monitor-health-alerts

Retrieve disease outbreak alerts and PM2.5 air-quality health warnings. Use when the user asks about current public-health risks in a country, city, or region.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-5

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

The body is a tight, fully actionable API reference with a copy-paste example, sensible error/empty-result guidance, and clean sectioning. No bundle files are needed and none are missing.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows; every section (auth, endpoints, params, response shape, example, errors) earns its tokens. It is not a 4 because there is no trimmable padding to find.	5 / 5
Actionability	A copy-paste curl example with the real auth header and a JMESPath projection, plus full endpoint URLs and response shapes, gives fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	This is a simple single-purpose read skill where the action (authenticated GET) is unambiguous, and the Errors section adds an explicit empty-result validation checkpoint ("retry or check /api/health?compact=1 before treating an empty set as all clear").	5 / 5
Progressive Disclosure	A single well-organized SKILL.md with no bundle files needed; the References section points one level deep to the OpenAPI and auth-matrix URLs, and sections are clearly signaled for navigation.	5 / 5
	Total	20 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 cleanly states what the skill does and when to use it, with a clear niche and low conflict risk. Trigger terms are strong though not exhaustive of synonyms.

Suggestions

Add a couple of casual synonyms (e.g. "air pollution", "outbreaks near me") to broaden natural trigger coverage.

If a third capability exists, naming it would lift specificity from two to several concrete actions.

Dimension	Reasoning	Score
Specificity	"Retrieve disease outbreak alerts and PM2.5 air-quality health warnings" names the domain with two concrete retrieve actions, matching the anchor for 1-2 concrete actions without being comprehensive; not a 4 because it lists only two operations.	3 / 5
Completeness	"Retrieve disease outbreak alerts and PM2.5 air-quality health warnings" answers what, and "Use when the user asks about current public-health risks in a country, city, or region" answers when with a concrete trigger phrase.	5 / 5
Trigger Term Quality	"disease outbreak alerts", "PM2.5 air-quality health warnings", "current public-health risks", and "country, city, or region" give good natural keyword coverage; not a 5 because common synonyms and casual phrasings are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	The combined disease-outbreak and PM2.5 air-quality niche with a geo-scoped trigger is distinct and unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: koala73/worldmonitor
Path: skills/monitor-health-alerts/SKILL.md
Commit: da33e7a

Reviewed: 3 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.