Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Design forms that minimize friction, prevent errors, and guide users to successful completion.
.claude/skills/owl-listener-form-design/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 15% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 23% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 4% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 21% | 0% |
You are an expert in designing forms that are clear, forgiving, and efficient to complete.
You apply form design principles to reduce abandonment, prevent errors, and make data collection feel effortless — from single-field inputs to complex multi-step flows.
Match input type to the data being collected: | Data type | Input type | |---|---| | Short text | Text input | | Long text | Textarea (with visible resize) | | One from few options (≤5) | Radio buttons (all visible) | | One from many options (6+) | Select / combobox | | Multiple from few options | Checkboxes | | Date | Date picker or segmented inputs (day/month/year) — never a freeform text field for structured dates | | Phone / card numbers | Formatted text input with masking | | Password | Password input with show/hide toggle |
<label for> or aria-label)aria-describedby)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,656 | 13,236 | -25% | 1 | 1 | 0% | 2,858 | 3,152 | +10% | 0 | 0 | — |
case-02 | fail→pass | 18,254 | 15,993 | -12% | 1 | 1 | 0% | 3,443 | 3,939 | +14% | 0 | 0 | — |
case-03 | pass→pass | 15,307 | 13,901 | -9% | 1 | 1 | 0% | 2,706 | 3,114 | +15% | 0 | 0 | — |
case-04 | pass→pass | 15,285 | 13,076 | -14% | 1 | 1 | 0% | 2,449 | 3,016 | +23% | 0 | 0 | — |
case-05 | pass→pass | 14,541 | 10,524 | -28% | 1 | 1 | 0% | 2,452 | 2,551 | +4% | 0 | 0 | — |
case-06 | pass→pass | 14,439 | 12,896 | -11% | 1 | 1 | 0% | 2,407 | 2,918 | +21% | 0 | 0 | — |
case-07 | pass→pass | 12,959 | 10,429 | -20% | 1 | 1 | 0% | 2,201 | 2,525 | +15% | 0 | 0 | — |
case-08 | pass→pass | 9,106 | 6,581 | -28% | 1 | 1 | 0% | 1,649 | 1,905 | +16% | 0 | 0 | — |
case-09 | pass→pass | 13,527 | 11,760 | -13% | 1 | 1 | 0% | 2,259 | 2,794 | +24% | 0 | 0 | — |
case-10 | pass→pass | 7,350 | 4,709 | -36% | 1 | 1 | 0% | 1,436 | 1,757 | +22% | 0 | 0 | — |
case-11 | pass→pass | 7,211 | 5,604 | -22% | 1 | 1 | 0% | 1,271 | 1,792 | +41% | 0 | 0 | — |
case-12 | pass→pass | 14,956 | 11,780 | -21% | 1 | 1 | 0% | 2,646 | 2,897 | +9% | 0 | 0 | — |
case-13 | pass→pass | 11,953 | 9,052 | -24% | 1 | 1 | 0% | 1,870 | 2,427 | +30% | 0 | 0 | — |
case-14 | pass→pass | 12,216 | 12,198 | -0% | 1 | 1 | 0% | 1,972 | 2,786 | +41% | 0 | 0 | — |
case-15 | pass→pass | 12,502 | 12,151 | -3% | 1 | 1 | 0% | 2,023 | 2,752 | +36% | 0 | 0 | — |
case-16 | pass→pass | 13,509 | 16,347 | +21% | 1 | 1 | 0% | 2,068 | 3,370 | +63% | 0 | 0 | — |
case-17 | pass→pass | 8,858 | 5,643 | -36% | 1 | 1 | 0% | 1,516 | 1,681 | +11% | 0 | 0 | — |
case-18 | pass→pass | 7,128 | 4,845 | -32% | 1 | 1 | 0% | 1,288 | 1,701 | +32% | 0 | 0 | — |
case-19 | pass→pass | 14,515 | 12,107 | -17% | 1 | 1 | 0% | 2,690 | 2,997 | +11% | 0 | 0 | — |
case-20 | pass→pass | 10,654 | 10,431 | -2% | 1 | 1 | 0% | 1,721 | 2,639 | +53% | 0 | 0 | — |
case-21 | pass→pass | 10,238 | 11,809 | +15% | 1 | 1 | 0% | 2,103 | 2,918 | +39% | 0 | 0 | — |
case-22 | pass→pass | 13,236 | 12,730 | -4% | 1 | 1 | 0% | 2,945 | 3,697 | +26% | 0 | 0 | — |
case-23 | pass→pass | 14,570 | 14,332 | -2% | 1 | 1 | 0% | 3,142 | 3,866 | +23% | 0 | 0 | — |
case-24 | pass→pass | 6,451 | 4,840 | -25% | 1 | 1 | 0% | 1,422 | 1,666 | +17% | 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. 24 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 24 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.