CtrlK
BlogDocsLog inGet started
Tessl Logo

track-vessel-traffic

Retrieve a point-in-time AIS vessel-traffic snapshot with disruption candidates and optional tanker overlay, filterable by bounding box. Use when the user asks what ships are in an area, or whether maritime traffic is disrupted.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An exemplary single-file API skill: everything needed to make a correct authenticated call is present exactly once, with no padding, an executable worked example, an explicit degradation contract that prevents the worst misinterpretation (reading no-data as no-ships), and clear routing to sibling skills for adjacent use cases.

DimensionReasoningScore

Conciseness

The body is lean throughout: a parameter table instead of prose, a compact response shape, and no explanation of concepts Claude already knows (AIS, curl, JMESPath, HTTP errors). The one borderline section ("Content safety") earns its tokens for an external-data API. Matches the 5-anchor — every section carries non-obvious information.

5 / 5

Actionability

Fully executable: exact endpoint URL, exact auth header with a realistic key format, a copy-paste-ready worked example (curl --get with --data-urlencode piped to jq), and concrete error responses with an action (429 → back off). Matches the 5-anchor's "copy-paste ready… covers the common cases".

5 / 5

Workflow Clarity

A simple single-task skill (one GET request) whose single action is unambiguous — the rubric's simple-skill exception applies. It also includes the feedback/failure handling the anchors reward: the degradation contract ("no data, never 'no ships'") and per-error guidance. Not a destructive or batch operation, so no validation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist; the ~74-line single-purpose body is well-sectioned (Auth → Endpoint → Parameters → Response → Example → Errors → When NOT to use → References) with external references (OpenAPI, auth matrix) clearly signaled one level deep. Nothing inlined that clearly belongs in a separate file.

5 / 5

Total

20

/

20

Passed

Description

92%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 well-crafted description: it states exactly what the skill returns (and with which overlays/filters) and gives explicit, natural-language triggers users would actually say. Only gap is that a few natural synonyms present in the body (shipping activity, vessel positions, dark fleet) did not make it into the description itself.

DimensionReasoningScore

Specificity

"Retrieve a point-in-time AIS vessel-traffic snapshot with disruption candidates and optional tanker overlay, filterable by bounding box" names multiple concrete, parameter-level capabilities with comprehensive coverage of this skill's scope. Anchor 4 ("minor gaps in coverage") would understate it — every capability of the endpoint is named.

5 / 5

Completeness

Explicit "what" in the first sentence plus an explicit "Use when the user asks…" clause with concrete trigger phrases — a direct match for the score-5 exemplar. Not 4, because the "when" is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

"what ships are in an area", "whether maritime traffic is disrupted", plus AIS, vessel, tanker, and bounding box give good natural-term coverage. Falls short of the 5-anchor's synonym/extension exhaustiveness — "shipping activity", "vessel positions", "dark fleet", and "tanker movements" appear only in the body, not the description.

4 / 5

Distinctiveness Conflict Risk

Clear niche (live AIS maritime snapshot) with domain-specific triggers and third-person voice; minimal overlap risk — the sibling chokepoint-aggregate use case is explicitly routed away in the body's "When NOT to use" section.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
koala73/worldmonitor
Reviewed

Table of Contents

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.