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

76%

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

75%Weight 40%Scale 1-5

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

A highly actionable, well-structured skill body with executable commands, real bundled-script references, and useful troubleshooting feedback loops. Its main weakness is redundancy across the Scripts/Examples/Filtering sections and the absence of an explicit post-run validation checkpoint.

Suggestions

Consolidate the largely duplicated command lists in 'Scripts' and 'Examples' into a single section to remove redundancy and improve token efficiency.

Add an explicit post-run verification step in the Workflow (e.g., check the xUnit result summary in artifacts/log and confirm pass count before declaring success).

Move the detailed xharness invocation reference and the full category list into a separate reference file linked from SKILL.md to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no padding about what MAUI or xharness is), but the same invocations are repeated across the 'Scripts', 'Examples', and 'Test Filtering' sections, and the 'Examples' section largely duplicates 'Scripts'; this redundant verbosity fits the 'mostly efficient but could be tightened' anchor rather than a 4.	3 / 5
Actionability	It provides copy-paste-ready, fully executable pwsh/xharness commands with real parameter values verified against the bundled Run-DeviceTests.ps1 (Project, Platform, iOSVersion, TestFilter, BuildOnly, SkipXcodeVersionCheck all exist), plus concrete xharness invocation examples and troubleshooting commands, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	The Workflow section gives a clear two-step sequence and the Troubleshooting/Test Filtering sections supply feedback loops (rebuild, check console output, verify category), aligning with 'clear sequence with most checkpoints present'; it is not a 5 because there is no explicit pass/fail verification checkpoint after a test run before declaring success.	4 / 5
Progressive Disclosure	Structure is good with clear section headers and references to real bundle files one level deep (Run-DeviceTests.ps1, Start-Emulator.ps1, shared-utils.ps1) plus inline source paths; however most detail (full xharness invocations, filter syntax, category lists) is inlined in SKILL.md rather than split into separate reference files, so it sits at 'good structure; minor organization gaps' rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

78%Weight 40%Scale 1-5

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

A specific, well-targeted description that names the domain, concrete actions, and supported platforms with a usage cue around TestFilter. The main gap is the absence of an explicit 'Use when...' trigger clause, which prevents a top completeness score.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when the user asks to run MAUI device/UI tests on iOS, MacCatalyst, Android, or Windows, or to run only specific test categories').

Include a few common synonyms ('UI tests', 'emulator/simulator tests') to broaden natural trigger term coverage.

Optionally name the available test projects (Controls/Core/Essentials/Graphics) in the description to strengthen capability specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('.NET MAUI device tests') and several concrete capabilities — 'Build and run', 'category filtering', listing supported platforms per host OS — which matches the 'lists several specific actions; minor gaps' anchor; it does not enumerate the individual test projects or the full parameter set, keeping it just short of a 5.	4 / 5
Completeness	It clearly answers 'what' (build and run device tests with category filtering) and supplies a 'when'-style cue via 'Use TestFilter to run specific test categories', but there is no explicit 'Use when...' clause, so by the guideline a missing explicit trigger clause caps completeness at 3 — nudged to 4 only because the TestFilter usage hint functions as concrete trigger guidance.	4 / 5
Trigger Term Quality	Includes natural user-facing terms like 'device tests', 'category filtering', platform names ('iOS, MacCatalyst, Android', 'Windows'), and 'TestFilter', giving good keyword coverage; it lacks common synonyms users might say ('run UI tests', 'emulator tests') so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The '.NET MAUI device tests' niche with per-OS platform support is highly specific and unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor; it is clearly not a 4 because nothing about it overlaps meaningfully with general build/test skills.	5 / 5
	Total	17 / 20 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: 90afade

Reviewed: ~18 hours 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.