Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need Kafka messaging in Quarkus with SmallRye Reactive Messaging — including channel/topic design, build-time Jackson serialization, typed @Channel/@Incoming, ack/failure strategies, retries/DLQ, idempotency, Dev Services, and Testcontainers integration tests. This should trigger for requests such as Add Kafka in Quarkus; Review Reactive Messaging consumers; Improve failure handling for Quarkus Kafka; Configure Quarkus Reactive Messaging Kafka channels; Add Quarkus Kafka failure str
.claude/skills/jabrena-414-frameworks-quarkus-kafka/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | -10% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | -4% | 0% |
Apply Quarkus Kafka guidance with concrete examples for design, implementation, and error handling.
Compile before messaging refactors; verify after changes.
./mvnw compile or mvn compile before applying any change./mvnw clean verify or mvn clean verify after applying improvementsRead references/414-frameworks-quarkus-kafka.md and inspect current messaging setup before proposing changes.
Identify delivery semantics and resilience goals to define safe improvements.
Implement/refactor channels, serializers, and failure strategies in Reactive Messaging.
Execute build/tests and summarize what changed, what was verified, and follow-up actions.
For detailed guidance, examples, and constraints, see references/414-frameworks-quarkus-kafka.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→fail | 13,514 | 13,773 | +2% | 1 | 1 | 0% | 2,600 | 2,156 | -17% | 0 | 0 | — |
case-01 | fail→fail | 15,683 | 14,008 | -11% | 1 | 1 | 0% | 2,828 | 2,788 | -1% | 0 | 0 | — |
case-02 | fail→fail | 15,177 | 9,589 | -37% | 1 | 1 | 0% | 2,919 | 2,261 | -23% | 0 | 0 | — |
case-03 | fail→fail | 15,388 | 6,646 | -57% | 1 | 1 | 0% | 2,958 | 586 | -80% | 0 | 0 | — |
case-04 | fail→fail | 5,498 | 6,161 | +12% | 1 | 1 | 0% | 1,052 | 768 | -27% | 0 | 0 | — |
case-05 | fail→pass | 10,575 | 10,283 | -3% | 1 | 1 | 0% | 2,016 | 1,929 | -4% | 0 | 0 | — |
case-06 | fail→pass | 15,448 | 11,540 | -25% | 1 | 1 | 0% | 2,917 | 2,346 | -20% | 0 | 0 | — |
case-07 | fail→fail | 19,232 | 5,152 | -73% | 1 | 1 | 0% | 3,579 | 556 | -84% | 0 | 0 | — |
case-08 | fail→fail | 10,870 | 7,880 | -28% | 1 | 1 | 0% | 1,887 | 1,757 | -7% | 0 | 0 | — |
case-10 | fail→fail | 14,388 | 5,405 | -62% | 1 | 1 | 0% | 2,621 | 509 | -81% | 0 | 0 | — |
case-11 | fail→fail | 17,101 | 8,432 | -51% | 1 | 1 | 0% | 3,347 | 2,019 | -40% | 0 | 0 | — |
case-12 | fail→fail | 13,541 | 5,808 | -57% | 1 | 1 | 0% | 2,710 | 581 | -79% | 0 | 0 | — |
case-13 | fail→fail | 14,244 | 5,512 | -61% | 1 | 1 | 0% | 2,489 | 579 | -77% | 0 | 0 | — |
case-14 | fail→fail | 17,921 | 4,714 | -74% | 1 | 1 | 0% | 3,461 | 583 | -83% | 0 | 0 | — |
case-15 | fail→fail | 12,302 | 6,830 | -44% | 1 | 1 | 0% | 2,342 | 1,665 | -29% | 0 | 0 | — |
case-16 | fail→fail | 11,459 | 6,144 | -46% | 1 | 1 | 0% | 2,119 | 587 | -72% | 0 | 0 | — |
case-17 | fail→fail | 14,514 | 14,042 | -3% | 1 | 1 | 0% | 2,807 | 2,924 | +4% | 0 | 0 | — |
case-18 | fail→fail | 15,611 | 14,122 | -10% | 1 | 1 | 0% | 2,517 | 2,218 | -12% | 0 | 0 | — |
case-19 | fail→fail | 9,548 | 5,943 | -38% | 1 | 1 | 0% | 1,951 | 593 | -70% | 0 | 0 | — |
case-20 | pass→pass | 15,654 | 13,283 | -15% | 1 | 1 | 0% | 3,072 | 2,750 | -10% | 0 | 0 | — |
case-21 | pass→pass | 13,773 | 11,953 | -13% | 1 | 1 | 0% | 2,733 | 2,824 | +3% | 0 | 0 | — |
case-22 | pass→pass | 8,203 | 6,541 | -20% | 1 | 1 | 0% | 1,666 | 1,594 | -4% | 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 14 counted toward the lift figure. The other 8 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 +9 percentage points is the difference between those two pass rates over the 14 comparable cases. 7 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.