Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Select carriers and manage cross-border shipping operations for Taiwan — carrier choices (DHL / FedEx / UPS / 郵局 國際), customs clearance operations (報關), DDP vs DDU trade-offs, label generation, and returns handling. Use when choosing a carrier, estimating shipping cost or transit time, or managing the physical movement of cross-border goods. Do NOT use for duty/tax calculation, HS-code classification, or 境外電商 tax registration (see tw-ecom-compliance-cross-border). Do NOT use for domestic TW ship
.claude/skills/asgard-ai-platform-tw-ecom-logistics-cross-border/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 2% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 13% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 39% | 0% |
> STATUS: SKELETON — body pending.
tw-ecom-compliance-cross-bordertw-ecom-compliance-cross-bordertw-ecom-logistics-home / tw-ecom-logistics-cvsTODO: DDP vs DDU trade-offs (landed cost transparency, liability shift), carrier-choice framework (weight / speed / destination / DDP capability), customs document prep (商業發票、包裝明細、原產地證明), label standards per carrier, returns friction and cost structure. NOTE: HS-code classification, de minimis thresholds, and duty/VAT rates belong in tw-ecom-compliance-cross-border — do not duplicate here.
TODO: carrier by destination / weight / speed / DDP preference.
TODO: customs doc prep, label generation, tracking reconciliation.
TODO: 5-6 pitfalls (HS misclassification, DDP total cost shock, returns black hole, restricted-items list, FTZ vs general customs).
TODO.
TODO.
tw-ecom-compliance-cross-borderxborder-logistics, xborder-sea-entry_Last verified: 2026-04_
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 42,292 | 40,766 | -4% | 1 | 1 | 0% | 1,651 | 1,832 | +11% | 0 | 0 | — |
case-02 | pass→pass | 18,839 | 41,909 | +122% | 1 | 1 | 0% | 2,292 | 2,331 | +2% | 0 | 0 | — |
case-03 | pass→pass | 46,580 | 46,744 | +0% | 1 | 1 | 0% | 2,706 | 3,046 | +13% | 0 | 0 | — |
case-04 | pass→pass | 19,179 | 57,523 | +200% | 1 | 1 | 0% | 2,889 | 4,019 | +39% | 0 | 0 | — |
case-05 | fail→pass | 17,970 | 21,494 | +20% | 1 | 1 | 0% | 2,590 | 3,582 | +38% | 0 | 0 | — |
case-06 | pass→pass | 16,974 | 24,154 | +42% | 1 | 1 | 0% | 2,865 | 3,643 | +27% | 0 | 0 | — |
case-07 | pass→pass | 14,678 | 9,570 | -35% | 1 | 1 | 0% | 1,903 | 2,419 | +27% | 0 | 0 | — |
case-08 | pass→pass | 15,583 | 49,715 | +219% | 1 | 1 | 0% | 2,623 | 3,336 | +27% | 0 | 0 | — |
case-09 | pass→pass | 19,761 | 15,571 | -21% | 1 | 1 | 0% | 2,578 | 2,990 | +16% | 0 | 0 | — |
case-10 | pass→pass | 21,142 | 23,719 | +12% | 1 | 1 | 0% | 2,910 | 4,462 | +53% | 0 | 0 | — |
case-11 | pass→pass | 22,862 | 36,771 | +61% | 1 | 1 | 0% | 3,111 | 3,931 | +26% | 0 | 0 | — |
case-12 | pass→pass | 12,500 | 15,552 | +24% | 1 | 1 | 0% | 2,021 | 2,485 | +23% | 0 | 0 | — |
case-13 | pass→pass | 17,913 | 21,505 | +20% | 1 | 1 | 0% | 2,818 | 3,604 | +28% | 0 | 0 | — |
case-14 | pass→pass | 8,202 | 9,287 | +13% | 1 | 1 | 0% | 1,185 | 1,860 | +57% | 0 | 0 | — |
case-15 | pass→pass | 17,034 | 18,385 | +8% | 1 | 1 | 0% | 2,432 | 3,348 | +38% | 0 | 0 | — |
case-16 | pass→pass | 13,985 | 18,219 | +30% | 1 | 1 | 0% | 2,467 | 3,441 | +39% | 0 | 0 | — |
case-17 | pass→pass | 19,331 | 18,046 | -7% | 1 | 1 | 0% | 3,161 | 2,820 | -11% | 0 | 0 | — |
case-18 | pass→pass | 17,923 | 15,699 | -12% | 1 | 1 | 0% | 3,124 | 3,172 | +2% | 0 | 0 | — |
case-19 | pass→pass | 21,909 | 30,056 | +37% | 1 | 1 | 0% | 3,763 | 5,688 | +51% | 0 | 0 | — |
case-20 | pass→pass | 24,621 | 39,243 | +59% | 1 | 1 | 0% | 3,499 | 4,428 | +27% | 0 | 0 | — |
case-21 | pass→pass | 21,805 | 20,795 | -5% | 1 | 1 | 0% | 3,485 | 3,629 | +4% | 0 | 0 | — |
case-22 | pass→pass | 21,488 | 41,420 | +93% | 1 | 1 | 0% | 3,936 | 6,695 | +70% | 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. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 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.