Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert skill in park assist focusing on parking domain applications. Covers 40 topics across parking domain. Includes 40 skill files covering ASPICE Level 3, AUTOSAR 4.4, ISO 21434, ISO 26262.
.claude/skills/pangzhenying2025-automotive-parking/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 124% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 205% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 163% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 167% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 123% | 0% |
40 skill files covering parking domain for automotive software engineering.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in park assist for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in parking sensors for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in remote parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking systems.
Expert in valet parking for automotive parking 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 | 27,358 | 26,918 | -2% | 1 | 1 | 0% | 6,189 | 10,541 | +70% | 0 | 0 | — |
case-02 | fail→fail | 27,325 | 24,788 | -9% | 1 | 1 | 0% | 6,182 | 10,534 | +70% | 0 | 0 | — |
case-03 | pass→pass | 21,622 | 21,927 | +1% | 1 | 1 | 0% | 4,135 | 9,224 | +123% | 0 | 0 | — |
case-04 | pass→pass | 19,120 | 23,002 | +20% | 1 | 1 | 0% | 4,053 | 9,629 | +138% | 0 | 0 | — |
case-05 | pass→pass | 18,357 | 23,424 | +28% | 1 | 1 | 0% | 3,684 | 9,644 | +162% | 0 | 0 | — |
case-06 | fail→fail | 22,668 | 25,798 | +14% | 1 | 1 | 0% | 4,046 | 10,530 | +160% | 0 | 0 | — |
case-07 | fail→fail | 8,242 | 8,346 | +1% | 1 | 1 | 0% | 1,874 | 6,082 | +225% | 0 | 0 | — |
case-08 | fail→pass | 17,312 | 18,605 | +7% | 1 | 1 | 0% | 3,910 | 8,777 | +124% | 0 | 0 | — |
case-09 | fail→fail | 26,671 | 27,173 | +2% | 1 | 1 | 0% | 6,180 | 10,532 | +70% | 0 | 0 | — |
case-10 | fail→pass | 14,145 | 20,969 | +48% | 1 | 1 | 0% | 2,739 | 8,363 | +205% | 0 | 0 | — |
case-11 | pass→pass | 16,671 | 18,477 | +11% | 1 | 1 | 0% | 2,688 | 7,971 | +197% | 0 | 0 | — |
case-12 | fail→fail | 22,412 | 27,129 | +21% | 1 | 1 | 0% | 3,370 | 9,367 | +178% | 0 | 0 | — |
case-13 | fail→fail | 25,938 | 28,857 | +11% | 1 | 1 | 0% | 5,403 | 10,519 | +95% | 0 | 0 | — |
case-14 | pass→pass | 18,116 | 27,680 | +53% | 1 | 1 | 0% | 3,104 | 10,026 | +223% | 0 | 0 | — |
case-15 | fail→fail | 23,464 | 22,750 | -3% | 1 | 1 | 0% | 3,728 | 8,434 | +126% | 0 | 0 | — |
case-16 | fail→pass | 19,958 | 27,867 | +40% | 1 | 1 | 0% | 3,870 | 10,187 | +163% | 0 | 0 | — |
case-17 | fail→pass | 16,864 | 21,789 | +29% | 1 | 1 | 0% | 3,366 | 8,983 | +167% | 0 | 0 | — |
case-18 | fail→fail | 20,821 | 28,138 | +35% | 1 | 1 | 0% | 4,489 | 10,511 | +134% | 0 | 0 | — |
case-19 | fail→fail | 14,376 | 21,589 | +50% | 1 | 1 | 0% | 2,753 | 8,640 | +214% | 0 | 0 | — |
case-20 | fail→fail | 16,329 | 30,236 | +85% | 1 | 1 | 0% | 2,906 | 10,521 | +262% | 0 | 0 | — |
case-21 | fail→fail | 30,672 | 28,793 | -6% | 1 | 1 | 0% | 6,023 | 10,509 | +74% | 0 | 0 | — |
case-22 | fail→fail | 23,204 | 30,103 | +30% | 1 | 1 | 0% | 4,434 | 10,511 | +137% | 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 +18 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.