Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive test runner for entire Python projects. Use when: - Running all tests in a project - Discovering untested files - Generating coverage reports - Finding gaps in test coverage - Testing all modules systematically Works with pytest and generates detailed reports.
.claude/skills/shadd0wtaka-full-project-test-runner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -66% | 0% |
Execute comprehensive testing across entire codebase.
bash# Test entire project ./scripts/test_project.py /path/to/project # With coverage report ./scripts/test_project.py /path/to/project --coverage # Fail fast (stop on first failure) ./scripts/test_project.py /path/to/project --fail-fast
See references/USAGE.md for detailed examples.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,423 | 3,306 | -73% | 1 | 1 | 0% | 2,208 | 691 | -69% | 0 | 0 | — |
case-02 | fail→fail | 2,589 | 4,971 | +92% | 1 | 1 | 0% | 248 | 412 | +66% | 0 | 0 | — |
case-03 | fail→fail | 4,523 | 4,985 | +10% | 1 | 1 | 0% | 221 | 531 | +140% | 0 | 0 | — |
case-04 | fail→pass | 4,218 | 2,690 | -36% | 1 | 1 | 0% | 749 | 683 | -9% | 0 | 0 | — |
case-05 | fail→pass | 8,266 | 3,240 | -61% | 1 | 1 | 0% | 1,472 | 799 | -46% | 0 | 0 | — |
case-06 | pass→pass | 12,408 | 3,116 | -75% | 1 | 1 | 0% | 1,882 | 761 | -60% | 0 | 0 | — |
case-07 | fail→pass | 10,398 | 2,884 | -72% | 1 | 1 | 0% | 1,629 | 703 | -57% | 0 | 0 | — |
case-08 | pass→pass | 11,010 | 2,817 | -74% | 1 | 1 | 0% | 1,824 | 642 | -65% | 0 | 0 | — |
case-09 | fail→pass | 12,901 | 2,945 | -77% | 1 | 1 | 0% | 2,210 | 739 | -67% | 0 | 0 | — |
case-10 | pass→pass | 6,247 | 2,347 | -62% | 1 | 1 | 0% | 1,138 | 597 | -48% | 0 | 0 | — |
case-11 | fail→pass | 8,279 | 1,927 | -77% | 1 | 1 | 0% | 1,421 | 478 | -66% | 0 | 0 | — |
case-12 | fail→pass | 9,016 | 1,635 | -82% | 1 | 1 | 0% | 1,604 | 439 | -73% | 0 | 0 | — |
case-13 | fail→pass | 7,378 | 2,043 | -72% | 1 | 1 | 0% | 1,184 | 572 | -52% | 0 | 0 | — |
case-14 | fail→pass | 9,909 | 4,129 | -58% | 1 | 1 | 0% | 1,813 | 998 | -45% | 0 | 0 | — |
case-15 | pass→pass | 7,818 | 4,540 | -42% | 1 | 1 | 0% | 1,310 | 975 | -26% | 0 | 0 | — |
case-16 | pass→pass | 12,926 | 3,460 | -73% | 1 | 1 | 0% | 1,943 | 801 | -59% | 0 | 0 | — |
case-17 | fail→pass | 6,722 | 1,848 | -73% | 1 | 1 | 0% | 1,002 | 528 | -47% | 0 | 0 | — |
case-18 | fail→pass | 6,954 | 2,055 | -70% | 1 | 1 | 0% | 1,009 | 534 | -47% | 0 | 0 | — |
case-19 | pass→pass | 11,518 | 2,000 | -83% | 1 | 1 | 0% | 1,949 | 546 | -72% | 0 | 0 | — |
case-20 | pass→pass | 4,105 | 3,984 | -3% | 1 | 1 | 0% | 723 | 985 | +36% | 0 | 0 | — |
case-21 | pass→pass | 5,972 | 4,381 | -27% | 1 | 1 | 0% | 1,043 | 972 | -7% | 0 | 0 | — |
case-22 | pass→pass | 6,303 | 5,247 | -17% | 1 | 1 | 0% | 1,235 | 1,287 | +4% | 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 +45 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.