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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 engine-specific executable queries and clear sequencing, but it keeps everything inline without leveraging the bundle files and lacks explicit validation feedback loops for the database operations it drives.

Suggestions

Add explicit validate→fix→retry checkpoints into the monitoring workflow (e.g., verify the health-check query completes within statement_timeout before evaluating thresholds) rather than relying on a separate Error Handling table.

Move the long inline SQL queries for each engine into scripts/ or references/ files and reference them from SKILL.md so the main body stays an overview, using the already-present bundle directories.

Trim redundancy between the Overview KPI list and the Instructions, and either provide the cron/JSON monitoring script (steps 9–10) as a real bundled file or mark it as to-be-generated.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient with executable SQL and minimal concept re-explanation, but the Overview enumerates KPIs that are then repeated verbatim in the Instructions and steps 9–10 describe deliverables in prose, leaving room to tighten.	2 / 3
Actionability	Provides concrete, engine-specific SQL queries with exact thresholds (e.g., 'utilization above 80%', 'lag above 30 seconds'), named system views, and a defined cron/JSON output format — copy-paste ready and fully executable.	3 / 3
Workflow Clarity	Steps 1–10 are clearly sequenced with thresholds as implicit checkpoints, but for database operations the rubric expects explicit validate→fix→retry feedback loops, and the workflow relies on a separate Error Handling table rather than embedding validation steps, capping this at 2.	2 / 3
Progressive Disclosure	The skill is a single well-organized file with clear sections, but all content is inline and it never points into the provided bundle (scripts/, references/, assets/), which are only placeholder READMEs rather than clearly signaled one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly states its purpose and provides explicit 'Use when' triggers, giving strong completeness, but it is vague about specific capabilities and the triggers are generic enough to risk overlap with non-database monitoring skills.

Suggestions

Replace 'comprehensive guidance and automation' with concrete actions such as 'check connection utilization, replication lag, cache hit ratio, and lock contention across PostgreSQL, MySQL, and MongoDB'.

Add database-specific trigger phrases (e.g., 'check database health', 'alert on slow queries', 'monitor replication lag') to sharpen distinctiveness.

Mention the supported database engines (PostgreSQL, MySQL, MongoDB) in the description to reduce conflict with general monitoring skills.

Dimension	Reasoning	Score
Specificity	Names the monitoring/observability domain and the actions 'health monitoring and alerting', but offers only vague capability language ('comprehensive guidance and automation') rather than concrete enumerated actions, so it lands above score 1 but below the multi-action specificity of 3.	2 / 3
Completeness	Explicitly answers both what ('provides health monitoring and alerting') and when ('use when you need to work with monitoring and observability' plus explicit trigger phrases), matching the anchored 3 example.	3 / 3
Trigger Term Quality	Includes several natural trigger phrases ('monitor system health', 'set up alerts', 'track metrics') a user might say, but coverage is thin and misses common variations like 'check database health' or 'alert on slow queries'.	2 / 3
Distinctiveness Conflict Risk	The description never mentions databases and uses broad terms ('monitoring and observability', 'monitor system health') that could overlap with general infrastructure monitoring skills, so it is distinguishable only somewhat.	2 / 3
	Total	9 / 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: 2cafb23

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.