Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert skill in aeb focusing on crash-avoidance domain applications. Covers 30 topics across crash-avoidance domain. Includes 30 skill files covering ASPICE Level 3, AUTOSAR 4.4, ISO 21434, ISO 26262.
.claude/skills/pangzhenying2025-automotive-crash-avoidance/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 120% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 202% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 112% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 85% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 140% | 0% |
30 skill files covering crash-avoidance domain for automotive software engineering.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in aeb for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in multi collision brake for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
Expert in pre crash for automotive crash-avoidance systems.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,709 | 25,045 | +1% | 1 | 1 | 0% | 6,182 | 9,614 | +56% | 0 | 0 | — |
case-02 | fail→fail | 25,824 | 26,440 | +2% | 1 | 1 | 0% | 6,195 | 9,627 | +55% | 0 | 0 | — |
case-03 | pass→pass | 20,632 | 25,643 | +24% | 1 | 1 | 0% | 5,169 | 9,575 | +85% | 0 | 0 | — |
case-04 | pass→pass | 17,834 | 25,946 | +45% | 1 | 1 | 0% | 4,001 | 9,622 | +140% | 0 | 0 | — |
case-05 | pass→pass | 19,583 | 25,639 | +31% | 1 | 1 | 0% | 4,500 | 9,634 | +114% | 0 | 0 | — |
case-06 | pass→pass | 15,035 | 19,381 | +29% | 1 | 1 | 0% | 3,496 | 8,037 | +130% | 0 | 0 | — |
case-07 | pass→pass | 12,392 | 13,152 | +6% | 1 | 1 | 0% | 2,523 | 6,164 | +144% | 0 | 0 | — |
case-08 | pass→pass | 15,235 | 25,866 | +70% | 1 | 1 | 0% | 3,068 | 8,907 | +190% | 0 | 0 | — |
case-09 | pass→pass | 16,751 | 18,496 | +10% | 1 | 1 | 0% | 3,015 | 6,856 | +127% | 0 | 0 | — |
case-10 | pass→pass | 20,232 | 29,629 | +46% | 1 | 1 | 0% | 4,163 | 9,382 | +125% | 0 | 0 | — |
case-11 | fail→pass | 18,957 | 23,043 | +22% | 1 | 1 | 0% | 3,694 | 8,134 | +120% | 0 | 0 | — |
case-12 | pass→fail | 23,930 | 29,377 | +23% | 1 | 1 | 0% | 4,527 | 9,617 | +112% | 0 | 0 | — |
case-13 | pass→pass | 18,666 | 26,083 | +40% | 1 | 1 | 0% | 4,033 | 9,622 | +139% | 0 | 0 | — |
case-14 | fail→pass | 12,910 | 16,220 | +26% | 1 | 1 | 0% | 2,275 | 6,873 | +202% | 0 | 0 | — |
case-15 | fail→fail | 15,564 | 28,287 | +82% | 1 | 1 | 0% | 2,793 | 8,903 | +219% | 0 | 0 | — |
case-16 | pass→pass | 14,100 | 16,235 | +15% | 1 | 1 | 0% | 2,769 | 6,639 | +140% | 0 | 0 | — |
case-17 | pass→pass | 17,425 | 12,796 | -27% | 1 | 1 | 0% | 3,718 | 6,124 | +65% | 0 | 0 | — |
case-18 | pass→pass | 14,307 | 18,551 | +30% | 1 | 1 | 0% | 2,242 | 6,571 | +193% | 0 | 0 | — |
case-19 | pass→pass | 14,974 | 21,120 | +41% | 1 | 1 | 0% | 2,590 | 7,298 | +182% | 0 | 0 | — |
case-20 | pass→pass | 24,380 | 23,568 | -3% | 1 | 1 | 0% | 5,695 | 8,426 | +48% | 0 | 0 | — |
case-21 | pass→pass | 14,747 | 19,902 | +35% | 1 | 1 | 0% | 3,536 | 7,944 | +125% | 0 | 0 | — |
case-22 | fail→fail | 66,656 | 74,495 | +12% | 1 | 1 | 0% | 787 | 4,367 | +455% | 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, and 21 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 0 percentage points is the difference between those two pass rates over the 21 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.