CtrlK
BlogDocsLog inGet started
Tessl Logo

check-country-risk

Retrieve composite country risk intelligence — Country Instability Index (CII), travel advisory level, and active sanctions exposure — for one country by ISO code. Use when the user asks how risky or unstable a country is right now.

73

Quality

92%

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.

The body is a model single-endpoint API skill: lean, entirely non-redundant with Claude's prior knowledge, with a copy-paste curl example, precise parameter and error semantics, an anti-prompt-injection content-safety rule, and a 'When NOT to use' section that cleanly routes to sibling skills. Structure and disclosure are appropriate for its size with no bundle files to consult.

DimensionReasoningScore

Conciseness

Every section carries API-specific knowledge Claude cannot already know — the custom auth header and its disambiguation from Bearer tokens, the exact endpoint, the parameter constraints ('Lowercase is rejected', '≤ 1024 chars'), and the degraded-snapshot semantics of 'upstreamUnavailable: true'. Nothing explains general concepts, and there is no padding, matching the 'every token earns its place' anchor; even 'fetchedAt is Unix epoch milliseconds' earns its place by disambiguating units.

5 / 5

Actionability

The worked curl example is copy-paste executable ('curl -s --get -H "X-WorldMonitor-Key: $WM_API_KEY" ... --data-urlencode country_code=SD | jq ...'), the endpoint and auth are given verbatim, the parameter table specifies shapes and edge behavior, and the error section prescribes the 429 retry-with-backoff response. This meets the 'fully executable, copy-paste ready' anchor; the only nit — no worked example of the optional jmespath projection — does not undermine the common case, so anchor 4's 'minor gaps' framing is too weak.

5 / 5

Workflow Clarity

This is a simple single-task skill (one authenticated GET), and the action is unambiguous: obtain key → call with uppercase ISO code → interpret fields, with error recovery guidance (400/401/429 with backoff) and a validation-style checkpoint in the 'upstreamUnavailable: true means treat as no data, not no risk' rule. Per the simple-skill exception the single action can score 5; no destructive or batch operation is involved, so no cap applies.

5 / 5

Progressive Disclosure

The body is compact, sectioned, and self-contained for a single-endpoint skill — no bundle files exist, and nothing here warrants them. The 'References' section signals one-level-deep external pointers (live CII rankings, the OpenAPI operation 'GetCountryRisk', the auth matrix), and the abbreviated response shape with '"…": "…"' correctly defers full schema detail to the OpenAPI file. Navigation is easy, matching the anchor-5 'clear overview with well-signaled one-level-deep references' description.

5 / 5

Total

20

/

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: it names the three concrete output fields, the input format, and an explicit natural-language trigger, all in third-person imperative voice with no padding. Its only weaknesses are a single retrieve-style action, a few missing trigger synonyms, and mild overlap with a closely related resilience-score skill.

Suggestions

Add one or two natural trigger variants users would say, e.g. 'is it safe to travel to X' or 'is X under sanctions', to broaden keyword coverage.

Sharpen the contrast with the companion structural skill inside the description itself (e.g. 'for the current snapshot, not the long-horizon resilience score') to reduce overlap risk with fetch-resilience-score.

Consider naming one additional concrete action beyond 'Retrieve' (e.g. 'Retrieve and summarize') if the skill genuinely post-processes the response, to lift specificity coverage.

DimensionReasoningScore

Specificity

The description names the exact artifacts retrieved — 'Country Instability Index (CII) stress score, its travel advisory level, and whether sanctions are active' — plus the input constraint 'by ISO code', which is highly concrete. It falls just short of anchor 5 because the only action verb is 'Retrieve'; there are no secondary actions (e.g., compare, monitor, summarize), leaving minor coverage gaps.

4 / 5

Completeness

Both halves are explicit: what — 'Retrieve composite country risk intelligence — CII stress score, travel advisory level, and active sanctions exposure — for one country by ISO code' — and when — 'Use when the user asks how risky or unstable a country is right now' with a concrete trigger phrase. This mirrors the anchor-5 example's structure and is not merely implied, ruling out anchor 4.

5 / 5

Trigger Term Quality

'Use when the user asks how risky or unstable a country is right now' supplies natural phrasings ('how risky', 'unstable', 'right now') a user would actually say. A few common variants are missing — e.g. 'is it safe to travel there', 'travel advisory', 'is this country under sanctions' — so it matches anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The 'current risk / right now' framing carves a clear niche distinct from a narrative brief or an events feed. However, a sibling skill (fetch-resilience-score, per the body) also answers 'how risky is this country' from a structural angle, so there is minor overlap risk with a closely related skill — anchor 4 — rather than the minimal conflict risk of anchor 5.

4 / 5

Total

17

/

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.