CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/unreal-automation-system

Author and run Unreal Engine's Automation Test Framework - Epic's C++ test framework for UE 4.x / 5.x, documented at dev.epicgames.com/documentation/en-us/unreal-engine. Covers the five test categories Epic defines (Unit / Feature / Smoke / Content Stress / Screenshot Comparison), the IMPLEMENT_SIMPLE_AUTOMATION_TEST and IMPLEMENT_COMPLEX_AUTOMATION_TEST macros, the BDD-style Automation Spec API (DEFINE_SPEC / BEGIN_DEFINE_SPEC / Describe / It / BeforeEach / LatentIt / xIt), latent commands (ADD_LATENT_AUTOMATION_COMMAND), the Automation Driver for UI input simulation (IAutomationDriverModule::Get().CreateDriver(), By::Id / By::Path locators), running via Session Frontend (Window > Test Automation) and command line (-ExecCmds="Automation RunTests …"), and CI integration. Use when the unit under test is C++ Unreal code that needs the UE runtime, editor, or UMG UI surface.

75

Quality

94%

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

92%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 well-structured decision-surface document: actionable, correctly progressive (full code lives in two real, one-level-deep reference files), and sequenced with explicit report-parsing validation and CI gating. The only trim opportunity is the verbatim repetition of the three Epic doc URLs throughout the anti-patterns table and body, which could be consolidated into the References section.

DimensionReasoningScore

Conciseness

The body is dense with UE-specific signal Claude does not already know (flags, application contexts, .spec.cpp convention, GameThread restriction) with no generic concept padding, but the same three Epic doc URLs are repeated verbatim roughly sixteen times - each anti-pattern row carries a full URL - and the reference-file links repeat about seven times. These are minor trimmable instances, not systemic verbosity.

4 / 5

Actionability

Provides a copy-paste-ready headless command (UnrealEditor-Cmd.exe ... -ExecCmds="Automation RunTests ...; Quit" -unattended -nopause -testexit=... -ReportOutputPath=...), exact flag combinations (ProductFilter | ApplicationContextMask), concrete naming conventions (dot-separated test paths, .spec.cpp suffix), and a fully concrete worked example covering category choice through CI gating.

5 / 5

Workflow Clarity

A six-step numbered workflow (pick category, pick style, name path, run in-editor, parse report, split CI matrix) with an explicit validation checkpoint - 'treat any "state": "Fail" as a failed build' - plus the iterate-in-editor-then-headless progression and an anti-patterns table acting as a checklist; the worked example closes the loop with the CI gate step.

5 / 5

Progressive Disclosure

The body explicitly declares itself 'the decision surface' and both referenced files (references/authoring-macros-and-apis.md, references/running-and-reporting.md) exist, are one level deep, topically split (authoring code vs. running/reporting/CI), and are clearly signaled at each point of need. Navigation is easy with no content that belongs in a reference inlined in the spine.

5 / 5

Total

19

/

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 dense, highly specific description that names the framework, its authoring surfaces, and its execution paths, with an explicit and concrete 'Use when' clause. Its only weakness is mild: a few common user phrasings (bare UE4/UE5, 'write tests', Gauntlet) are not present in the description text itself.

DimensionReasoningScore

Specificity

Enumerates multiple named concrete capabilities - IMPLEMENT_SIMPLE_AUTOMATION_TEST / IMPLEMENT_COMPLEX_AUTOMATION_TEST macros, the Spec API symbols (DEFINE_SPEC, Describe / It / LatentIt), ADD_LATENT_AUTOMATION_COMMAND, the Driver entry point (IAutomationDriverModule::Get().CreateDriver(), By::Id / By::Path), Session Frontend, the -ExecCmds command line, and CI integration - with no coverage gaps, matching the comprehensive anchor.

5 / 5

Completeness

Explicitly answers both: what ("Author and run Unreal Engine's Automation Test Framework... Covers the five test categories...") and when ("Use when the unit under test is C++ Unreal code that needs the UE runtime, editor, or UMG UI surface") - a concrete, specific trigger clause rather than an implied one.

5 / 5

Trigger Term Quality

Strong natural terms ("Unreal Engine", "Automation Test Framework", "Automation Spec", "Automation Driver", "Session Frontend", "C++", "CI", "UE 4.x / 5.x"), but a few natural variations users would actually say are absent from the description itself - bare "UE4"/"UE5" tokens, "write tests", and "Gauntlet" (which appears only in metadata keywords).

4 / 5

Distinctiveness Conflict Risk

A clear Unreal-specific niche defined by Epic-exclusive terms (Session Frontend, UMG, UnrealEditor-Cmd.exe, EAutomationTestFlags categories) with distinct triggers and minimal risk of firing for the wrong 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

Table of Contents