Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need to design, review, or improve validation in Quarkus applications — including Bean Validation on JAX-RS resources, @Valid on parameters and CDI beans, constraint groups, @ConfigMapping validation, custom constraints, nested DTO validation, and ExceptionMapper-based error mapping. This should trigger for requests such as Add validation support in Quarkus; Review Quarkus validation rules; Improve request validation in Quarkus REST APIs; Add custom validation constraints in Quarkus
.claude/skills/jabrena-403-frameworks-quarkus-validation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-22 | ✓→✗ | ▼ Worse | -2% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -5% | 0% |
Apply Quarkus validation best practices at REST boundaries.
What is covered in this Skill?
Scope: Apply recommendations based on the reference rules and good/bad examples.
Before applying validation changes, ensure the project compiles. After improvements, run full verification.
./mvnw compile or mvn compile before applying any change./mvnw clean verify or mvn clean verify after applying improvementsRead references/403-frameworks-quarkus-validation.md and inspect the current project setup before proposing changes.
Identify requested outcomes, constraints, and the minimum safe set of changes to apply.
Implement or refactor validation-related configuration/code following the reference patterns and project conventions.
Execute appropriate build/tests and summarize what changed, what was verified, and any follow-up actions.
For detailed guidance, examples, and constraints, see references/403-frameworks-quarkus-validation.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 8,853 | 6,548 | -26% | 1 | 1 | 0% | 1,565 | 1,583 | +1% | 0 | 0 | — |
case-01 | fail→pass | 4,742 | 2,090 | -56% | 1 | 1 | 0% | 769 | 754 | -2% | 0 | 0 | — |
case-02 | pass→pass | 4,789 | 2,828 | -41% | 1 | 1 | 0% | 716 | 843 | +18% | 0 | 0 | — |
case-03 | pass→pass | 7,444 | 6,765 | -9% | 1 | 1 | 0% | 1,681 | 1,603 | -5% | 0 | 0 | — |
case-04 | pass→pass | 4,473 | 3,179 | -29% | 1 | 1 | 0% | 707 | 957 | +35% | 0 | 0 | — |
case-05 | pass→pass | 3,353 | 2,870 | -14% | 1 | 1 | 0% | 660 | 923 | +40% | 0 | 0 | — |
case-06 | pass→pass | 6,791 | 5,305 | -22% | 1 | 1 | 0% | 1,267 | 1,327 | +5% | 0 | 0 | — |
case-07 | pass→pass | 10,504 | 4,300 | -59% | 1 | 1 | 0% | 1,756 | 1,307 | -26% | 0 | 0 | — |
case-08 | pass→pass | 16,382 | 9,959 | -39% | 1 | 1 | 0% | 2,946 | 2,559 | -13% | 0 | 0 | — |
case-09 | pass→pass | 7,788 | 6,987 | -10% | 1 | 1 | 0% | 1,497 | 1,668 | +11% | 0 | 0 | — |
case-10 | pass→pass | 7,352 | 5,777 | -21% | 1 | 1 | 0% | 1,173 | 1,461 | +25% | 0 | 0 | — |
case-11 | pass→pass | 13,023 | 7,210 | -45% | 1 | 1 | 0% | 2,554 | 1,776 | -30% | 0 | 0 | — |
case-12 | pass→pass | 9,242 | 4,506 | -51% | 1 | 1 | 0% | 1,488 | 1,087 | -27% | 0 | 0 | — |
case-13 | pass→pass | 7,432 | 6,329 | -15% | 1 | 1 | 0% | 1,271 | 1,443 | +14% | 0 | 0 | — |
case-14 | pass→pass | 4,837 | 3,120 | -35% | 1 | 1 | 0% | 697 | 893 | +28% | 0 | 0 | — |
case-15 | pass→pass | 6,813 | 3,808 | -44% | 1 | 1 | 0% | 1,312 | 1,157 | -12% | 0 | 0 | — |
case-16 | pass→pass | 9,408 | 10,015 | +6% | 1 | 1 | 0% | 2,058 | 2,279 | +11% | 0 | 0 | — |
case-17 | pass→pass | 10,679 | 5,739 | -46% | 1 | 1 | 0% | 1,957 | 1,384 | -29% | 0 | 0 | — |
case-18 | pass→pass | 2,828 | 2,959 | +5% | 1 | 1 | 0% | 467 | 927 | +99% | 0 | 0 | — |
case-19 | pass→pass | 3,754 | 2,146 | -43% | 1 | 1 | 0% | 504 | 694 | +38% | 0 | 0 | — |
case-21 | pass→pass | 7,738 | 13,780 | +78% | 1 | 1 | 0% | 1,448 | 1,692 | +17% | 0 | 0 | — |
case-22 | pass→fail | 18,995 | 14,993 | -21% | 1 | 1 | 0% | 3,646 | 3,558 | -2% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.