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

88%

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

88%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.

A lean, highly actionable API skill: exact authentication, endpoints, a runnable example, and thoughtful error and empty-result handling, plus a content-safety guardrail. The main improvement is structural — moving the response-shape JSON and parameter details into a reference file to keep SKILL.md as a tighter overview.

Suggestions

Move the two full JSON response-shape examples (~40 lines) into a single reference file (e.g. references/response-shapes.md) and keep only one abbreviated example per endpoint inline.

Tighten the health-availability error bullet into a short "Empty results" subsection; its current single sentence packs three distinct behaviors (empty arrays + fetchedAt, the /api/health?compact=1 check, and the problems/summary.warn vs status nuance).

Add a short air-quality worked example parallel to the disease-outbreak curl so both endpoints have runnable coverage.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence throughout — no concept explanations, no padding — with an exact auth header, endpoint URLs, and a single worked curl. It falls short of 5 only because the two full inline JSON response shapes (~40 lines) and the dense health-availability error bullet could be trimmed or split out.	4 / 5
Actionability	Fully executable end-to-end: exact header name ("X-WorldMonitor-Key"), key-issuance URL, two concrete GET endpoints, a copy-paste curl example with JMESPath projection and jq, and specific error codes (401, 429 with retry/backoff). The worked example covers the common case.	5 / 5
Workflow Clarity	The single action is unambiguous (authenticate with the API key header, call the endpoint, project via jmespath), and error-recovery guidance is explicit for 401, 429, and empty result sets. This is a simple single-purpose skill with no destructive or batch operations, so the simple-skill exception applies.	5 / 5
Progressive Disclosure	No bundle files exist, and the body is organized into clear, well-labeled sections (Authentication, Endpoints, Parameters, Response shape, Errors, When NOT to use, References) with external OpenAPI and auth-matrix links. It is not a 5 because at ~105 lines the inline response-shape schemas and parameter reference are content that could live in a one-level-deep reference file.	4 / 5
	Total	18 / 20 Passed

Description

83%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.

A strong description: third-person, concise, with two concrete capabilities and an explicit, well-scoped "Use when" trigger clause. The only gaps are a few missing natural synonyms (epidemic, AQI, pollution) and no mention of the two endpoints' other capabilities.

Suggestions

Add one or two common synonyms such as "epidemic", "pollution", or "AQI" to the trigger clause to widen natural-term coverage.

Consider naming the remaining capability dimensions (e.g., filtering by location via JMESPath projection) so the 'what' is fully comprehensive.

Dimension	Reasoning	Score
Specificity	"Retrieve disease outbreak alerts and PM2.5 air-quality health warnings" names two concrete third-person actions that fully cover the skill's two data sources. It is not a 3 because nothing the skill does is omitted; not a 5 because only two actions are listed with no further concretization.	4 / 5
Completeness	It explicitly answers both: what ("Retrieve disease outbreak alerts and PM2.5 air-quality health warnings") and when ("Use when the user asks about current public-health risks in a country, city, or region"), with concrete trigger phrasing matching the top anchor.	5 / 5
Trigger Term Quality	Natural user phrases like "disease outbreak", "air-quality", "PM2.5", and "current public-health risks in a country, city, or region" are present. Common synonyms such as "epidemic", "pollution", "AQI", or "health advisory" are missing, keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	The disease-outbreak/PM2.5 niche has distinct triggers and minimal conflict risk; only minor overlap with weather/climate-hazard or travel-advisory skills, which the body's "When NOT to use" section resolves.	4 / 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: public/.well-known/agent-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.