Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check the current status of the Strait of Hormuz — shipping transit data, oil price impact, stranded vessels, insurance risk levels, diplomatic developments, and global trade impact. Use this skill whenever the user asks about the Strait of Hormuz, Hormuz chokepoint, Persian Gulf shipping risk, oil transit disruption, war risk premium in the Gulf, Middle East shipping routes, tanker traffic through Hormuz, oil supply chain risk, or geopolitical risk affecting energy markets. Triggers include: "H
.claude/skills/himself65-hormuz-strait/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -3% | 0% |
Fetches real-time status of the Strait of Hormuz from the Hormuz Strait Monitor dashboard API. Covers shipping transits, oil prices, stranded vessels, insurance risk, diplomatic status, global trade impact, and crisis timeline.
This skill is read-only. It fetches public dashboard data — no authentication required.
Use curl to fetch the dashboard API:
bashcurl -s https://hormuzstraitmonitor.com/api/dashboard
Parse the JSON response. The API returns { "success": true, "data": { ... }, "timestamp": "..." }.
If success is false or the request fails, inform the user the monitor is temporarily unavailable and suggest checking https://hormuzstraitmonitor.com directly.
Match the user's request to the relevant data sections. If the user asks for a general status update, present all sections. If they ask about something specific, focus on the relevant section(s).
| User Request | Data Section | Key Fields | |---|---|---| | General status / "is Hormuz open?" | straitStatus | status, since, description | | Ship traffic / transit count | shipCount | currentTransits, last24h, normalDaily, percentOfNormal | | Oil price impact | oilPrice | brentPrice, change24h, changePercent24h, sparkline | | Stranded / stuck vessels | strandedVessels | total, tankers, bulk, other, changeToday | | Insurance / war risk | insurance | level, warRiskPercent, normalPercent, multiplier | | Cargo throughput | throughput | todayDWT, averageDWT, percentOfNormal, last7Days | | Diplomatic situation | diplomacy | status, headline, parties, summary | | Global trade impact | globalTradeImpact | percentOfWorldOilAtRisk, estimatedDailyCostBillions, affectedRegions, lngImpact, alternativeRoutes, supplyChainImpact | | Crisis timeline / events | crisisTimeline | events[] with date, type, title, description | | Tanker freight rates / VLCC rates | tankerRates | currentRate, preCrisisRate, changePercent, route, vesselType, trend, unit | | Latest news | news | title, source, url, publishedAt, description |
Format the results clearly for financial research. Adapt the presentation based on what the user asked for.
When the user asks for a general update, present a concise briefing covering all key sections:
percentOfNormal is below 80% or above 120%, call it outoilPrice.sparkline, describe the trend (rising, falling, stable) rather than listing raw numbersthroughput.last7Days, describe the trend directionlastUpdated timestamp so the user knows data freshnessBased on the data, provide a brief risk assessment:
Values are returned uppercase.
| Insurance Level | Interpretation | |---|---| | NORMAL | No elevated risk — shipping operating normally | | ELEVATED | Some disruption concerns — monitor closely | | HIGH | Significant risk — active disruption or credible threat | | CRITICAL | Severe disruption — major impact on global oil supply | | EXTREME | Effective closure — war risk premiums at multi-decade highs, most commercial traffic halted |
If the strait status is anything other than fully open, highlight:
lastUpdated timestamp)references/api_schema.md — Complete API response schema with field descriptions and data typesRead the reference file when you need exact field names or data type details.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,510 | 3,322 | -71% | 1 | 1 | 0% | 1,894 | 1,490 | -21% | 0 | 0 | — |
case-02 | fail→fail | 19,781 | 3,620 | -82% | 1 | 1 | 0% | 3,552 | 1,521 | -57% | 0 | 0 | — |
case-03 | fail→fail | 14,498 | 3,453 | -76% | 1 | 1 | 0% | 1,943 | 1,515 | -22% | 0 | 0 | — |
case-04 | fail→pass | 9,586 | 2,280 | -76% | 1 | 1 | 0% | 1,795 | 1,733 | -3% | 0 | 0 | — |
case-05 | fail→pass | 8,811 | 3,188 | -64% | 1 | 1 | 0% | 1,482 | 1,884 | +27% | 0 | 0 | — |
case-06 | pass→pass | 9,353 | 3,430 | -63% | 1 | 1 | 0% | 1,692 | 2,001 | +18% | 0 | 0 | — |
case-07 | pass→pass | 11,120 | 1,530 | -86% | 1 | 1 | 0% | 1,963 | 1,572 | -20% | 0 | 0 | — |
case-08 | pass→pass | 7,170 | 1,736 | -76% | 1 | 1 | 0% | 1,352 | 1,681 | +24% | 0 | 0 | — |
case-09 | fail→pass | 8,901 | 1,864 | -79% | 1 | 1 | 0% | 1,504 | 1,671 | +11% | 0 | 0 | — |
case-10 | pass→pass | 7,292 | 2,254 | -69% | 1 | 1 | 0% | 1,241 | 1,820 | +47% | 0 | 0 | — |
case-11 | pass→fail | 7,644 | 1,406 | -82% | 1 | 1 | 0% | 1,296 | 1,576 | +22% | 0 | 0 | — |
case-12 | fail→pass | 12,395 | 4,060 | -67% | 1 | 1 | 0% | 2,128 | 2,056 | -3% | 0 | 0 | — |
case-13 | fail→pass | 10,945 | 2,175 | -80% | 1 | 1 | 0% | 1,787 | 1,728 | -3% | 0 | 0 | — |
case-14 | fail→pass | 4,728 | 1,365 | -71% | 1 | 1 | 0% | 676 | 1,580 | +134% | 0 | 0 | — |
case-15 | fail→pass | 11,223 | 3,075 | -73% | 1 | 1 | 0% | 2,212 | 2,040 | -8% | 0 | 0 | — |
case-16 | pass→pass | 10,515 | 5,418 | -48% | 1 | 1 | 0% | 1,922 | 2,299 | +20% | 0 | 0 | — |
case-17 | fail→fail | 5,068 | 3,700 | -27% | 1 | 1 | 0% | 893 | 1,469 | +65% | 0 | 0 | — |
case-18 | pass→pass | 4,709 | 2,356 | -50% | 1 | 1 | 0% | 808 | 1,712 | +112% | 0 | 0 | — |
case-19 | pass→pass | 9,865 | 2,568 | -74% | 1 | 1 | 0% | 2,052 | 1,726 | -16% | 0 | 0 | — |
case-20 | fail→fail | 6,066 | 5,985 | -1% | 1 | 1 | 0% | 1,239 | 1,779 | +44% | 0 | 0 | — |
case-21 | fail→pass | 7,174 | 2,215 | -69% | 1 | 1 | 0% | 1,354 | 1,702 | +26% | 0 | 0 | — |
case-22 | fail→fail | 8,874 | 5,321 | -40% | 1 | 1 | 0% | 1,541 | 1,676 | +9% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +32 percentage points is the difference between those two pass rates over the 16 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.