monitor-webcams

Discover live webcams in a map viewport and resolve thumbnails or player URLs. Use when the user asks for visual context near a location, route, border, port, or city.

Quality

91%

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

96%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.

An excellent, dense API skill body: executable examples with validation and error-recovery feedback, zero padding, and clear section structure. The only structural nit is that the full parameter and response reference is inlined in SKILL.md rather than split into a reference file, which keeps it at 4 on progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Every section carries API-specific knowledge Claude cannot already know (the "X-WorldMonitor-Key" header, "Omitted REST numeric params are interpreted as `0`", response shapes, error codes), delivered via tables and code rather than prose. There is no concept re-teaching or padding, matching anchor 5's lean-and-efficient profile.	5 / 5
Actionability	The worked example is fully executable copy-paste-ready bash: real endpoint URLs, required headers, `--data-urlencode` for each param, `jq` extraction, and exact response JSON for both endpoints. This matches anchor 5's complete, executable coverage of the common case.	5 / 5
Workflow Clarity	"First list webcams in a viewport, then resolve a selected `webcamId`" gives an explicit two-step sequence, and the worked example includes a real validation checkpoint (empty WEBCAM_ID guard with recovery guidance "increase zoom or adjust bounds") plus 429 backoff and in-band `error`-field handling. The skill is read-only, so no destructive-operation cap applies.	5 / 5
Progressive Disclosure	Sections are well organized and external references are clearly signaled one level deep (OpenAPI, auth matrix), and the inline param/response tables are appropriate for a two-endpoint API with no bundle files. It exceeds the under-50-line simple-skill exception, and the full parameter/response reference could arguably live in a separate file, placing it at anchor 4 rather than 5.	4 / 5
	Total	19 / 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, concrete about both what the skill does and when to use it, with an explicit trigger clause. The main gap is thinner synonym coverage (no "camera" or "live view" variants) and slight overlap risk with imagery-adjacent skills.

Dimension	Reasoning	Score
Specificity	"Discover live webcams in a map viewport and resolve thumbnails or player URLs" names the domain plus concrete, endpoint-level actions covering the skill's full scope. It lists two actions rather than the several of anchor 5, but sits above anchor 3 because the actions are specific and cover the complete capability set.	4 / 5
Completeness	It clearly answers both questions: the "what" ("Discover live webcams in a map viewport and resolve thumbnails or player URLs") and an explicit "Use when..." clause with concrete trigger phrases ("location, route, border, port, or city"), matching anchor 5 exactly. Not 4 because the when-clause is already explicit and concrete rather than merely adequate.	5 / 5
Trigger Term Quality	"Use when the user asks for visual context near a location, route, border, port, or city" plus "webcams" gives good natural-term coverage. A few natural synonyms users would say ("camera", "live view", "traffic camera") are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"webcams", "map viewport", and "thumbnails or player URLs" establish a clear niche with distinct triggers, but "visual context near a location" is broad enough to overlap with satellite-imagery or map-imagery skills. Minor overlap risk with closely related skills places it at anchor 4 rather than 5.	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: skills/monitor-webcams/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.