Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need MongoDB persistence in Quarkus — including Panache Mongo entities/repositories, document design, indexes, transactions where applicable, and error handling. This should trigger for requests such as Add MongoDB in Quarkus; Review Quarkus Mongo Panache design; Improve Mongo error handling in Quarkus services; Model MongoDB documents for a Quarkus service; Configure Quarkus MongoDB clients codecs or transactions. Part of Plinth Toolkit
.claude/skills/jabrena-415-frameworks-quarkus-mongodb/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 23% | 0% |
Apply Quarkus MongoDB guidance with concrete examples for design, implementation, and error handling.
Compile before MongoDB refactors; verify after changes.
./mvnw compile or mvn compile before applying any change./mvnw clean verify or mvn clean verify after applying improvementsRead references/415-frameworks-quarkus-mongodb.md and inspect persistence setup before proposing changes.
Identify model/query consistency needs and define safe improvements.
Implement/refactor Panache Mongo mappings, repository access, and failure handling.
Execute build/tests and summarize what changed, what was verified, and follow-up actions.
For detailed guidance, examples, and constraints, see references/415-frameworks-quarkus-mongodb.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | 14,481 | 7,883 | -46% | 1 | 1 | 0% | 2,525 | 1,760 | -30% | 0 | 0 | — |
case-01 | fail→fail | 4,038 | 5,476 | +36% | 1 | 1 | 0% | 152 | 592 | +289% | 0 | 0 | — |
case-13 | fail→fail | 22,129 | 5,783 | -74% | 1 | 1 | 0% | 4,107 | 555 | -86% | 0 | 0 | — |
case-02 | fail→fail | 19,029 | 4,837 | -75% | 1 | 1 | 0% | 3,536 | 584 | -83% | 0 | 0 | — |
case-03 | fail→fail | 5,272 | 5,623 | +7% | 1 | 1 | 0% | 238 | 579 | +143% | 0 | 0 | — |
case-04 | fail→fail | 2,371 | 2,907 | +23% | 1 | 1 | 0% | 192 | 652 | +240% | 0 | 0 | — |
case-05 | fail→fail | 3,656 | 5,546 | +52% | 1 | 1 | 0% | 207 | 594 | +187% | 0 | 0 | — |
case-06 | fail→pass | 17,195 | 6,959 | -60% | 1 | 1 | 0% | 3,155 | 1,689 | -46% | 0 | 0 | — |
case-08 | fail→fail | 12,068 | 5,719 | -53% | 1 | 1 | 0% | 2,094 | 643 | -69% | 0 | 0 | — |
case-09 | fail→fail | 13,213 | 2,815 | -79% | 1 | 1 | 0% | 2,499 | 654 | -74% | 0 | 0 | — |
case-10 | fail→fail | 36,400 | 5,654 | -84% | 1 | 1 | 0% | 6,260 | 660 | -89% | 0 | 0 | — |
case-11 | fail→fail | 21,216 | 5,939 | -72% | 1 | 1 | 0% | 3,592 | 600 | -83% | 0 | 0 | — |
case-12 | fail→fail | 18,264 | 10,437 | -43% | 1 | 1 | 0% | 3,521 | 2,096 | -40% | 0 | 0 | — |
case-14 | fail→fail | 16,319 | 5,747 | -65% | 1 | 1 | 0% | 2,777 | 638 | -77% | 0 | 0 | — |
case-15 | fail→fail | 19,137 | 5,263 | -72% | 1 | 1 | 0% | 3,647 | 602 | -83% | 0 | 0 | — |
case-16 | fail→fail | 15,928 | 8,757 | -45% | 1 | 1 | 0% | 2,834 | 1,928 | -32% | 0 | 0 | — |
case-17 | fail→pass | 13,582 | 11,818 | -13% | 1 | 1 | 0% | 2,446 | 2,860 | +17% | 0 | 0 | — |
case-18 | fail→fail | 10,120 | 5,842 | -42% | 1 | 1 | 0% | 1,706 | 1,205 | -29% | 0 | 0 | — |
case-19 | fail→pass | 16,659 | 8,772 | -47% | 1 | 1 | 0% | 3,168 | 1,922 | -39% | 0 | 0 | — |
case-20 | pass→pass | 10,693 | 12,362 | +16% | 1 | 1 | 0% | 2,254 | 2,772 | +23% | 0 | 0 | — |
case-21 | pass→pass | 12,887 | 13,585 | +5% | 1 | 1 | 0% | 2,592 | 2,858 | +10% | 0 | 0 | — |
case-22 | pass→pass | 15,525 | 10,684 | -31% | 1 | 1 | 0% | 2,904 | 2,305 | -21% | 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 13 counted toward the lift figure. The other 9 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 +18 percentage points is the difference between those two pass rates over the 13 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.