Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Scaffolds an xUnit integration test project for validating Oracle-to-PostgreSQL database migration behavior in .NET solutions. Creates the test project, transaction-rollback base class, and seed data manager. Use when setting up test infrastructure before writing migration integration tests, or when a test project is needed for Oracle-to-PostgreSQL validation.
.claude/skills/scaffolding-oracle-to-postgres-migration-test-project/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 325% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 18% | 0% |
Creates a compilable, empty xUnit test project with transaction management and seed data infrastructure for a single target project. Run once per project before writing tests.
Progress:
- [ ] Step 1: Inspect the target project
- [ ] Step 2: Create the xUnit test project
- [ ] Step 3: Implement transaction-rollback base class
- [ ] Step 4: Implement seed data manager
- [ ] Step 5: Verify the project compilesStep 1: Inspect the target project
Read the target project's .csproj to determine the .NET version and existing package references. Match these versions exactly — do not upgrade.
Step 2: Create the xUnit test project
Oracle.ManagedDataAccess.Core) and xUnit.appsettings.json configured for Oracle database connectivity.Step 3: Implement transaction-rollback base class
Step 4: Implement seed data manager
TRUNCATE TABLE — preserve existing database data.Step 5: Verify the project compiles
Build the test project and confirm it compiles with zero errors before finishing.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | pass→pass | 15,856 | 7,169 | -55% | 1 | 1 | 0% | 3,079 | 1,895 | -38% | 0 | 0 | — |
case-01 | fail→fail | 16,858 | 4,414 | -74% | 1 | 1 | 0% | 3,485 | 813 | -77% | 0 | 0 | — |
case-02 | fail→fail | 15,794 | 1,224 | -92% | 1 | 1 | 0% | 3,475 | 712 | -80% | 0 | 0 | — |
case-03 | fail→fail | 13,223 | 2,153 | -84% | 1 | 1 | 0% | 2,819 | 813 | -71% | 0 | 0 | — |
case-04 | fail→pass | 11,990 | 3,694 | -69% | 1 | 1 | 0% | 2,875 | 1,093 | -62% | 0 | 0 | — |
case-05 | fail→pass | 22,335 | 19,474 | -13% | 1 | 1 | 0% | 5,366 | 4,804 | -10% | 0 | 0 | — |
case-06 | fail→fail | 9,272 | 22,031 | +138% | 1 | 1 | 0% | 1,830 | 5,645 | +208% | 0 | 0 | — |
case-07 | fail→pass | 13,648 | 12,027 | -12% | 1 | 1 | 0% | 3,000 | 3,323 | +11% | 0 | 0 | — |
case-08 | fail→pass | 4,622 | 15,612 | +238% | 1 | 1 | 0% | 936 | 3,981 | +325% | 0 | 0 | — |
case-09 | fail→pass | 13,570 | 12,100 | -11% | 1 | 1 | 0% | 2,766 | 3,271 | +18% | 0 | 0 | — |
case-10 | fail→pass | 10,426 | 5,358 | -49% | 1 | 1 | 0% | 1,926 | 1,297 | -33% | 0 | 0 | — |
case-11 | fail→fail | 8,652 | 8,838 | +2% | 1 | 1 | 0% | 1,888 | 2,423 | +28% | 0 | 0 | — |
case-12 | pass→pass | 13,423 | 10,838 | -19% | 1 | 1 | 0% | 2,500 | 2,925 | +17% | 0 | 0 | — |
case-13 | fail→pass | 7,387 | 2,599 | -65% | 1 | 1 | 0% | 1,553 | 1,034 | -33% | 0 | 0 | — |
case-14 | fail→pass | 12,220 | 3,575 | -71% | 1 | 1 | 0% | 2,108 | 1,252 | -41% | 0 | 0 | — |
case-15 | fail→pass | 8,604 | 4,645 | -46% | 1 | 1 | 0% | 1,609 | 1,331 | -17% | 0 | 0 | — |
case-17 | pass→pass | 9,264 | 3,482 | -62% | 1 | 1 | 0% | 1,800 | 1,145 | -36% | 0 | 0 | — |
case-18 | pass→pass | 7,451 | 3,415 | -54% | 1 | 1 | 0% | 1,525 | 1,195 | -22% | 0 | 0 | — |
case-19 | fail→fail | 10,973 | 10,972 | -0% | 1 | 1 | 0% | 2,446 | 3,002 | +23% | 0 | 0 | — |
case-20 | fail→pass | 11,150 | 7,226 | -35% | 1 | 1 | 0% | 1,741 | 1,628 | -6% | 0 | 0 | — |
case-21 | pass→pass | 14,788 | 8,499 | -43% | 1 | 1 | 0% | 2,558 | 1,993 | -22% | 0 | 0 | — |
case-22 | pass→pass | 5,654 | 2,043 | -64% | 1 | 1 | 0% | 968 | 876 | -10% | 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 +45 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/24/2026 | +41% |
Other measured skills in the registry, with their headline benchmark lift.