Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create or redesign appointment-based service websites for salons, barbers, spas, wellness studios, clinics, and hospitality brands. Use for warm editorial layouts, serif-led identity, documentary portrait crops, calm treatment selectors, location-aware booking, and operational states that remain elegant and trustworthy.
.claude/skills/mengto-editorial-service-booking/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 214% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 203% | 0% |
Make browsing services feel like turning through a quiet lookbook, then carry that confidence into a resilient booking flow.
Use original or licensed people and place photography. Replace every source service, price, person, location, review, and claim.
tablist, tab, and tabpanel behavior when tabs are appropriate.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 28,817 | 28,882 | +0% | 1 | 1 | 0% | 6,221 | 7,077 | +14% | 0 | 0 | — |
case-02 | fail→fail | 28,740 | 28,698 | -0% | 1 | 1 | 0% | 6,208 | 7,065 | +14% | 0 | 0 | — |
case-03 | fail→fail | 26,436 | 28,487 | +8% | 1 | 1 | 0% | 6,205 | 7,062 | +14% | 0 | 0 | — |
case-04 | fail→pass | 12,892 | 28,460 | +121% | 1 | 1 | 0% | 2,248 | 7,056 | +214% | 0 | 0 | — |
case-05 | fail→pass | 10,015 | 5,039 | -50% | 1 | 1 | 0% | 1,854 | 1,861 | +0% | 0 | 0 | — |
case-06 | fail→pass | 11,443 | 9,335 | -18% | 1 | 1 | 0% | 1,923 | 2,765 | +44% | 0 | 0 | — |
case-07 | fail→pass | 12,059 | 15,912 | +32% | 1 | 1 | 0% | 2,396 | 4,090 | +71% | 0 | 0 | — |
case-08 | pass→pass | 13,667 | 15,156 | +11% | 1 | 1 | 0% | 2,339 | 3,841 | +64% | 0 | 0 | — |
case-09 | pass→pass | 13,731 | 14,554 | +6% | 1 | 1 | 0% | 2,550 | 3,607 | +41% | 0 | 0 | — |
case-10 | fail→pass | 13,785 | 26,308 | +91% | 1 | 1 | 0% | 2,330 | 7,050 | +203% | 0 | 0 | — |
case-11 | fail→fail | 11,776 | 27,365 | +132% | 1 | 1 | 0% | 1,925 | 7,031 | +265% | 0 | 0 | — |
case-12 | pass→pass | 11,939 | 9,322 | -22% | 1 | 1 | 0% | 2,308 | 2,681 | +16% | 0 | 0 | — |
case-13 | fail→pass | 9,542 | 16,893 | +77% | 1 | 1 | 0% | 1,626 | 4,421 | +172% | 0 | 0 | — |
case-14 | pass→pass | 11,197 | 5,892 | -47% | 1 | 1 | 0% | 1,888 | 1,929 | +2% | 0 | 0 | — |
case-15 | fail→pass | 11,332 | 8,031 | -29% | 1 | 1 | 0% | 1,859 | 2,085 | +12% | 0 | 0 | — |
case-16 | fail→pass | 17,352 | 14,656 | -16% | 1 | 1 | 0% | 2,812 | 3,802 | +35% | 0 | 0 | — |
case-17 | pass→pass | 11,629 | 8,394 | -28% | 1 | 1 | 0% | 1,870 | 2,145 | +15% | 0 | 0 | — |
case-18 | pass→pass | 8,516 | 5,487 | -36% | 1 | 1 | 0% | 1,505 | 1,794 | +19% | 0 | 0 | — |
case-19 | pass→pass | 15,000 | 14,250 | -5% | 1 | 1 | 0% | 3,763 | 4,062 | +8% | 0 | 0 | — |
case-20 | pass→pass | 15,185 | 26,566 | +75% | 1 | 1 | 0% | 3,265 | 7,027 | +115% | 0 | 0 | — |
case-21 | pass→fail | 18,668 | 26,830 | +44% | 1 | 1 | 0% | 4,296 | 7,027 | +64% | 0 | 0 | — |
case-22 | pass→pass | 10,554 | 8,313 | -21% | 1 | 1 | 0% | 1,998 | 2,401 | +20% | 0 | 0 | — |
case-23 | pass→pass | 10,467 | 28,957 | +177% | 1 | 1 | 0% | 1,876 | 7,023 | +274% | 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 +30 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.