Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run backend (.NET) xUnit unit and integration tests via the developer CLI.
.claude/skills/platformplatform-test/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -43% | 0% |
bashdotnet run --project developer-cli -- test [--self-contained-system <name>] [--filter <expr>] [--no-build] [--exclude-category <cat>] --quiet
Use developer-cli exactly as written - do not expand to an absolute worktree path.
Backend only - there is no frontend test runner.
--self-contained-system <name> - narrows to one SCS (e.g. account, main)--filter <expr> - forwarded to dotnet test --filter to scope to a subset of tests--no-build - skip rebuild before running (faster after a recent build)--exclude-category <cat> - defaults to Noisy; pass an empty string to include themNo arguments runs every test across every SCS.
After build succeeds, run format, lint, test in parallel with --no-build.
bashdotnet run --project developer-cli -- test --quiet # all tests dotnet run --project developer-cli -- test --self-contained-system account --quiet # one SCS dotnet run --project developer-cli -- test --filter "FullyQualifiedName~LoginTests" --quiet # filter by name dotnet run --project developer-cli -- test --no-build --quiet # after a recent build
Verbose output goes to a log file. On success the CLI prints a one-line summary (totals + duration); on failure it lists the failed test names plus the log path - read the log if you need stack traces. Without --quiet every test result streams into the conversation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 6,806 | 1,465 | -78% | 1 | 1 | 0% | 953 | 561 | -41% | 0 | 0 | — |
case-02 | fail→fail | 6,584 | 6,277 | -5% | 1 | 1 | 0% | 935 | 813 | -13% | 0 | 0 | — |
case-03 | fail→pass | 5,899 | 5,081 | -14% | 1 | 1 | 0% | 847 | 575 | -32% | 0 | 0 | — |
case-04 | fail→pass | 10,233 | 2,444 | -76% | 1 | 1 | 0% | 1,663 | 550 | -67% | 0 | 0 | — |
case-05 | fail→pass | 4,178 | 3,075 | -26% | 1 | 1 | 0% | 475 | 684 | +44% | 0 | 0 | — |
case-06 | fail→pass | 7,825 | 2,284 | -71% | 1 | 1 | 0% | 1,264 | 717 | -43% | 0 | 0 | — |
case-07 | fail→pass | 5,879 | 5,210 | -11% | 1 | 1 | 0% | 929 | 717 | -23% | 0 | 0 | — |
case-08 | fail→pass | 11,952 | 3,021 | -75% | 1 | 1 | 0% | 1,941 | 844 | -57% | 0 | 0 | — |
case-09 | fail→fail | 4,860 | 5,588 | +15% | 1 | 1 | 0% | 755 | 619 | -18% | 0 | 0 | — |
case-10 | fail→pass | 13,277 | 6,718 | -49% | 1 | 1 | 0% | 1,833 | 1,402 | -24% | 0 | 0 | — |
case-11 | fail→pass | 10,519 | 2,537 | -76% | 1 | 1 | 0% | 1,584 | 626 | -60% | 0 | 0 | — |
case-12 | pass→pass | 10,689 | 2,833 | -73% | 1 | 1 | 0% | 1,742 | 744 | -57% | 0 | 0 | — |
case-13 | fail→pass | 10,476 | 1,988 | -81% | 1 | 1 | 0% | 1,909 | 650 | -66% | 0 | 0 | — |
case-14 | pass→pass | 11,344 | 1,447 | -87% | 1 | 1 | 0% | 1,733 | 550 | -68% | 0 | 0 | — |
case-15 | fail→pass | 7,608 | 1,496 | -80% | 1 | 1 | 0% | 1,281 | 572 | -55% | 0 | 0 | — |
case-16 | pass→pass | 12,216 | 1,651 | -86% | 1 | 1 | 0% | 2,084 | 599 | -71% | 0 | 0 | — |
case-17 | fail→pass | 14,204 | 3,194 | -78% | 1 | 1 | 0% | 2,324 | 821 | -65% | 0 | 0 | — |
case-18 | pass→pass | 12,059 | 2,809 | -77% | 1 | 1 | 0% | 1,832 | 780 | -57% | 0 | 0 | — |
case-19 | fail→pass | 10,142 | 1,756 | -83% | 1 | 1 | 0% | 1,600 | 589 | -63% | 0 | 0 | — |
case-20 | fail→pass | 6,391 | 1,820 | -72% | 1 | 1 | 0% | 1,110 | 596 | -46% | 0 | 0 | — |
case-21 | fail→pass | 7,838 | 6,985 | -11% | 1 | 1 | 0% | 1,315 | 1,568 | +19% | 0 | 0 | — |
case-22 | fail→pass | 9,296 | 1,844 | -80% | 1 | 1 | 0% | 1,587 | 592 | -63% | 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 20 counted toward the lift figure. The other 2 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 +73 percentage points is the difference between those two pass rates over the 20 comparable cases.
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.