Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides idiomatic Kotlin patterns including coroutine concurrency, Flow streams, multiplatform architecture, Compose UI, Ktor servers, and type-safe DSL design.
.claude/skills/paperclipai-kotlin-specialist/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 6 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-01 | ✓→✓ | = Same ✓ | -17% | 0% |
| case-02 | ✓→✓ | = Same ✓ | -6% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -8% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 27% | 0% |
name: kotlin-specialist description: > Provides idiomatic Kotlin patterns including coroutine concurrency, Flow streams, multiplatform architecture, Compose UI, Ktor servers, and type-safe DSL design. metadata: sources:
repo: jeffallan/claude-skills path: skills/kotlin-specialist/SKILL.md commit: 3bf9a24b76a7c122f1fc05e83929fbc84e1c207a attribution: Jeffallan license: MIT usage: referenced
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 11,196 | 8,701 | -22% | 1 | 1 | 0% | 2,120 | 1,766 | -17% | 0 | 0 | — |
case-02 | pass→pass | 9,297 | 6,831 | -27% | 1 | 1 | 0% | 1,461 | 1,374 | -6% | 0 | 0 | — |
case-03 | pass→pass | 10,537 | 9,256 | -12% | 1 | 1 | 0% | 2,112 | 1,944 | -8% | 0 | 0 | — |
case-04 | fail→fail | 13,023 | 12,947 | -1% | 1 | 1 | 0% | 2,428 | 2,687 | +11% | 0 | 0 | — |
case-05 | pass→pass | 9,418 | 11,171 | +19% | 1 | 1 | 0% | 2,081 | 2,651 | +27% | 0 | 0 | — |
case-20 | pass→pass | 7,332 | 6,019 | -18% | 1 | 1 | 0% | 1,531 | 1,449 | -5% | 0 | 0 | — |
case-06 | pass→pass | 8,577 | 8,257 | -4% | 1 | 1 | 0% | 1,513 | 1,833 | +21% | 0 | 0 | — |
case-07 | pass→pass | 14,203 | 13,550 | -5% | 1 | 1 | 0% | 2,822 | 2,756 | -2% | 0 | 0 | — |
case-08 | pass→pass | 7,828 | 8,379 | +7% | 1 | 1 | 0% | 1,571 | 1,530 | -3% | 0 | 0 | — |
case-09 | pass→pass | 12,786 | 8,811 | -31% | 1 | 1 | 0% | 2,143 | 1,851 | -14% | 0 | 0 | — |
case-10 | pass→pass | 8,099 | 7,503 | -7% | 1 | 1 | 0% | 1,417 | 1,493 | +5% | 0 | 0 | — |
case-11 | pass→pass | 10,524 | 8,578 | -18% | 1 | 1 | 0% | 1,576 | 1,746 | +11% | 0 | 0 | — |
case-12 | pass→pass | 8,495 | 6,242 | -27% | 1 | 1 | 0% | 1,681 | 1,296 | -23% | 0 | 0 | — |
case-13 | fail→pass | 11,220 | 7,702 | -31% | 1 | 1 | 0% | 2,172 | 1,647 | -24% | 0 | 0 | — |
case-14 | pass→pass | 8,901 | 5,079 | -43% | 1 | 1 | 0% | 1,310 | 1,163 | -11% | 0 | 0 | — |
case-21 | pass→pass | 11,672 | 12,856 | +10% | 1 | 1 | 0% | 2,632 | 2,641 | +0% | 0 | 0 | — |
case-15 | pass→pass | 10,602 | 7,626 | -28% | 1 | 1 | 0% | 2,063 | 1,469 | -29% | 0 | 0 | — |
case-16 | pass→pass | 8,486 | 8,130 | -4% | 1 | 1 | 0% | 1,538 | 1,602 | +4% | 0 | 0 | — |
case-17 | pass→pass | 9,366 | 9,057 | -3% | 1 | 1 | 0% | 1,726 | 1,644 | -5% | 0 | 0 | — |
case-18 | pass→pass | 10,983 | 10,753 | -2% | 1 | 1 | 0% | 2,429 | 2,590 | +7% | 0 | 0 | — |
case-19 | pass→pass | 9,608 | 10,447 | +9% | 1 | 1 | 0% | 1,731 | 1,830 | +6% | 0 | 0 | — |
case-22 | pass→pass | 13,238 | 8,120 | -39% | 1 | 1 | 0% | 2,376 | 1,894 | -20% | 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 +5 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.