Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need data access with Micronaut Data — @MappedEntity, CrudRepository/PageableRepository, @Query with parameters, @Transactional services, projections, @Version, and @MicronautTest with TestPropertyProvider and Testcontainers. For raw java.sql access without generated repositories, use @511-frameworks-micronaut-jdbc. This should trigger for requests such as Review or implement Micronaut Data repositories and entities; Add transactions, pagination, or projections in Micronaut persiste
.claude/skills/jabrena-512-frameworks-micronaut-data/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✓→✗ | ▼ Worse | -19% | 0% |
| case-19 | ✓→✗ | ▼ Worse | -65% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 71% | 0% |
Apply Micronaut Data patterns for relational repositories and safe SQL.
What is covered in this Skill?
Scope: Apply recommendations based on the reference rules and good/bad code examples.
Compile before persistence changes; verify the full build after.
./mvnw compile or mvn compile before applying any change./mvnw clean verify or mvn clean verify after applying improvementsRead references/512-frameworks-micronaut-data.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 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/512-frameworks-micronaut-data.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,215 | 5,573 | -40% | 1 | 1 | 0% | 1,945 | 794 | -59% | 0 | 0 | — |
case-02 | fail→fail | 20,186 | 5,812 | -71% | 1 | 1 | 0% | 4,013 | 850 | -79% | 0 | 0 | — |
case-03 | fail→fail | 15,649 | 5,130 | -67% | 1 | 1 | 0% | 3,016 | 824 | -73% | 0 | 0 | — |
case-04 | pass→pass | 7,999 | 3,411 | -57% | 1 | 1 | 0% | 1,457 | 1,245 | -15% | 0 | 0 | — |
case-05 | pass→pass | 6,979 | 3,456 | -50% | 1 | 1 | 0% | 1,148 | 1,155 | +1% | 0 | 0 | — |
case-06 | pass→pass | 3,935 | 3,884 | -1% | 1 | 1 | 0% | 686 | 1,173 | +71% | 0 | 0 | — |
case-07 | pass→pass | 19,970 | 6,429 | -68% | 1 | 1 | 0% | 2,552 | 1,607 | -37% | 0 | 0 | — |
case-08 | pass→pass | 3,773 | 3,360 | -11% | 1 | 1 | 0% | 622 | 1,088 | +75% | 0 | 0 | — |
case-09 | pass→fail | 7,218 | 2,522 | -65% | 1 | 1 | 0% | 1,078 | 869 | -19% | 0 | 0 | — |
case-10 | pass→pass | 5,965 | 3,113 | -48% | 1 | 1 | 0% | 973 | 990 | +2% | 0 | 0 | — |
case-11 | pass→pass | 6,454 | 5,461 | -15% | 1 | 1 | 0% | 1,034 | 1,343 | +30% | 0 | 0 | — |
case-12 | fail→fail | 9,765 | 5,269 | -46% | 1 | 1 | 0% | 1,811 | 763 | -58% | 0 | 0 | — |
case-13 | pass→pass | 12,428 | 5,006 | -60% | 1 | 1 | 0% | 2,039 | 1,260 | -38% | 0 | 0 | — |
case-14 | pass→pass | 25,829 | 4,442 | -83% | 1 | 1 | 0% | 2,721 | 1,377 | -49% | 0 | 0 | — |
case-15 | pass→pass | 14,051 | 5,905 | -58% | 1 | 1 | 0% | 2,176 | 1,608 | -26% | 0 | 0 | — |
case-16 | pass→pass | 10,447 | 2,151 | -79% | 1 | 1 | 0% | 1,126 | 844 | -25% | 0 | 0 | — |
case-17 | pass→pass | 6,223 | 3,562 | -43% | 1 | 1 | 0% | 832 | 1,109 | +33% | 0 | 0 | — |
case-18 | pass→pass | 5,145 | 3,344 | -35% | 1 | 1 | 0% | 837 | 1,098 | +31% | 0 | 0 | — |
case-19 | pass→fail | 16,744 | 5,495 | -67% | 1 | 1 | 0% | 3,149 | 1,090 | -65% | 0 | 0 | — |
case-20 | pass→pass | 15,804 | 13,086 | -17% | 1 | 1 | 0% | 2,636 | 2,351 | -11% | 0 | 0 | — |
case-21 | pass→pass | 16,074 | 12,094 | -25% | 1 | 1 | 0% | 2,992 | 2,765 | -8% | 0 | 0 | — |
case-22 | pass→pass | 22,366 | 5,000 | -78% | 1 | 1 | 0% | 2,198 | 1,300 | -41% | 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 18 counted toward the lift figure. The other 4 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 -100 percentage points is the difference between those two pass rates over the 18 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.