monitoring-database-health

Monitor use when you need to work with monitoring and observability. This skill provides health monitoring and alerting with comprehensive guidance and automation. Trigger with phrases like "monitor system health", "set up alerts", or "track metrics".

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

80%Weight 40%Scale 1-3

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

The content is highly actionable and token-efficient, packed with executable SQL and concrete thresholds, but it lacks validation checkpoints in its workflow and keeps all material inline instead of splitting it into the provided bundle files.

Suggestions

Add an explicit validation step after step 9 (e.g., run the cron script once and confirm JSON output / verify alerts fire on a deliberately-breached threshold) before relying on it.

Move the per-check SQL into assets/example_queries.sql and the monitoring script into scripts/metric_collection.py, then reference them from the body so content is one level deep instead of inline.

Reference the existing scripts/ placeholders (database_connection_test.sh, alert_trigger.py) from the relevant steps so the bundle is actually wired into the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and token-efficient: a one-sentence overview, tight prerequisites, and concrete SQL with thresholds, with no padding explaining what databases or monitoring are — every section earns its place.	3 / 3
Actionability	Each health check provides fully executable SQL/commands with explicit alert thresholds (e.g., 80% utilization, 95% cache hit), making the guidance copy-paste ready.	3 / 3
Workflow Clarity	Steps are numbered 1–10 in a clear sequence, but there are no explicit validation checkpoints, and step 9 (building a cron script that runs every 60s) is a batch operation with no verify-the-script-works feedback loop, capping the score.	2 / 3
Progressive Disclosure	The body is well-sectioned but monolithic — all SQL is inline despite bundle placeholders (assets/example_queries.sql, scripts/metric_collection.py) that should hold it, and none of those bundle files are referenced or signaled from the body.	2 / 3
	Total	10 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 explicitly covers both what and when with natural trigger phrases, but is weakened by vague fluff ('comprehensive guidance and automation') and a generic domain that omits 'database', creating conflict risk with other monitoring skills.

Suggestions

Replace 'comprehensive guidance and automation' with concrete capabilities (e.g., 'checks connections, cache hit ratio, replication lag, vacuum health, and lock contention').

Add 'database' to the domain and triggers so the skill is distinguishable from general monitoring skills (e.g., 'Monitor PostgreSQL, MySQL, and MongoDB health').

Fix the awkward opener 'Monitor use when...' to a clean third-person verb phrase such as 'Monitor database server health. Use when...'.

Dimension	Reasoning	Score
Specificity	Names the domain ('monitoring and observability') and a couple of actions ('health monitoring and alerting') but does not list multiple concrete actions, and 'comprehensive guidance and automation' is vague fluff/over-claim rather than specific capability.	2 / 3
Completeness	Answers both what ('health monitoring and alerting') and when ('use when you need to work with monitoring and observability' plus explicit 'Trigger with phrases like...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would actually say — 'monitor system health', 'set up alerts', 'track metrics' — giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	The description never mentions databases, so 'monitoring and observability' with triggers like 'set up alerts' and 'track metrics' is generic and would overlap with general server/app/network monitoring skills.	2 / 3
	Total	10 / 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
Path: plugins/database/database-health-monitor/skills/monitoring-database-health/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.