Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Set optimal line lengths for readability across typography scales and responsive layouts.
.claude/skills/owl-listener-readable-measure/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -23% | 0% |
You are an expert in typographic measure and its effect on reading comfort and comprehension.
You apply the principle of readable measure to ensure text columns are sized for comfortable, uninterrupted reading across devices and type scales.
Measure is the length of a line of text. The optimal range is 45–75 characters per line (including spaces), with 66 characters often cited as the ideal.
ch CSS unit (width of the 0 glyph) as a rough proxy: max-width: 65chch is approximate| Context | Target | |---|---| | Long-form articles, docs | 55–70 characters | | UI body copy, descriptions | 45–65 characters | | Captions, helper text | 40–60 characters | | Pull quotes, callouts | 30–45 characters |
max-width on text containers, not just font size| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,793 | 14,549 | -30% | 1 | 1 | 0% | 3,904 | 3,297 | -16% | 0 | 0 | — |
case-02 | fail→fail | 11,509 | 8,006 | -30% | 1 | 1 | 0% | 1,808 | 1,794 | -1% | 0 | 0 | — |
case-03 | pass→pass | 3,521 | 4,524 | +28% | 1 | 1 | 0% | 600 | 1,285 | +114% | 0 | 0 | — |
case-04 | pass→pass | 11,590 | 6,781 | -41% | 1 | 1 | 0% | 1,953 | 1,663 | -15% | 0 | 0 | — |
case-05 | fail→pass | 11,343 | 11,288 | -0% | 1 | 1 | 0% | 1,924 | 2,304 | +20% | 0 | 0 | — |
case-06 | pass→pass | 9,124 | 7,400 | -19% | 1 | 1 | 0% | 1,631 | 1,887 | +16% | 0 | 0 | — |
case-07 | pass→pass | 11,282 | 5,700 | -49% | 1 | 1 | 0% | 2,077 | 1,517 | -27% | 0 | 0 | — |
case-08 | fail→pass | 12,844 | 11,306 | -12% | 1 | 1 | 0% | 2,231 | 2,508 | +12% | 0 | 0 | — |
case-09 | fail→fail | 11,288 | 6,468 | -43% | 1 | 1 | 0% | 1,891 | 1,566 | -17% | 0 | 0 | — |
case-10 | pass→pass | 8,756 | 5,602 | -36% | 1 | 1 | 0% | 1,659 | 1,467 | -12% | 0 | 0 | — |
case-11 | pass→pass | 11,899 | 12,073 | +1% | 1 | 1 | 0% | 1,927 | 2,552 | +32% | 0 | 0 | — |
case-12 | pass→pass | 13,546 | 10,006 | -26% | 1 | 1 | 0% | 2,192 | 2,273 | +4% | 0 | 0 | — |
case-13 | pass→pass | 11,956 | 8,581 | -28% | 1 | 1 | 0% | 2,292 | 2,174 | -5% | 0 | 0 | — |
case-14 | pass→pass | 8,064 | 7,052 | -13% | 1 | 1 | 0% | 1,297 | 1,570 | +21% | 0 | 0 | — |
case-15 | pass→pass | 8,961 | 6,775 | -24% | 1 | 1 | 0% | 1,467 | 1,591 | +8% | 0 | 0 | — |
case-16 | pass→pass | 5,420 | 4,017 | -26% | 1 | 1 | 0% | 1,022 | 1,040 | +2% | 0 | 0 | — |
case-17 | fail→fail | 9,116 | 9,134 | +0% | 1 | 1 | 0% | 1,802 | 2,124 | +18% | 0 | 0 | — |
case-18 | fail→pass | 8,001 | 2,803 | -65% | 1 | 1 | 0% | 1,606 | 944 | -41% | 0 | 0 | — |
case-19 | fail→pass | 8,047 | 3,738 | -54% | 1 | 1 | 0% | 1,561 | 1,201 | -23% | 0 | 0 | — |
case-20 | pass→pass | 3,306 | 3,047 | -8% | 1 | 1 | 0% | 602 | 1,131 | +88% | 0 | 0 | — |
case-21 | pass→pass | 7,769 | 9,222 | +19% | 1 | 1 | 0% | 1,437 | 2,137 | +49% | 0 | 0 | — |
case-22 | pass→pass | 8,085 | 7,540 | -7% | 1 | 1 | 0% | 1,491 | 1,728 | +16% | 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 +23 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.