run-device-tests

Build and run .NET MAUI device tests locally with category filtering. Supports iOS, MacCatalyst, Android on macOS; Android, Windows on Windows. Use TestFilter to run specific test categories.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/run-device-tests/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and good troubleshooting coverage, but it is padded by repeated command examples across sections and keeps implementation detail inline rather than offloading it to reference files, while the core workflow lacks an explicit validation gate.

Suggestions

Deduplicate the Run-DeviceTests.ps1 command examples shown in Scripts, Examples, Test Filtering, and XHarness — keep one canonical set and cross-reference it.

Add an explicit verification checkpoint to the Workflow section (e.g., confirm the test run completed and inspect artifacts/log/ for pass/fail counts before reporting success) so the batch operation has a validation gate.

Move the XHarness device-detection internals and per-platform filter-passing tables into a references/ file, keeping SKILL.md an overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and command-driven but repeats the same Run-DeviceTests.ps1 invocations across the Scripts, Examples, Test Filtering, and XHarness sections; tightening the duplicates would reach the level-3 lean anchor.	2 / 3
Actionability	Provides fully executable pwsh commands with real project paths, parameter values, and copy-paste-ready xharness invocations, matching the level-3 anchor for concrete executable guidance.	3 / 3
Workflow Clarity	The core two-step workflow (run script, check console/logs) lacks an explicit validation checkpoint, and because running device tests is a batch operation the judging guideline caps workflow_clarity at 2 even though the Troubleshooting section adds error-recovery loops.	2 / 3
Progressive Disclosure	The two bundle scripts in ./scripts/ are referenced with a clear path, but substantial detail (xharness internals, test-filter mechanics, device detection) is kept inline in SKILL.md with no references/ split, fitting the level-2 anchor of structure present but content that could be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming concrete build/run/filter actions across platforms, but it omits an explicit 'Use when...' trigger clause and leans on a parameter name (TestFilter) instead of natural user phrasings, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasings (e.g., 'Use when the user wants to run MAUI device tests on iOS/Android/MacCatalyst/Windows, or filter tests by category like Button or Shell').

Replace or supplement the parameter jargon 'TestFilter' with plain-language triggers users would actually say, such as 'run only Button tests' or 'skip heavy test categories'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Build and run .NET MAUI device tests locally with category filtering" plus per-platform support — matching the level-3 anchor of multiple specific concrete actions rather than the single-domain level-2 example.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes relevant terms ("device tests", "iOS", "Android", "Windows", "test categories") but leans on the parameter jargon "TestFilter" and omits common natural variations like "run Button tests" or "test on iOS simulator"; not the broad level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	The niche is specific (".NET MAUI device tests" on named platforms) with distinct triggers, making it unlikely to fire for unrelated skills; matches the level-3 clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dotnet/maui
Path: .github/skills/run-device-tests/SKILL.md
Commit: 6a24ec5

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.