Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need to create a new Maven-based Quarkus 3.x project using SDKMAN-managed Java and Quarkus CLI tooling. This should trigger for requests such as Create a Quarkus Maven project; Bootstrap Quarkus project with SDKMAN; Generate a new Quarkus service; Create Quarkus 3 Maven project; Scaffold Quarkus service with Java 25. Part of Plinth Toolkit
.claude/skills/jabrena-400-frameworks-quarkus-create-project/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✓→✗ | ▼ Worse | -18% | 0% |
Create a new Quarkus Maven project through SDKMAN-managed tooling, aligned with Java 25 and the repository's Quarkus 3.x baseline.
What is covered in this Skill?
Project creation must be explicit, reproducible, and Maven-based.
sdk version; if missing, stop and provide setup guidance instead of installing it silently./mvnw clean verify from the generated project when the Maven wrapper exists; otherwise run mvn clean verifyRead references/400-frameworks-quarkus-create-project.md, then gather project directory, group, artifact, package name, Java version, and desired Quarkus extensions.
Check SDKMAN, Java, and Quarkus CLI availability. Install or switch candidates only after confirming the intended versions with the user.
Use the Quarkus CLI to create a Maven project, keeping extensions explicit and the Quarkus 3.x baseline as the default.
Run Maven verification in the generated project and summarize commands used, selected options, generated path, and any follow-up setup.
For detailed guidance, examples, and constraints, see references/400-frameworks-quarkus-create-project.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | fail→fail | 12,743 | 15,275 | +20% | 1 | 1 | 0% | 2,137 | 3,522 | +65% | 0 | 0 | — |
case-02 | fail→fail | 4,062 | 5,444 | +34% | 1 | 1 | 0% | 511 | 909 | +78% | 0 | 0 | — |
case-01 | fail→fail | 4,386 | 5,618 | +28% | 1 | 1 | 0% | 617 | 870 | +41% | 0 | 0 | — |
case-03 | pass→fail | 7,284 | 6,381 | -12% | 1 | 1 | 0% | 1,138 | 932 | -18% | 0 | 0 | — |
case-04 | fail→fail | 4,620 | 5,507 | +19% | 1 | 1 | 0% | 672 | 791 | +18% | 0 | 0 | — |
case-05 | pass→fail | 6,268 | 5,878 | -6% | 1 | 1 | 0% | 942 | 895 | -5% | 0 | 0 | — |
case-06 | fail→fail | 12,715 | 6,339 | -50% | 1 | 1 | 0% | 1,909 | 964 | -50% | 0 | 0 | — |
case-11 | pass→pass | 3,705 | 2,826 | -24% | 1 | 1 | 0% | 528 | 943 | +79% | 0 | 0 | — |
case-07 | fail→pass | 8,837 | 18,147 | +105% | 1 | 1 | 0% | 1,434 | 3,059 | +113% | 0 | 0 | — |
case-08 | fail→pass | 4,886 | 3,555 | -27% | 1 | 1 | 0% | 740 | 1,079 | +46% | 0 | 0 | — |
case-09 | fail→pass | 7,369 | 3,893 | -47% | 1 | 1 | 0% | 1,153 | 1,176 | +2% | 0 | 0 | — |
case-10 | pass→fail | 6,960 | 5,883 | -15% | 1 | 1 | 0% | 1,223 | 799 | -35% | 0 | 0 | — |
case-12 | pass→fail | 3,121 | 4,861 | +56% | 1 | 1 | 0% | 473 | 736 | +56% | 0 | 0 | — |
case-13 | pass→pass | 9,614 | 4,912 | -49% | 1 | 1 | 0% | 1,539 | 1,364 | -11% | 0 | 0 | — |
case-14 | pass→pass | 13,084 | 3,016 | -77% | 1 | 1 | 0% | 1,866 | 1,022 | -45% | 0 | 0 | — |
case-15 | pass→pass | 3,183 | 2,020 | -37% | 1 | 1 | 0% | 426 | 829 | +95% | 0 | 0 | — |
case-16 | pass→pass | 9,426 | 3,865 | -59% | 1 | 1 | 0% | 1,578 | 1,158 | -27% | 0 | 0 | — |
case-17 | pass→fail | 4,486 | 4,401 | -2% | 1 | 1 | 0% | 653 | 1,211 | +85% | 0 | 0 | — |
case-18 | pass→pass | 11,910 | 3,918 | -67% | 1 | 1 | 0% | 1,720 | 1,093 | -36% | 0 | 0 | — |
case-19 | fail→fail | 15,776 | 5,681 | -64% | 1 | 1 | 0% | 3,419 | 725 | -79% | 0 | 0 | — |
case-20 | fail→pass | 9,465 | 9,906 | +5% | 1 | 1 | 0% | 1,834 | 2,159 | +18% | 0 | 0 | — |
case-22 | fail→fail | 15,493 | 6,236 | -60% | 1 | 1 | 0% | 2,350 | 784 | -67% | 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 12 counted toward the lift figure. The other 10 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 -5 percentage points is the difference between those two pass rates over the 12 comparable cases. 5 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.