Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Guidelines for modern Avalonia UI layout using Zafiro.Avalonia, emphasizing shared styles, generic components, and avoiding XAML redundancy.
.claude/skills/davila7-avalonia-layout-zafiro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -19% | 0% |
> Master modern, clean, and maintainable Avalonia UI layouts. > Focus on semantic containers, shared styles, and minimal XAML.
Read ONLY files relevant to the layout challenge!
| File | Description | When to Read | |------|-------------|--------------| | themes.md | Theme organization and shared styles | Setting up or refining app themes | | containers.md | Semantic containers (HeaderedContainer, EdgePanel, Card) | Structuring views and layouts | | icons.md | Icon usage with IconExtension and IconOptions | Adding and customizing icons | | behaviors.md | Xaml.Interaction.Behaviors and avoiding Converters | Implementing complex interactions | | components.md | Generic components and avoiding nesting | Creating reusable UI elements |
For a real-world example, refer to the Angor project: /mnt/fast/Repos/angor/src/Angor/Avalonia/Angor.Avalonia.sln
HeaderedContainer instead of Border with manual header)axaml files.EdgePanel or generic components.{Icon fa-name} and IconOptions for styling.Interaction.Behaviors for UI-logic.DON'T:
Grid and StackPanel.IValueConverter for simple logic that belongs in the ViewModel.DO:
DynamicResource for colors and brushes.Zafiro.Avalonia specific panels like EdgePanel for common UI patterns.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,795 | 8,311 | -30% | 1 | 1 | 0% | 2,369 | 2,286 | -4% | 0 | 0 | — |
case-02 | fail→pass | 12,891 | 13,452 | +4% | 1 | 1 | 0% | 2,834 | 3,535 | +25% | 0 | 0 | — |
case-03 | fail→fail | 24,434 | 15,275 | -37% | 1 | 1 | 0% | 5,360 | 3,756 | -30% | 0 | 0 | — |
case-04 | pass→pass | 11,935 | 6,912 | -42% | 1 | 1 | 0% | 2,508 | 1,836 | -27% | 0 | 0 | — |
case-05 | pass→pass | 13,309 | 7,962 | -40% | 1 | 1 | 0% | 2,794 | 2,095 | -25% | 0 | 0 | — |
case-06 | pass→pass | 19,553 | 13,809 | -29% | 1 | 1 | 0% | 4,454 | 3,899 | -12% | 0 | 0 | — |
case-07 | pass→fail | 11,745 | 5,622 | -52% | 1 | 1 | 0% | 2,178 | 1,552 | -29% | 0 | 0 | — |
case-08 | fail→pass | 10,014 | 8,462 | -15% | 1 | 1 | 0% | 1,896 | 2,226 | +17% | 0 | 0 | — |
case-09 | fail→fail | 13,711 | 4,875 | -64% | 1 | 1 | 0% | 3,028 | 1,418 | -53% | 0 | 0 | — |
case-10 | pass→pass | 13,462 | 6,547 | -51% | 1 | 1 | 0% | 2,582 | 1,837 | -29% | 0 | 0 | — |
case-11 | pass→pass | 11,949 | 9,266 | -22% | 1 | 1 | 0% | 2,443 | 2,421 | -1% | 0 | 0 | — |
case-12 | pass→pass | 10,995 | 10,290 | -6% | 1 | 1 | 0% | 1,974 | 2,303 | +17% | 0 | 0 | — |
case-13 | pass→pass | 11,864 | 9,147 | -23% | 1 | 1 | 0% | 2,232 | 2,215 | -1% | 0 | 0 | — |
case-14 | pass→pass | 14,874 | 9,509 | -36% | 1 | 1 | 0% | 3,008 | 2,216 | -26% | 0 | 0 | — |
case-15 | fail→pass | 12,747 | 2,243 | -82% | 1 | 1 | 0% | 2,085 | 892 | -57% | 0 | 0 | — |
case-16 | fail→pass | 8,587 | 1,349 | -84% | 1 | 1 | 0% | 1,674 | 778 | -54% | 0 | 0 | — |
case-17 | pass→pass | 7,127 | 1,261 | -82% | 1 | 1 | 0% | 1,374 | 784 | -43% | 0 | 0 | — |
case-18 | pass→pass | 10,067 | 1,442 | -86% | 1 | 1 | 0% | 1,879 | 831 | -56% | 0 | 0 | — |
case-19 | pass→pass | 10,791 | 1,819 | -83% | 1 | 1 | 0% | 2,033 | 811 | -60% | 0 | 0 | — |
case-20 | fail→fail | 12,939 | 1,609 | -88% | 1 | 1 | 0% | 2,467 | 805 | -67% | 0 | 0 | — |
case-21 | fail→pass | 11,431 | 6,855 | -40% | 1 | 1 | 0% | 2,231 | 1,802 | -19% | 0 | 0 | — |
case-22 | pass→pass | 6,323 | 3,167 | -50% | 1 | 1 | 0% | 1,192 | 1,170 | -2% | 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 +18 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.