CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/xcuitest-suite

Use whenever an iOS, iPadOS, tvOS or macOS app needs UI tests in Apple's XCUITest: XCUIApplication, XCUIElement and queries, accessibility identifiers in app code, xcodebuild test with a destination, and reading the xcresult bundle, plus macOS specifics such as privacy permission resets.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

86%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 high-quality, actionable skill body: an 8-step workflow carried by executable code, a useful anti-patterns table, and exemplary progressive disclosure with the macOS delta moved to a real, one-level-deep reference file. The main improvements are isolating time-sensitive version specifics and adding an explicit post-run results-validation step.

Suggestions

Move version-sensitive specifics (device names like "iPhone 15", "OS=17.4", "macos-15", "actions/checkout@v5") into a dedicated, clearly-dated section or the macOS reference so they can be updated in one place as they drift.

Add an explicit validation step after Step 6/7, e.g., check the xcresulttool summary for failed tests and treat any failure as a stop-and-diagnose checkpoint before uploading or reporting.

Trim the repeated Apple-doc block quotes in Overview and Step 1 to single-line citations; the guidance is already restated in the body's own words.

DimensionReasoningScore

Conciseness

The body is code-forward and assumes competence, but includes minor trimmable material (repeated Apple-doc block quotes) and time-sensitive version references ("iPhone 15, OS=17.4", "macos-15", "actions/checkout@v5") that are not isolated in a deprecated/old-patterns section. This sits at anchor 4: efficient with minor instances that could be trimmed, and clearly above anchor 3 since no basic concepts are over-explained.

4 / 5

Actionability

Nearly every section gives copy-paste-ready material: complete Swift snippets for setUp, identifiers, queries, events and assertions; a full xcodebuild command; an xcresulttool invocation; a GitHub Actions workflow; plus a destination table and an anti-pattern table with concrete fixes. This matches the fully-executable, common-cases-covered anchor.

5 / 5

Workflow Clarity

Steps 1-8 form a clear, logically ordered sequence (target → identifiers → query → events → assert → run → parse → CI) with waitForExistence guidance as an async checkpoint. It falls short of anchor 5 only because there is no explicit post-run validation loop (e.g., inspect the xcresult summary and act on failures); it is above anchor 3 since sequence and most checkpoints are present and no destructive/batch cap applies.

4 / 5

Progressive Disclosure

The SKILL.md is a well-sectioned overview, and the macOS-specific delta is correctly split into references/macos.md — verified to exist, one level deep (it links only back to SKILL.md and external Apple/Jamf docs), and clearly signaled both in the body's macOS section and the References list. This matches the clear-overview, well-signaled one-level-deep-references anchor.

5 / 5

Total

18

/

20

Passed

Description

92%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 strong description: third-person, dense with concrete capabilities, and led by an explicit "Use whenever" trigger covering all Apple platforms. The only minor gap is a few missing natural synonyms (e.g., "Xcode", "simulator") that would make triggering even more reliable.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions spanning the full workflow: "XCUIApplication, XCUIElement and queries", "accessibility identifiers in app code", "xcodebuild test with a destination", "reading the xcresult bundle", and "privacy permission resets". This matches the comprehensive-coverage anchor; it is not a 4 because no meaningful part of the skill's scope is missing.

5 / 5

Completeness

It opens with an explicit trigger clause ("Use whenever an iOS, iPadOS, tvOS or macOS app needs UI tests in Apple's XCUITest") and follows with a concrete what-list of capabilities. Both what and when are explicitly answered with concrete trigger phrases, matching the top anchor; a 4 would require the when to be less explicit.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: "iOS, iPadOS, tvOS or macOS app needs UI tests", "XCUITest", "xcresult". A few natural synonyms ("Xcode", "simulator", "UI automation") are absent, so it falls just short of the comprehensive-synonyms anchor at 5 while clearly exceeding anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

"Apple's XCUITest" scoped to iOS/iPadOS/tvOS/macOS defines a clear niche with distinct triggers, minimizing overlap with cross-platform alternatives like Appium or Detox. It is not a 4 because the platform list and framework name pin it unambiguously to one skill.

5 / 5

Total

19

/

20

Passed

Validation

100%

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.

Reviewed

On this page