collecting-infrastructure-metrics

Collect comprehensive infrastructure performance metrics across compute, storage, network, containers, load balancers, and databases. Use when monitoring system performance or troubleshooting infrastructure issues. Trigger with phrases like "collect infrastructure metrics", "monitor server performance", or "track system resources".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

35%

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

The content is well-sectioned and readable but stays at a descriptive level: it explains the process and concepts rather than providing executable guidance, and it fails to wire its bundled scripts into the workflow. Tightening the prose and adding concrete commands would materially improve it.

Suggestions

Add executable examples — actual Prometheus/Datadog/CloudWatch config snippets or script invocations (e.g. `python scripts/configure_prometheus.py ...`) — instead of describing the steps in prose.

Reference the bundled scripts from the body (e.g. 'See scripts/configure_prometheus.py') so the supporting files are discoverable and progressive disclosure is one level deep.

Collapse the redundant 'How It Works' and 'Instructions' sections into one sequenced workflow with explicit validation checkpoints (e.g. verify agent connectivity before aggregation), and trim generic explanations of KPIs and dashboards that Claude already knows.

Dimension	Reasoning	Score
Conciseness	The body is mostly organized but includes generic prose Claude already knows ('identifies key performance indicators (KPIs)', dashboard/agent explanations) and redundant sections where 'How It Works' and 'Instructions' restate the same steps, so it could be tightened.	2 / 3
Actionability	Despite bundled scripts existing, the body gives no executable code, commands, or config snippets — it describes actions ('Configure Prometheus to collect CPU, memory, disk I/O, and network bandwidth metrics') rather than instructing, matching the lowest anchor.	1 / 3
Workflow Clarity	Steps are sequenced (the 4-step 'How It Works' and 6-step 'Instructions'), but there are no explicit validation checkpoints within the workflow for batch agent configuration across infrastructure, capping it at 2.	2 / 3
Progressive Disclosure	The ~90-line body is sectioned but monolithic, and the bundled scripts listed in scripts/README.md (e.g. configure_prometheus.py) are never referenced or linked from the body, so navigation to supporting material is not signaled.	2 / 3
	Total	7 / 12 Passed

Description

90%

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, well-structured description that clearly states purpose, use cases, and natural trigger phrases with broad domain coverage. The only weakness is that the capability is expressed as a single action rather than multiple distinct concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain comprehensively ('compute, storage, network, containers, load balancers, and databases') but relies on a single action verb ('Collect ... metrics'), so it names the domain and an action without listing multiple distinct concrete actions as the top anchor requires.	2 / 3
Completeness	It explicitly answers both 'what' ('Collect comprehensive infrastructure performance metrics across ...') and 'when' ('Use when monitoring system performance or troubleshooting infrastructure issues') with explicit trigger guidance.	3 / 3
Trigger Term Quality	It provides natural trigger phrases users would actually say ('collect infrastructure metrics', 'monitor server performance', 'track system resources'), giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Infrastructure metrics collection is a clear niche with distinct triggers, making it 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 days 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.