacted JSON snapshot and conservative planning helpers without stress tests or assuming visible host hardware is usable.

Quality

92%

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

100%

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

A well-structured, actionable, and lean body for a complex multi-platform skill: executable commands throughout, explicit validation and provenance feedback, and clean one-level-deep reference disclosure. Minor time-sensitive elements (a refresh date and version pins) are tied to provenance rather than padding, so conciseness holds.

Dimension	Reasoning	Score
Conciseness	The body is dense but lean: it assumes Claude knows what CPUs/cgroups/filesystems are and spends tokens on non-obvious specifics (field semantics, what to keep separate, redaction contract, platform behaviors) rather than basic concepts, so most tokens earn their place.	3 / 3
Actionability	It supplies many copy-paste-ready, fully executable commands with concrete flags and arguments (e.g. `python scripts/plan_workload.py resource-snapshot.json --workload cpu --tasks 100 --memory-per-worker-mib 2048`), matching the executable-and-complete anchor.	3 / 3
Workflow Clarity	The detect → (optionally enhance) → plan → validate/diff flow is clear, with an explicit validation step (`snapshot_tools.py validate`) and a provenance/warnings feedback loop for error recovery; operations are explicitly read-only so the destructive-ops cap does not apply.	3 / 3
Progressive Disclosure	The overview stays concise and points to verified one-level-deep references (resource_semantics.md, snapshot_schema.md, sources.md) plus a clean "Bundled files" listing with per-file descriptions, giving easy navigation without nested references.	3 / 3
	Total	12 / 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.

A specific, complete, and distinctive description that clearly states both capability and trigger conditions. Its main weakness is trigger-term breadth: the phrasing is competent but somewhat technical rather than covering the natural variations users actually say.

Suggestions

Broaden trigger terms toward natural user phrasing (e.g. add "how much CPU/memory is available", "how many workers/cores can I use", "check available resources") alongside the existing technical triggers.

Consider a shorter explicit "Use when…" clause listing a few concrete natural phrases to improve trigger coverage without losing precision.

Dimension	Reasoning	Score
Specificity	It enumerates concrete detection actions across multiple resource domains ("effective CPU, memory, disk, scheduler, container, and accelerator limits") and names two concrete outputs ("redacted JSON snapshot and conservative planning helpers"), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Both halves are explicit: the "what" (detect inventory/limits, produce snapshot and helpers) and the "when" ("when a user asks for resource-aware planning or before a clearly resource-sensitive local workload"), satisfying the explicit-trigger-guidance requirement.	3 / 3
Trigger Term Quality	The triggers ("resource-aware planning", "clearly resource-sensitive local workload") are relevant and natural-ish but lean technical and miss common variations a user would actually say (e.g. "how many cores", "available memory", "what resources can I use").	2 / 3
Distinctiveness Conflict Risk	Host-resource detection for conservative planning is a clear, narrow niche with distinct triggers, unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/get-available-resources/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.