Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply the Law of Closure — the eye completes implied shapes from partial forms. Use when reducing visual weight by dropping borders or letting negative space suggest structure. For explicit containers, use `law-of-common-region`.
.claude/skills/owl-listener-law-of-closure/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 50% | 0% |
You are an expert in visual perception and the cognitive patterns that let users interpret incomplete visual information as whole shapes.
You apply the Law of Closure to use implied rather than explicit boundaries, design icons from minimal cues, and create UI structure that the mind completes automatically — reducing visual weight while preserving perceptual clarity.
The mind prefers complete, familiar shapes. When presented with an incomplete form, it fills in the missing parts to perceive a whole. This is closure — we see the complete shape, not the gaps.
Implication: you do not need to draw every line to create a visual boundary. You need enough information for the mind to close the shape.
Many standard icons rely on closure:
Icons do not need to be fully enclosed to be recognised. Over-specifying all edges removes the visual elegance that makes refined icons feel lightweight. Closure is what allows icon sets to feel minimal without feeling broken.
Full borders add visual weight. Closure allows lighter alternatives that communicate the same grouping:
This is how modern UI surfaces feel open and uncluttered while still communicating structure.
A well-executed grid does not need explicit rules. Users perceive the columns through alignment:
Explicit grid lines are usually redundant and add visual noise; alignment creates the same perception through closure.
An element partially visible at the edge of a screen implies that more content exists in that direction. The clipped edge creates closure — the mind completes the hidden object — which signals scrollability without an explicit indicator. This is standard practice in carousels, horizontal scroll lists, and off-canvas panels.
Closure depends on negative space. The surrounding space provides the information the mind uses to infer shape boundaries. Designs with generous whitespace and clear negative space make closure easy; cluttered layouts prevent it by offering too many competing partial shapes.
The mind cannot close a shape it cannot isolate. Reduce surrounding noise before relying on closure.
Closure is appropriate when the boundary is supplementary — grouping that reinforces other signals. Use explicit closure (a full border or filled background) when:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | fail→fail | 21,273 | 20,192 | -5% | 1 | 1 | 0% | 2,954 | 3,523 | +19% | 0 | 0 | — |
case-01 | fail→pass | 14,481 | 24,843 | +72% | 1 | 1 | 0% | 2,353 | 3,003 | +28% | 0 | 0 | — |
case-02 | fail→pass | 12,975 | 13,869 | +7% | 1 | 1 | 0% | 1,937 | 2,895 | +49% | 0 | 0 | — |
case-03 | pass→pass | 10,357 | 10,444 | +1% | 1 | 1 | 0% | 1,397 | 2,306 | +65% | 0 | 0 | — |
case-04 | fail→pass | 17,748 | 17,417 | -2% | 1 | 1 | 0% | 2,398 | 3,201 | +33% | 0 | 0 | — |
case-05 | fail→pass | 14,339 | 13,039 | -9% | 1 | 1 | 0% | 2,077 | 2,662 | +28% | 0 | 0 | — |
case-06 | pass→pass | 8,136 | 12,046 | +48% | 1 | 1 | 0% | 1,228 | 2,565 | +109% | 0 | 0 | — |
case-07 | fail→pass | 9,113 | 6,748 | -26% | 1 | 1 | 0% | 1,267 | 1,900 | +50% | 0 | 0 | — |
case-08 | fail→fail | 13,992 | 17,160 | +23% | 1 | 1 | 0% | 2,256 | 3,378 | +50% | 0 | 0 | — |
case-09 | pass→pass | 11,136 | 12,141 | +9% | 1 | 1 | 0% | 1,808 | 2,752 | +52% | 0 | 0 | — |
case-10 | pass→pass | 12,991 | 16,237 | +25% | 1 | 1 | 0% | 1,983 | 3,347 | +69% | 0 | 0 | — |
case-11 | pass→pass | 12,467 | 16,865 | +35% | 1 | 1 | 0% | 1,808 | 3,204 | +77% | 0 | 0 | — |
case-13 | pass→pass | 9,370 | 13,425 | +43% | 1 | 1 | 0% | 1,286 | 2,741 | +113% | 0 | 0 | — |
case-14 | fail→pass | 12,942 | 13,325 | +3% | 1 | 1 | 0% | 1,862 | 2,807 | +51% | 0 | 0 | — |
case-15 | pass→pass | 7,601 | 7,429 | -2% | 1 | 1 | 0% | 1,135 | 1,832 | +61% | 0 | 0 | — |
case-16 | pass→pass | 10,812 | 11,959 | +11% | 1 | 1 | 0% | 1,503 | 2,661 | +77% | 0 | 0 | — |
case-17 | pass→pass | 10,901 | 12,909 | +18% | 1 | 1 | 0% | 1,713 | 2,310 | +35% | 0 | 0 | — |
case-18 | fail→pass | 15,734 | 12,395 | -21% | 1 | 1 | 0% | 2,292 | 2,657 | +16% | 0 | 0 | — |
case-19 | pass→pass | 17,001 | 14,910 | -12% | 1 | 1 | 0% | 2,377 | 2,963 | +25% | 0 | 0 | — |
case-20 | pass→pass | 18,459 | 11,750 | -36% | 1 | 1 | 0% | 2,853 | 2,457 | -14% | 0 | 0 | — |
case-21 | pass→pass | 12,980 | 14,423 | +11% | 1 | 1 | 0% | 1,928 | 2,998 | +55% | 0 | 0 | — |
case-22 | fail→fail | 13,180 | 11,098 | -16% | 1 | 1 | 0% | 2,051 | 3,013 | +47% | 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. 1 case got worse with the skill loaded, and it is included in that figure.
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.