Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Fitts's Law to size and position interactive targets for fast, accurate interaction.
.claude/skills/owl-listener-fitts-law/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-14 | ✓→✓ | = Same ✓ | 21% | 0% |
| case-15 | ✓→✓ | = Same ✓ | 45% | 0% |
| case-16 | ✓→✓ | = Same ✓ | 27% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 19% | 0% |
You are an expert in the relationship between target size, distance, and interaction accuracy.
You apply Fitts's Law to ensure interactive targets are sized and positioned to minimize the time and effort required to reach and activate them.
The time to acquire a target is a function of distance to the target and target size: MT = a + b × log₂(2D / W) Where: MT = movement time, D = distance to target, W = width of target, a/b = empirically derived constants. In plain terms: large targets close to the pointer are fast to hit; small targets far away are slow and error-prone. Both dimensions — size and proximity — matter independently.
| Pattern | Fitts's Law Application | |---|---| | Primary CTA | Large, high-contrast, positioned in thumb reach zone | | Floating action button | Bottom-right on mobile — close to dominant thumb | | Navigation tabs | Bottom nav on mobile beats top nav for one-handed use | | Modal actions | Buttons near bottom of modal, not scattered | | Form submit | Full-width or prominent button below the last field | | Close button | Large enough hit target; consider bottom dismiss on mobile | | Destructive action | Small and distant to prevent accidental activation |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | pass→pass | 16,017 | 11,909 | -26% | 1 | 1 | 0% | 2,425 | 2,925 | +21% | 0 | 0 | — |
case-15 | pass→pass | 10,675 | 11,028 | +3% | 1 | 1 | 0% | 1,830 | 2,646 | +45% | 0 | 0 | — |
case-16 | pass→pass | 10,521 | 9,899 | -6% | 1 | 1 | 0% | 1,811 | 2,293 | +27% | 0 | 0 | — |
case-17 | fail→pass | 10,263 | 10,713 | +4% | 1 | 1 | 0% | 1,720 | 2,765 | +61% | 0 | 0 | — |
case-01 | pass→pass | 12,026 | 9,511 | -21% | 1 | 1 | 0% | 2,000 | 2,385 | +19% | 0 | 0 | — |
case-02 | pass→pass | 10,406 | 8,309 | -20% | 1 | 1 | 0% | 1,793 | 2,141 | +19% | 0 | 0 | — |
case-03 | pass→pass | 13,898 | 8,777 | -37% | 1 | 1 | 0% | 2,260 | 2,214 | -2% | 0 | 0 | — |
case-04 | pass→pass | 11,719 | 9,019 | -23% | 1 | 1 | 0% | 2,162 | 2,397 | +11% | 0 | 0 | — |
case-05 | pass→pass | 10,167 | 8,728 | -14% | 1 | 1 | 0% | 1,884 | 2,261 | +20% | 0 | 0 | — |
case-06 | pass→pass | 10,066 | 10,121 | +1% | 1 | 1 | 0% | 1,736 | 2,459 | +42% | 0 | 0 | — |
case-07 | pass→pass | 14,853 | 15,372 | +3% | 1 | 1 | 0% | 2,289 | 3,055 | +33% | 0 | 0 | — |
case-08 | pass→pass | 12,818 | 12,030 | -6% | 1 | 1 | 0% | 2,051 | 2,853 | +39% | 0 | 0 | — |
case-09 | pass→pass | 10,389 | 8,826 | -15% | 1 | 1 | 0% | 1,775 | 2,296 | +29% | 0 | 0 | — |
case-18 | pass→pass | 15,005 | 12,065 | -20% | 1 | 1 | 0% | 2,347 | 2,673 | +14% | 0 | 0 | — |
case-10 | pass→pass | 10,045 | 7,065 | -30% | 1 | 1 | 0% | 1,663 | 1,985 | +19% | 0 | 0 | — |
case-11 | pass→pass | 9,887 | 9,794 | -1% | 1 | 1 | 0% | 1,720 | 2,368 | +38% | 0 | 0 | — |
case-12 | pass→pass | 12,435 | 11,861 | -5% | 1 | 1 | 0% | 2,293 | 2,779 | +21% | 0 | 0 | — |
case-13 | pass→pass | 6,894 | 6,812 | -1% | 1 | 1 | 0% | 1,240 | 1,890 | +52% | 0 | 0 | — |
case-19 | pass→pass | 12,351 | 10,059 | -19% | 1 | 1 | 0% | 2,035 | 2,241 | +10% | 0 | 0 | — |
case-20 | pass→pass | 8,628 | 8,952 | +4% | 1 | 1 | 0% | 1,504 | 2,319 | +54% | 0 | 0 | — |
case-21 | fail→fail | 12,575 | 15,646 | +24% | 1 | 1 | 0% | 2,047 | 3,281 | +60% | 0 | 0 | — |
case-22 | pass→pass | 17,832 | 14,025 | -21% | 1 | 1 | 0% | 3,093 | 3,247 | +5% | 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 +5 percentage points is the difference between those two pass rates over the 22 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.