Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing stylesheets, component styles, and responsive behavior related to Use CSS Grid for two-dimensional layouts. Check the rendered layout across breakpoints and interaction states before proposing a fix.
.claude/skills/thedaviddias-css-grid/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 16% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 35% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 19% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | -14% | 0% |
CSS Grid solves layout problems that previously required JavaScript or complex CSS hacks — aligning items across both axes simultaneously, creating named layout areas, and building responsive grids that adapt to content. Using Flexbox for two-dimensional layouts results in workarounds like fixed widths that break responsiveness.
Look for float-based or Flexbox layouts in this CSS that are trying to control both rows and columns — they may be better implemented with CSS Grid.
Convert this two-dimensional layout to use CSS Grid with appropriate grid-template-columns, grid-template-rows, and grid-template-areas.
Explain CSS Grid fundamentals: tracks, cells, areas, fr units, minmax, and auto-fill vs auto-fit.
Review stylesheets, component styles, and responsive states related to Use CSS Grid for two-dimensional layouts. Flag exact selectors, declarations, or breakpoints that violate the rule in the rendered UI.
For full implementation details, code examples, and framework-specific guidance, see references/rule.md.
Rule page: https://frontendchecklist.io/en/rules/css/css-grid
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 2,000 | 5,106 | +155% | 1 | 1 | 0% | 358 | 1,244 | +247% | 0 | 0 | — |
case-02 | fail→fail | 8,980 | 7,811 | -13% | 1 | 1 | 0% | 2,207 | 2,233 | +1% | 0 | 0 | — |
case-03 | fail→pass | 14,433 | 8,352 | -42% | 1 | 1 | 0% | 2,952 | 2,119 | -28% | 0 | 0 | — |
case-04 | pass→fail | 6,342 | 6,358 | +0% | 1 | 1 | 0% | 1,469 | 1,697 | +16% | 0 | 0 | — |
case-05 | pass→pass | 4,011 | 4,044 | +1% | 1 | 1 | 0% | 781 | 1,051 | +35% | 0 | 0 | — |
case-06 | pass→pass | 9,920 | 8,729 | -12% | 1 | 1 | 0% | 1,907 | 2,262 | +19% | 0 | 0 | — |
case-07 | pass→pass | 10,522 | 7,191 | -32% | 1 | 1 | 0% | 2,145 | 1,834 | -14% | 0 | 0 | — |
case-08 | pass→pass | 4,850 | 5,090 | +5% | 1 | 1 | 0% | 1,084 | 1,303 | +20% | 0 | 0 | — |
case-09 | pass→pass | 4,045 | 4,672 | +16% | 1 | 1 | 0% | 738 | 1,195 | +62% | 0 | 0 | — |
case-10 | pass→pass | 6,680 | 4,913 | -26% | 1 | 1 | 0% | 1,392 | 1,325 | -5% | 0 | 0 | — |
case-11 | pass→pass | 5,227 | 5,364 | +3% | 1 | 1 | 0% | 1,152 | 1,452 | +26% | 0 | 0 | — |
case-12 | pass→pass | 7,817 | 6,571 | -16% | 1 | 1 | 0% | 1,558 | 1,622 | +4% | 0 | 0 | — |
case-13 | pass→pass | 10,842 | 9,245 | -15% | 1 | 1 | 0% | 2,118 | 2,245 | +6% | 0 | 0 | — |
case-14 | pass→pass | 7,477 | 6,828 | -9% | 1 | 1 | 0% | 1,504 | 1,818 | +21% | 0 | 0 | — |
case-15 | pass→pass | 9,574 | 6,791 | -29% | 1 | 1 | 0% | 2,046 | 1,682 | -18% | 0 | 0 | — |
case-16 | fail→fail | 5,908 | 3,747 | -37% | 1 | 1 | 0% | 1,362 | 1,227 | -10% | 0 | 0 | — |
case-17 | pass→pass | 9,569 | 7,414 | -23% | 1 | 1 | 0% | 2,002 | 1,912 | -4% | 0 | 0 | — |
case-18 | pass→pass | 8,107 | 6,066 | -25% | 1 | 1 | 0% | 1,643 | 1,522 | -7% | 0 | 0 | — |
case-19 | pass→pass | 10,699 | 6,139 | -43% | 1 | 1 | 0% | 2,196 | 1,732 | -21% | 0 | 0 | — |
case-20 | pass→pass | 7,175 | 7,369 | +3% | 1 | 1 | 0% | 1,528 | 1,834 | +20% | 0 | 0 | — |
case-21 | pass→pass | 16,593 | 16,424 | -1% | 1 | 1 | 0% | 3,564 | 3,896 | +9% | 0 | 0 | — |
case-22 | pass→pass | 8,061 | 7,974 | -1% | 1 | 1 | 0% | 1,700 | 1,988 | +17% | 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 0 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.