Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Auto-format code via the developer CLI - backend (.NET via JetBrains cleanupcode), frontend (oxfmt + oxlint --fix), and the developer CLI itself.
.claude/skills/platformplatform-format/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -37% | 0% |
bashdotnet run --project developer-cli -- format [--backend] [--frontend] [--cli] [--self-contained-system <name>] [--no-build] [--all-files] --quiet
Use developer-cli exactly as written - do not expand to an absolute worktree path.
--backend - .NET (JetBrains cleanupcode)--frontend - React/TypeScript (oxfmt + oxlint --fix)--cli - the developer CLI itself--self-contained-system <name> - narrows backend formatting to one SCS (e.g. account, main)--no-build - skip the dotnet tool restore step (faster after a recent run)--all-files - format every file in the solution. Default is to format only .cs files changed against origin/main (faster).No arguments formats everything (changed-only by default). Unformatted code fails CI - commit all changes, never revert.
After build succeeds, run format, lint, test in parallel with --no-build.
bashdotnet run --project developer-cli -- format --quiet # everything dotnet run --project developer-cli -- format --backend --quiet # all backend dotnet run --project developer-cli -- format --frontend --quiet # frontend dotnet run --project developer-cli -- format --backend --self-contained-system account --quiet # one SCS
Verbose output goes to a log file. On success the CLI prints a single line; on failure it prints a short error message - read the log if you need details. Backend is slow - run last. Frontend is fast.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 5,644 | 1,433 | -75% | 1 | 1 | 0% | 887 | 580 | -35% | 0 | 0 | — |
case-02 | fail→pass | 3,815 | 1,766 | -54% | 1 | 1 | 0% | 615 | 618 | +0% | 0 | 0 | — |
case-03 | fail→pass | 3,464 | 1,298 | -63% | 1 | 1 | 0% | 355 | 546 | +54% | 0 | 0 | — |
case-04 | fail→pass | 7,403 | 1,837 | -75% | 1 | 1 | 0% | 1,224 | 649 | -47% | 0 | 0 | — |
case-05 | fail→pass | 6,530 | 1,908 | -71% | 1 | 1 | 0% | 1,041 | 652 | -37% | 0 | 0 | — |
case-06 | fail→pass | 5,085 | 2,189 | -57% | 1 | 1 | 0% | 737 | 689 | -7% | 0 | 0 | — |
case-07 | fail→pass | 9,753 | 1,790 | -82% | 1 | 1 | 0% | 1,574 | 606 | -61% | 0 | 0 | — |
case-08 | fail→pass | 9,389 | 2,285 | -76% | 1 | 1 | 0% | 1,457 | 763 | -48% | 0 | 0 | — |
case-09 | fail→pass | 15,160 | 1,965 | -87% | 1 | 1 | 0% | 2,409 | 669 | -72% | 0 | 0 | — |
case-10 | fail→pass | 8,796 | 2,572 | -71% | 1 | 1 | 0% | 1,305 | 751 | -42% | 0 | 0 | — |
case-11 | fail→pass | 10,988 | 1,361 | -88% | 1 | 1 | 0% | 1,689 | 513 | -70% | 0 | 0 | — |
case-12 | fail→pass | 6,078 | 1,492 | -75% | 1 | 1 | 0% | 894 | 543 | -39% | 0 | 0 | — |
case-13 | fail→pass | 7,435 | 1,932 | -74% | 1 | 1 | 0% | 1,311 | 599 | -54% | 0 | 0 | — |
case-14 | fail→pass | 13,908 | 2,783 | -80% | 1 | 1 | 0% | 2,193 | 632 | -71% | 0 | 0 | — |
case-15 | fail→pass | 10,585 | 1,941 | -82% | 1 | 1 | 0% | 1,723 | 642 | -63% | 0 | 0 | — |
case-16 | fail→pass | 14,824 | 2,312 | -84% | 1 | 1 | 0% | 2,330 | 732 | -69% | 0 | 0 | — |
case-17 | fail→pass | 6,998 | 1,069 | -85% | 1 | 1 | 0% | 1,100 | 471 | -57% | 0 | 0 | — |
case-18 | fail→pass | 9,513 | 1,460 | -85% | 1 | 1 | 0% | 1,467 | 540 | -63% | 0 | 0 | — |
case-19 | pass→pass | 8,602 | 1,206 | -86% | 1 | 1 | 0% | 1,378 | 526 | -62% | 0 | 0 | — |
case-20 | pass→pass | 5,556 | 4,362 | -21% | 1 | 1 | 0% | 1,065 | 1,143 | +7% | 0 | 0 | — |
case-21 | pass→pass | 4,672 | 2,721 | -42% | 1 | 1 | 0% | 806 | 770 | -4% | 0 | 0 | — |
case-22 | pass→pass | 3,025 | 2,607 | -14% | 1 | 1 | 0% | 405 | 767 | +89% | 0 | 0 | — |
case-23 | pass→pass | 5,983 | 3,799 | -37% | 1 | 1 | 0% | 954 | 977 | +2% | 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. 23 cases were attempted. The headline lift of +78 percentage points is the difference between those two pass rates over the 23 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.