Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A valid test skill for integration testing. Use when running tests.
.claude/skills/michellepellon-valid-skill/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✓→✗ | ▼ Worse | -38% | 0% |
| case-01 | ✓→✓ | = Same ✓ | -38% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 33% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -48% | 0% |
| case-05 | ✓→✓ | = Same ✓ | -8% | 0% |
This is a valid skill for testing purposes.
Follow these steps to use this skill.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 4,714 | 2,629 | -44% | 1 | 1 | 0% | 695 | 430 | -38% | 0 | 0 | — |
case-02 | pass→pass | 2,523 | 2,928 | +16% | 1 | 1 | 0% | 350 | 467 | +33% | 0 | 0 | — |
case-03 | pass→pass | 5,611 | 2,634 | -53% | 1 | 1 | 0% | 959 | 498 | -48% | 0 | 0 | — |
case-04 | fail→fail | 7,797 | 6,021 | -23% | 1 | 1 | 0% | 1,422 | 1,075 | -24% | 0 | 0 | — |
case-05 | pass→pass | 5,901 | 4,848 | -18% | 1 | 1 | 0% | 922 | 847 | -8% | 0 | 0 | — |
case-06 | pass→pass | 8,299 | 4,593 | -45% | 1 | 1 | 0% | 1,384 | 690 | -50% | 0 | 0 | — |
case-07 | pass→pass | 2,981 | 3,261 | +9% | 1 | 1 | 0% | 553 | 528 | -5% | 0 | 0 | — |
case-08 | pass→pass | 5,884 | 3,723 | -37% | 1 | 1 | 0% | 838 | 563 | -33% | 0 | 0 | — |
case-09 | pass→pass | 2,335 | 1,819 | -22% | 1 | 1 | 0% | 290 | 232 | -20% | 0 | 0 | — |
case-10 | pass→pass | 5,818 | 4,274 | -27% | 1 | 1 | 0% | 966 | 741 | -23% | 0 | 0 | — |
case-11 | pass→pass | 11,674 | 7,015 | -40% | 1 | 1 | 0% | 1,873 | 1,101 | -41% | 0 | 0 | — |
case-12 | pass→pass | 6,885 | 3,281 | -52% | 1 | 1 | 0% | 1,080 | 593 | -45% | 0 | 0 | — |
case-13 | pass→pass | 9,698 | 8,077 | -17% | 1 | 1 | 0% | 1,676 | 1,484 | -11% | 0 | 0 | — |
case-14 | pass→pass | 8,246 | 3,207 | -61% | 1 | 1 | 0% | 1,388 | 546 | -61% | 0 | 0 | — |
case-15 | pass→pass | 6,797 | 3,482 | -49% | 1 | 1 | 0% | 1,166 | 564 | -52% | 0 | 0 | — |
case-16 | pass→fail | 5,360 | 2,618 | -51% | 1 | 1 | 0% | 650 | 402 | -38% | 0 | 0 | — |
case-17 | pass→pass | 7,117 | 5,068 | -29% | 1 | 1 | 0% | 1,238 | 902 | -27% | 0 | 0 | — |
case-18 | pass→pass | 10,426 | 9,165 | -12% | 1 | 1 | 0% | 2,012 | 1,520 | -24% | 0 | 0 | — |
case-19 | pass→pass | 2,911 | 2,347 | -19% | 1 | 1 | 0% | 524 | 420 | -20% | 0 | 0 | — |
case-20 | pass→pass | 3,831 | 3,707 | -3% | 1 | 1 | 0% | 609 | 624 | +2% | 0 | 0 | — |
case-21 | pass→pass | 3,570 | 3,628 | +2% | 1 | 1 | 0% | 633 | 601 | -5% | 0 | 0 | — |
case-22 | pass→pass | 7,484 | 3,826 | -49% | 1 | 1 | 0% | 1,034 | 639 | -38% | 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 -100 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.
Other measured skills in the registry, with their headline benchmark lift.