Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check a skill file and explain whether it is usable. Use when an agent needs to review a SKILL.md and call out missing structure.
.claude/skills/oahc09-missing-name/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✓→✗ | ▼ Worse | -21% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 4% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -31% | 0% |
Explain why the missing field blocks a clean specification review and show the exact repair the author should make.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 7,782 | 7,713 | -1% | 1 | 1 | 0% | 1,657 | 1,724 | +4% | 0 | 0 | — |
case-02 | pass→pass | 5,526 | 8,504 | +54% | 1 | 1 | 0% | 1,202 | 1,569 | +31% | 0 | 0 | — |
case-03 | pass→pass | 10,874 | 11,117 | +2% | 1 | 1 | 0% | 2,043 | 2,165 | +6% | 0 | 0 | — |
case-04 | pass→pass | 7,636 | 5,015 | -34% | 1 | 1 | 0% | 1,512 | 1,040 | -31% | 0 | 0 | — |
case-05 | pass→pass | 7,370 | 5,507 | -25% | 1 | 1 | 0% | 1,391 | 1,180 | -15% | 0 | 0 | — |
case-06 | pass→pass | 4,296 | 5,440 | +27% | 1 | 1 | 0% | 894 | 1,215 | +36% | 0 | 0 | — |
case-07 | pass→pass | 5,720 | 5,056 | -12% | 1 | 1 | 0% | 1,009 | 944 | -6% | 0 | 0 | — |
case-08 | pass→pass | 9,402 | 7,255 | -23% | 1 | 1 | 0% | 1,718 | 1,432 | -17% | 0 | 0 | — |
case-09 | pass→pass | 6,195 | 6,171 | -0% | 1 | 1 | 0% | 1,108 | 1,128 | +2% | 0 | 0 | — |
case-10 | pass→pass | 6,428 | 4,312 | -33% | 1 | 1 | 0% | 1,241 | 828 | -33% | 0 | 0 | — |
case-11 | pass→pass | 6,751 | 5,602 | -17% | 1 | 1 | 0% | 1,363 | 1,092 | -20% | 0 | 0 | — |
case-12 | pass→pass | 7,382 | 5,202 | -30% | 1 | 1 | 0% | 1,355 | 1,021 | -25% | 0 | 0 | — |
case-13 | pass→pass | 5,510 | 5,020 | -9% | 1 | 1 | 0% | 1,110 | 1,043 | -6% | 0 | 0 | — |
case-14 | pass→pass | 4,909 | 4,726 | -4% | 1 | 1 | 0% | 1,031 | 995 | -3% | 0 | 0 | — |
case-15 | pass→pass | 9,946 | 4,901 | -51% | 1 | 1 | 0% | 1,741 | 925 | -47% | 0 | 0 | — |
case-16 | pass→pass | 5,466 | 4,775 | -13% | 1 | 1 | 0% | 1,018 | 1,049 | +3% | 0 | 0 | — |
case-17 | pass→pass | 6,576 | 6,496 | -1% | 1 | 1 | 0% | 1,208 | 1,389 | +15% | 0 | 0 | — |
case-18 | pass→pass | 5,940 | 4,986 | -16% | 1 | 1 | 0% | 1,193 | 940 | -21% | 0 | 0 | — |
case-19 | pass→pass | 6,124 | 5,026 | -18% | 1 | 1 | 0% | 1,118 | 1,050 | -6% | 0 | 0 | — |
case-20 | pass→pass | 4,291 | 4,962 | +16% | 1 | 1 | 0% | 893 | 893 | 0% | 0 | 0 | — |
case-21 | pass→pass | 7,160 | 5,929 | -17% | 1 | 1 | 0% | 1,303 | 1,068 | -18% | 0 | 0 | — |
case-22 | pass→fail | 6,803 | 4,868 | -28% | 1 | 1 | 0% | 1,225 | 970 | -21% | 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +4% |
Other measured skills in the registry, with their headline benchmark lift.