Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Universal tariff calculator for Amazon sellers. Calculate import duties, landed costs, and VAT/GST for any trade route. Supports CN→US, CN→EU, US→EU, EU→US, US→CN and custom origin/destination pairs. Includes Section 301 tariffs, trade agreement rates (USMCA, EVFTA), and HS code lookup. No API key required.
.claude/skills/nexscope-ai-tariff-calculator-amazon/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 38% | 0% |
Universal tariff and landed cost calculator for international Amazon sellers.
bashnpx skills add nexscope-ai/eCommerce-Skills --skill tariff-calculator-amazon -g
| Route | Key Tariffs | VAT/GST | |-------|-------------|---------| | 🇨🇳 → 🇺🇸 China → USA | Section 301 (7.5-25%) | N/A | | 🇨🇳 → 🇪🇺 China → EU | Standard duties | 19-22% | | 🇨🇳 → 🇬🇧 China → UK | Standard duties | 20% | | 🇺🇸 → 🇪🇺 USA → EU | Standard duties | 19-22% | | 🇪🇺 → 🇺🇸 EU → USA | Standard duties | N/A | | 🇺🇸 → 🇨🇳 USA → China | Retaliatory tariffs | 13% VAT | | 🇨🇳 → 🇨🇦 China → Canada | Standard duties | 5% GST | | 🇨🇳 → 🇦🇺 China → Australia | Standard duties | 10% GST | | Custom | User-defined | User-defined |
| HS Chapter | Products | Additional Rate | |------------|----------|-----------------| | 84xx | Computers, machinery | 25% | | 85xx | Electronics (some) | 0-25% | | 94xx | Furniture, lighting | 25% | | 95xx | Toys | 25% | | 61/62 | Apparel | 7.5% | | 64xx | Footwear | 7.5% | | 42xx | Bags, accessories | 7.5% |
Landed Cost =
FOB Value
+ International Freight
+ Insurance
+ Import Duty
+ VAT/GST (if applicable)
+ Customs Clearance
+ Port Fees
+ Inland Freightbashpython3 scripts/calculator.py
bashpython3 scripts/calculator.py '{ "hs_code": "8518300000", "origin_country": "CN", "destination_country": "US", "fob_value": 5000.00, "quantity": 500, "freight_cost": 200.00 }'
bashpython3 scripts/hs_lookup.py "wireless earbuds" python3 scripts/hs_lookup.py "bluetooth speaker"
bashpython3 scripts/calculator.py '{ "hs_code": "9503009000", "origin_country": "VN", "destination_country": "DE", "fob_value": 10000.00, "quantity": 1000, "freight_cost": 500.00, "custom_duty_rate": 0.047, "custom_vat_rate": 0.19 }'
💰 Tariff & Landed Cost Report
Product: Wireless Bluetooth Earbuds
HS Code: 8518300000
Route: China 🇨🇳 → USA 🇺🇸
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📦 Cost Breakdown
FOB Value $ 5,000.00
International Freight $ 200.00
Insurance $ 15.00
CIF Value $ 5,215.00
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🏛️ Duties & Taxes
Base Duty (0.0%) $ 0.00
Section 301 (0.0%) $ 0.00
Total Duty $ 0.00
Customs Clearance $ 150.00
Port Fees $ 50.00
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💵 Landed Cost Summary
Total Landed Cost $ 5,515.00
Per Unit Cost $ 11.03| Agreement | Countries | Benefit | |-----------|-----------|---------| | USMCA | US, Mexico, Canada | Reduced/zero duties | | EVFTA | EU, Vietnam | Reduced duties | | RCEP | Asia-Pacific | Reduced duties | | UK-Japan | UK, Japan | Reduced duties |
Create a custom config for your routes:
json{ "default_origin": "CN", "default_destination": "US", "include_insurance": true, "insurance_rate": 0.003, "customs_fee": 150, "port_fee": 50 }
Part of Nexscope AI — AI tools for e-commerce sellers.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,923 | 11,776 | -21% | 1 | 1 | 0% | 2,810 | 3,588 | +28% | 0 | 0 | — |
case-02 | fail→fail | 18,446 | 13,731 | -26% | 1 | 1 | 0% | 3,237 | 3,764 | +16% | 0 | 0 | — |
case-03 | fail→fail | 15,305 | 9,904 | -35% | 1 | 1 | 0% | 2,707 | 3,196 | +18% | 0 | 0 | — |
case-04 | fail→fail | 10,679 | 9,360 | -12% | 1 | 1 | 0% | 1,871 | 3,026 | +62% | 0 | 0 | — |
case-05 | fail→fail | 10,840 | 12,111 | +12% | 1 | 1 | 0% | 2,135 | 3,685 | +73% | 0 | 0 | — |
case-06 | fail→fail | 8,478 | 36,336 | +329% | 1 | 1 | 0% | 1,625 | 2,534 | +56% | 0 | 0 | — |
case-07 | pass→pass | 10,398 | 7,429 | -29% | 1 | 1 | 0% | 1,975 | 2,723 | +38% | 0 | 0 | — |
case-16 | fail→pass | 11,870 | 4,453 | -62% | 1 | 1 | 0% | 2,400 | 2,284 | -5% | 0 | 0 | — |
case-08 | pass→pass | 14,566 | 11,792 | -19% | 1 | 1 | 0% | 2,710 | 3,433 | +27% | 0 | 0 | — |
case-09 | fail→fail | 20,018 | 12,662 | -37% | 1 | 1 | 0% | 1,349 | 3,544 | +163% | 0 | 0 | — |
case-10 | pass→pass | 4,930 | 7,749 | +57% | 1 | 1 | 0% | 763 | 2,633 | +245% | 0 | 0 | — |
case-11 | pass→pass | 7,804 | 6,184 | -21% | 1 | 1 | 0% | 1,216 | 2,364 | +94% | 0 | 0 | — |
case-12 | pass→pass | 7,444 | 6,908 | -7% | 1 | 1 | 0% | 1,261 | 2,507 | +99% | 0 | 0 | — |
case-13 | pass→pass | 12,609 | 6,092 | -52% | 1 | 1 | 0% | 2,087 | 2,364 | +13% | 0 | 0 | — |
case-14 | fail→pass | 18,075 | 3,244 | -82% | 1 | 1 | 0% | 1,567 | 1,789 | +14% | 0 | 0 | — |
case-15 | fail→pass | 6,806 | 1,413 | -79% | 1 | 1 | 0% | 958 | 1,475 | +54% | 0 | 0 | — |
case-17 | fail→pass | 8,502 | 3,512 | -59% | 1 | 1 | 0% | 1,510 | 1,941 | +29% | 0 | 0 | — |
case-18 | pass→pass | 3,269 | 3,153 | -4% | 1 | 1 | 0% | 399 | 1,770 | +344% | 0 | 0 | — |
case-19 | pass→pass | 12,271 | 6,362 | -48% | 1 | 1 | 0% | 1,940 | 2,367 | +22% | 0 | 0 | — |
case-20 | pass→pass | 7,629 | 3,755 | -51% | 1 | 1 | 0% | 1,334 | 1,894 | +42% | 0 | 0 | — |
case-21 | pass→pass | 2,881 | 2,930 | +2% | 1 | 1 | 0% | 407 | 1,773 | +336% | 0 | 0 | — |
case-22 | pass→pass | 9,686 | 4,021 | -58% | 1 | 1 | 0% | 1,598 | 2,045 | +28% | 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 21 counted toward the lift figure. The other 1 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 +18 percentage points is the difference between those two pass rates over the 21 comparable cases.
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.