Implement the Model-View-ViewModel pattern in .NET applications with proper separation of concerns, data binding, commands, and testable ViewModels using MVVM Toolkit. USE FOR: implementing UI separation with Model-View-ViewModel; using MVVM Toolkit (CommunityToolkit.Mvvm) for ViewModels; designing testable UI architecture. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build,
SkillScore91Maintained
Automatic
◆Frontend / UI pack
Last verified 8/19/2026
What it changes
Passed 20 of 22 test cases with the skill, and 19 of 22 without it.
Without skill86%
With skill91%
Checks it passed that the model alone missed
Uses x:Bind syntax for data binding
Executes LoadCommand on the ViewModel instance
2 fixed18 passed either way1 still failing1 broke
Pass-rate lift
+5 pp
Tokens
+94%
Agent turns
0%
Response time
-27%
Model gemini-3.6-flashMeasured 8/19/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
Write a XAML snippet for a page displaying a list of products and a refresh button, using high-performance compiled bindings referencing a ProductListViewModel.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses x:Bind syntax for data binding
Missed
Passed
Binds button interaction to ViewModel command properties
Passed
Passed
case-10 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md371 lines3 files
MVVM Pattern for .NET
Trigger On
implementing UI separation with Model-View-ViewModel
using MVVM Toolkit (CommunityToolkit.Mvvm) for ViewModels
designing testable UI architecture
handling commands, property changes, and messaging
Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates, screenshot diff triage, or CI workflows for UI regression screenshots. DO NOT USE FOR: pure unit tests, accessibility audits, browser-debugging sessions, or frontend linting.