Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetches live Waze traffic incidents and jams for a location. Use for real-ti metraffic or user says waze report, live traffic, road incidents. Use when t heuser needs this capability. Triggers: waze report, live traffic, road inci dents, traffic jams.
.claude/skills/stijnman-waze-live-reports/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 148% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 111% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 126% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 46% | 0% |
waze-navigatortraffic-flight-controllertelegram-traffic-reports| Failure | Response | |---------|----------| | Location not found | Ask user to clarify or share map link. |
Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,757 | 8,712 | +132% | 1 | 1 | 0% | 536 | 1,330 | +148% | 0 | 0 | — |
case-02 | fail→pass | 9,292 | 10,572 | +14% | 1 | 1 | 0% | 760 | 1,601 | +111% | 0 | 0 | — |
case-03 | pass→pass | 16,186 | 15,663 | -3% | 1 | 1 | 0% | 2,537 | 1,891 | -25% | 0 | 0 | — |
case-04 | pass→pass | 6,049 | 2,669 | -56% | 1 | 1 | 0% | 929 | 673 | -28% | 0 | 0 | — |
case-16 | fail→pass | 4,772 | 8,953 | +88% | 1 | 1 | 0% | 705 | 1,592 | +126% | 0 | 0 | — |
case-05 | pass→pass | 6,903 | 4,115 | -40% | 1 | 1 | 0% | 881 | 955 | +8% | 0 | 0 | — |
case-06 | pass→pass | 9,173 | 6,820 | -26% | 1 | 1 | 0% | 1,536 | 1,413 | -8% | 0 | 0 | — |
case-07 | fail→fail | 5,527 | 8,538 | +54% | 1 | 1 | 0% | 907 | 1,321 | +46% | 0 | 0 | — |
case-08 | fail→pass | 4,913 | 5,681 | +16% | 1 | 1 | 0% | 892 | 1,204 | +35% | 0 | 0 | — |
case-09 | fail→pass | 7,013 | 7,908 | +13% | 1 | 1 | 0% | 1,067 | 1,563 | +46% | 0 | 0 | — |
case-10 | fail→fail | 8,074 | 6,127 | -24% | 1 | 1 | 0% | 1,316 | 600 | -54% | 0 | 0 | — |
case-11 | pass→pass | 26,820 | 8,674 | -68% | 1 | 1 | 0% | 2,219 | 1,405 | -37% | 0 | 0 | — |
case-12 | fail→pass | 7,515 | 15,709 | +109% | 1 | 1 | 0% | 1,306 | 1,710 | +31% | 0 | 0 | — |
case-13 | fail→pass | 3,715 | 2,977 | -20% | 1 | 1 | 0% | 497 | 575 | +16% | 0 | 0 | — |
case-14 | fail→pass | 8,472 | 8,856 | +5% | 1 | 1 | 0% | 1,245 | 1,334 | +7% | 0 | 0 | — |
case-15 | fail→fail | 10,226 | 14,017 | +37% | 1 | 1 | 0% | 1,315 | 1,751 | +33% | 0 | 0 | — |
case-17 | pass→pass | 5,777 | 2,544 | -56% | 1 | 1 | 0% | 882 | 609 | -31% | 0 | 0 | — |
case-18 | fail→pass | 7,512 | 7,859 | +5% | 1 | 1 | 0% | 1,206 | 1,550 | +29% | 0 | 0 | — |
case-19 | pass→pass | 8,984 | 9,380 | +4% | 1 | 1 | 0% | 1,331 | 1,662 | +25% | 0 | 0 | — |
case-20 | fail→pass | 10,974 | 10,355 | -6% | 1 | 1 | 0% | 1,388 | 1,753 | +26% | 0 | 0 | — |
case-21 | pass→pass | 19,378 | 17,815 | -8% | 1 | 1 | 0% | 3,391 | 3,304 | -3% | 0 | 0 | — |
case-22 | fail→pass | 4,619 | 4,671 | +1% | 1 | 1 | 0% | 627 | 899 | +43% | 0 | 0 | — |
case-23 | pass→pass | 13,520 | 8,585 | -37% | 1 | 1 | 0% | 2,226 | 1,578 | -29% | 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, and 22 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 +48 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.