Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Hick's Law to reduce decision time by limiting the number of simultaneous choices presented to users.
.claude/skills/owl-listener-hicks-law/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 4% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 18% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 5% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 16% | 0% |
You are an expert in cognitive load and decision-making in interface design.
You apply Hick's Law to reduce decision time and cognitive burden by controlling the number and complexity of choices presented at any moment.
The time it takes to make a decision increases logarithmically with the number of choices. Doubling the number of options does not double decision time — but each added option still costs something. The practical design implication:
RT = a + b × log₂(n + 1) — where RT is reaction time, n is the number of choices, and a/b are empirically measured constants. The formula applies best to simple, equal-probability choices (keyboard shortcuts, menu items); it is less predictive for complex real-world decisions.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | 14,853 | 11,306 | -24% | 1 | 1 | 0% | 2,587 | 2,501 | -3% | 0 | 0 | — |
case-01 | pass→pass | 14,849 | 11,353 | -24% | 1 | 1 | 0% | 2,170 | 2,264 | +4% | 0 | 0 | — |
case-02 | pass→pass | 14,204 | 13,545 | -5% | 1 | 1 | 0% | 2,293 | 2,717 | +18% | 0 | 0 | — |
case-03 | fail→fail | 14,223 | 12,752 | -10% | 1 | 1 | 0% | 2,347 | 2,728 | +16% | 0 | 0 | — |
case-05 | pass→pass | 15,104 | 12,227 | -19% | 1 | 1 | 0% | 2,344 | 2,462 | +5% | 0 | 0 | — |
case-06 | fail→pass | 11,852 | 9,518 | -20% | 1 | 1 | 0% | 1,972 | 2,032 | +3% | 0 | 0 | — |
case-07 | pass→pass | 13,517 | 12,338 | -9% | 1 | 1 | 0% | 2,113 | 2,449 | +16% | 0 | 0 | — |
case-08 | pass→pass | 10,672 | 9,404 | -12% | 1 | 1 | 0% | 1,890 | 2,100 | +11% | 0 | 0 | — |
case-09 | pass→pass | 10,768 | 9,446 | -12% | 1 | 1 | 0% | 1,946 | 2,164 | +11% | 0 | 0 | — |
case-10 | pass→pass | 17,779 | 11,827 | -33% | 1 | 1 | 0% | 2,804 | 2,591 | -8% | 0 | 0 | — |
case-11 | pass→pass | 14,935 | 14,059 | -6% | 1 | 1 | 0% | 2,194 | 2,538 | +16% | 0 | 0 | — |
case-12 | pass→pass | 14,113 | 12,078 | -14% | 1 | 1 | 0% | 2,417 | 2,426 | +0% | 0 | 0 | — |
case-13 | pass→pass | 11,373 | 9,103 | -20% | 1 | 1 | 0% | 1,738 | 1,924 | +11% | 0 | 0 | — |
case-14 | pass→pass | 14,560 | 12,931 | -11% | 1 | 1 | 0% | 2,192 | 2,510 | +15% | 0 | 0 | — |
case-15 | pass→pass | 13,998 | 11,121 | -21% | 1 | 1 | 0% | 2,335 | 2,302 | -1% | 0 | 0 | — |
case-16 | pass→pass | 11,646 | 11,120 | -5% | 1 | 1 | 0% | 2,025 | 2,240 | +11% | 0 | 0 | — |
case-17 | pass→pass | 13,797 | 12,233 | -11% | 1 | 1 | 0% | 2,330 | 2,575 | +11% | 0 | 0 | — |
case-18 | pass→pass | 12,964 | 11,726 | -10% | 1 | 1 | 0% | 2,136 | 2,227 | +4% | 0 | 0 | — |
case-19 | fail→fail | 12,460 | 10,627 | -15% | 1 | 1 | 0% | 2,165 | 2,262 | +4% | 0 | 0 | — |
case-20 | fail→fail | 11,937 | 10,773 | -10% | 1 | 1 | 0% | 2,442 | 2,369 | -3% | 0 | 0 | — |
case-21 | fail→fail | 12,248 | 10,038 | -18% | 1 | 1 | 0% | 2,145 | 2,237 | +4% | 0 | 0 | — |
case-22 | pass→pass | 12,994 | 11,304 | -13% | 1 | 1 | 0% | 2,154 | 2,374 | +10% | 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.