Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create or optimize a shipping or delivery information page. Also use when the user mentions "shipping," "delivery," "shipping policy," "delivery times," "shipping page," "free shipping," "shipping rates," "delivery options," or "shipping info." For legal overview, use legal-page-generator.
.claude/skills/sediman-agent-shipping-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-13 | ✓→✓ | ＝ Same ✓ | -24% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
| case-12 | ✓→✓ | ＝ Same ✓ | -13% | 0% |
Guides shipping and delivery information page content for e-commerce.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Identify:
| Element | Purpose | |---------|---------| | Regions | Where you ship; restrictions | | Options | Standard, express; costs | | Timelines | Processing; delivery estimates | | Cutoffs | Order-by for same-day, etc. | | Tracking | How to track orders | | Issues | Lost, damaged; contact |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 15,111 | 9,391 | -38% | 1 | 1 | 0% | 2,582 | 1,972 | -24% | 0 | 0 | — |
case-07 | pass→pass | 14,106 | 12,038 | -15% | 1 | 1 | 0% | 2,199 | 2,227 | +1% | 0 | 0 | — |
case-12 | pass→pass | 11,670 | 7,979 | -32% | 1 | 1 | 0% | 1,880 | 1,642 | -13% | 0 | 0 | — |
case-01 | fail→fail | 15,029 | 10,630 | -29% | 1 | 1 | 0% | 2,440 | 2,255 | -8% | 0 | 0 | — |
case-02 | pass→pass | 13,671 | 10,159 | -26% | 1 | 1 | 0% | 2,136 | 2,025 | -5% | 0 | 0 | — |
case-03 | pass→pass | 13,396 | 12,481 | -7% | 1 | 1 | 0% | 2,099 | 2,335 | +11% | 0 | 0 | — |
case-04 | pass→pass | 10,792 | 9,232 | -14% | 1 | 1 | 0% | 1,789 | 1,812 | +1% | 0 | 0 | — |
case-05 | pass→pass | 11,509 | 8,573 | -26% | 1 | 1 | 0% | 1,885 | 1,794 | -5% | 0 | 0 | — |
case-06 | pass→pass | 11,502 | 9,203 | -20% | 1 | 1 | 0% | 1,817 | 1,875 | +3% | 0 | 0 | — |
case-08 | fail→pass | 15,195 | 12,300 | -19% | 1 | 1 | 0% | 2,608 | 2,329 | -11% | 0 | 0 | — |
case-09 | pass→pass | 11,158 | 10,484 | -6% | 1 | 1 | 0% | 1,863 | 2,077 | +11% | 0 | 0 | — |
case-10 | fail→fail | 12,580 | 10,760 | -14% | 1 | 1 | 0% | 1,942 | 2,038 | +5% | 0 | 0 | — |
case-11 | pass→pass | 12,017 | 9,217 | -23% | 1 | 1 | 0% | 1,776 | 1,700 | -4% | 0 | 0 | — |
case-14 | fail→fail | 7,603 | 7,255 | -5% | 1 | 1 | 0% | 1,141 | 1,428 | +25% | 0 | 0 | — |
case-15 | fail→pass | 15,331 | 11,593 | -24% | 1 | 1 | 0% | 2,523 | 2,208 | -12% | 0 | 0 | — |
case-16 | pass→pass | 8,902 | 9,469 | +6% | 1 | 1 | 0% | 1,418 | 1,926 | +36% | 0 | 0 | — |
case-17 | pass→pass | 8,966 | 5,588 | -38% | 1 | 1 | 0% | 1,366 | 1,165 | -15% | 0 | 0 | — |
case-18 | pass→pass | 6,679 | 4,139 | -38% | 1 | 1 | 0% | 1,001 | 1,019 | +2% | 0 | 0 | — |
case-19 | pass→pass | 9,009 | 7,847 | -13% | 1 | 1 | 0% | 1,518 | 1,616 | +6% | 0 | 0 | — |
case-20 | pass→pass | 14,258 | 11,672 | -18% | 1 | 1 | 0% | 2,438 | 2,346 | -4% | 0 | 0 | — |
case-21 | pass→pass | 16,421 | 14,710 | -10% | 1 | 1 | 0% | 3,050 | 3,068 | +1% | 0 | 0 | — |
case-22 | pass→pass | 24,285 | 14,224 | -41% | 1 | 1 | 0% | 4,112 | 2,865 | -30% | 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 +9 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.