Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Amazon FBA Calculator - Complete fee breakdown and profit analysis
.claude/skills/nexscope-ai-amazon-fba-calculator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | -19% | 0% |
Precise FBA fee calculation based on product dimensions and weight.
| Tier | Max Weight | Max Dimensions | |------|------------|----------------| | Small Standard | 1 lb | 15"×12"×0.75" | | Large Standard | 20 lb | 18"×14"×8" | | Small Oversize | 70 lb | 60"×30" | | Medium Oversize | 150 lb | L+Girth ≤108" | | Large Oversize | 150 lb | L+Girth ≤165" | | Special Oversize | >150 lb | >165" |
json{ "length": 10.0, "width": 6.0, "height": 3.0, "weight": 1.2, "selling_price": 29.99, "product_cost": 8.00, "inbound_shipping_cost": 1.50, "category": "kitchen" }
bashpython3 scripts/calculator.py python3 scripts/calculator.py '{"length": 10, "width": 6, ...}' --zh
_Version 1.0.0 | Platform: Amazon | Variant: Lite_
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 | pass→pass | 9,827 | 5,610 | -43% | 1 | 1 | 0% | 1,749 | 1,494 | -15% | 0 | 0 | — |
case-11 | pass→pass | 8,934 | 3,573 | -60% | 1 | 1 | 0% | 1,449 | 1,168 | -19% | 0 | 0 | — |
case-02 | pass→pass | 6,630 | 7,013 | +6% | 1 | 1 | 0% | 1,295 | 1,729 | +34% | 0 | 0 | — |
case-03 | pass→pass | 10,076 | 4,740 | -53% | 1 | 1 | 0% | 1,833 | 1,448 | -21% | 0 | 0 | — |
case-04 | pass→pass | 6,956 | 4,249 | -39% | 1 | 1 | 0% | 1,259 | 1,276 | +1% | 0 | 0 | — |
case-05 | fail→pass | 9,833 | 7,597 | -23% | 1 | 1 | 0% | 1,890 | 1,992 | +5% | 0 | 0 | — |
case-06 | pass→pass | 9,777 | 5,205 | -47% | 1 | 1 | 0% | 1,933 | 1,453 | -25% | 0 | 0 | — |
case-07 | pass→pass | 8,843 | 5,358 | -39% | 1 | 1 | 0% | 1,531 | 1,581 | +3% | 0 | 0 | — |
case-08 | pass→pass | 7,040 | 4,435 | -37% | 1 | 1 | 0% | 1,239 | 1,306 | +5% | 0 | 0 | — |
case-09 | pass→pass | 6,485 | 2,394 | -63% | 1 | 1 | 0% | 1,146 | 843 | -26% | 0 | 0 | — |
case-10 | fail→pass | 5,748 | 1,856 | -68% | 1 | 1 | 0% | 866 | 786 | -9% | 0 | 0 | — |
case-12 | fail→pass | 6,766 | 2,277 | -66% | 1 | 1 | 0% | 1,092 | 875 | -20% | 0 | 0 | — |
case-13 | pass→pass | 8,292 | 2,683 | -68% | 1 | 1 | 0% | 1,334 | 898 | -33% | 0 | 0 | — |
case-14 | pass→pass | 2,680 | 2,019 | -25% | 1 | 1 | 0% | 353 | 800 | +127% | 0 | 0 | — |
case-15 | pass→pass | 5,007 | 2,811 | -44% | 1 | 1 | 0% | 783 | 908 | +16% | 0 | 0 | — |
case-16 | pass→pass | 4,870 | 2,286 | -53% | 1 | 1 | 0% | 731 | 771 | +5% | 0 | 0 | — |
case-17 | pass→pass | 4,720 | 2,448 | -48% | 1 | 1 | 0% | 800 | 866 | +8% | 0 | 0 | — |
case-18 | pass→pass | 5,878 | 2,130 | -64% | 1 | 1 | 0% | 1,039 | 739 | -29% | 0 | 0 | — |
case-19 | pass→pass | 7,441 | 2,189 | -71% | 1 | 1 | 0% | 1,337 | 844 | -37% | 0 | 0 | — |
case-20 | pass→pass | 5,866 | 2,114 | -64% | 1 | 1 | 0% | 1,034 | 803 | -22% | 0 | 0 | — |
case-21 | fail→fail | 12,841 | 11,383 | -11% | 1 | 1 | 0% | 2,390 | 2,611 | +9% | 0 | 0 | — |
case-22 | fail→fail | 18,912 | 19,555 | +3% | 1 | 1 | 0% | 2,964 | 3,629 | +22% | 0 | 0 | — |
case-23 | fail→fail | 11,312 | 10,066 | -11% | 1 | 1 | 0% | 1,964 | 2,288 | +16% | 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. 23 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 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.