Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply the Law of Continuity — the eye follows alignment and unbroken paths. Use when sequencing steps, aligning content, or designing carousels and timelines. For grouping rather than sequencing, use `law-of-proximity`.
.claude/skills/owl-listener-law-of-continuity/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 33% | 0% |
You are an expert in visual flow, eye movement, and directional design.
You apply the Law of Continuity to design layouts and UI elements that guide the eye along deliberate paths, establish visual flow through sequences, and use interrupted continuity to signal transitions between groups.
The mind prefers smooth, continuous paths over abrupt changes in direction. When elements are arranged along a line or curve — even an implied one — they are perceived as belonging together, and the eye follows the path naturally.
Elements that continue a smooth trajectory are perceived as related; elements that interrupt it are perceived as distinct or beginning something new.
The most fundamental application of continuity is alignment:
In a form, every input aligned on the same left edge creates a continuous reading path. Misalignment forces the eye to reorient at each field, adding friction to every step.
Arrows and chevrons extend the trajectory the eye is already following:
The arrow does not add information; it makes continuous flow explicit where it might otherwise be ambiguous.
Timeline components rely entirely on continuity. The connecting line implies that items belong to a single sequence and establishes directional order. Without the line, the same items read as an unordered list. The line creates sequence from spatial arrangement.
Implied directional paths signal interaction:
The affordance works through continuity: the eye reads the implied path and the hand follows it.
Just as continuity groups, interrupted continuity separates. A deliberate break in an otherwise continuous path signals a transition:
Continuity interacts with hierarchy:
Indented content is not just spatially different; it is on a different continuous axis, which is what makes the hierarchy legible.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,850 | 19,513 | +23% | 1 | 1 | 0% | 2,357 | 2,903 | +23% | 0 | 0 | — |
case-02 | pass→pass | 15,509 | 15,572 | +0% | 1 | 1 | 0% | 2,139 | 2,991 | +40% | 0 | 0 | — |
case-03 | fail→pass | 11,483 | 14,520 | +26% | 1 | 1 | 0% | 1,737 | 2,818 | +62% | 0 | 0 | — |
case-04 | fail→pass | 15,223 | 13,670 | -10% | 1 | 1 | 0% | 2,221 | 2,827 | +27% | 0 | 0 | — |
case-05 | fail→pass | 12,089 | 15,265 | +26% | 1 | 1 | 0% | 1,988 | 2,838 | +43% | 0 | 0 | — |
case-11 | pass→pass | 13,471 | 13,085 | -3% | 1 | 1 | 0% | 1,976 | 2,510 | +27% | 0 | 0 | — |
case-06 | pass→pass | 13,843 | 16,793 | +21% | 1 | 1 | 0% | 2,095 | 3,143 | +50% | 0 | 0 | — |
case-07 | pass→pass | 17,453 | 14,185 | -19% | 1 | 1 | 0% | 2,575 | 2,956 | +15% | 0 | 0 | — |
case-08 | fail→pass | 12,699 | 15,025 | +18% | 1 | 1 | 0% | 2,059 | 2,739 | +33% | 0 | 0 | — |
case-09 | pass→pass | 15,710 | 16,659 | +6% | 1 | 1 | 0% | 2,559 | 3,293 | +29% | 0 | 0 | — |
case-10 | pass→pass | 16,029 | 17,610 | +10% | 1 | 1 | 0% | 2,400 | 3,080 | +28% | 0 | 0 | — |
case-12 | pass→pass | 13,741 | 14,179 | +3% | 1 | 1 | 0% | 2,039 | 2,863 | +40% | 0 | 0 | — |
case-13 | pass→pass | 14,332 | 12,644 | -12% | 1 | 1 | 0% | 2,104 | 2,462 | +17% | 0 | 0 | — |
case-14 | fail→fail | 13,636 | 12,735 | -7% | 1 | 1 | 0% | 2,027 | 2,674 | +32% | 0 | 0 | — |
case-15 | pass→pass | 15,304 | 16,476 | +8% | 1 | 1 | 0% | 2,170 | 2,678 | +23% | 0 | 0 | — |
case-16 | pass→pass | 14,404 | 16,222 | +13% | 1 | 1 | 0% | 2,243 | 3,088 | +38% | 0 | 0 | — |
case-17 | pass→pass | 14,392 | 15,035 | +4% | 1 | 1 | 0% | 2,440 | 3,114 | +28% | 0 | 0 | — |
case-18 | fail→pass | 15,893 | 15,509 | -2% | 1 | 1 | 0% | 2,323 | 2,863 | +23% | 0 | 0 | — |
case-19 | pass→pass | 11,456 | 10,419 | -9% | 1 | 1 | 0% | 1,639 | 2,260 | +38% | 0 | 0 | — |
case-20 | pass→pass | 15,112 | 13,144 | -13% | 1 | 1 | 0% | 2,478 | 3,055 | +23% | 0 | 0 | — |
case-21 | pass→pass | 9,556 | 8,863 | -7% | 1 | 1 | 0% | 1,481 | 2,069 | +40% | 0 | 0 | — |
case-22 | fail→pass | 8,406 | 7,546 | -10% | 1 | 1 | 0% | 1,741 | 2,150 | +23% | 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 +32 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.