[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS5986ZJ268YQRNDSSHXKN":3,"skill-same:01M7CS5986ZJ268YQRNDSSHXKN":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CS5986ZJ268YQRNDSSHXKN","unreal-automation-testing",null,"Use when writing or running Unreal Engine tests - which test type fits (simple\u002Fcomplex automation tests, Automation Specs, functional tests, CQTest, Low-Level Tests, Gauntlet), naming and filters, latent tests, and the headless UnrealEditor-Cmd run with report export, exit handling and screenshot captures.","makifbaysal\u002Ftasktrooper","makifbaysal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25031940?v=4","01M7CRG3ZCSYZSSEVDMW3DEYC8","Mehmet Akif Baysal","01M7CRG401FJ8YAXH5ER730XYV",122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fgame-developer\u002Fskills\u002Funreal-automation-testing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: unreal-automation-testing\ncategory: testing\ndescription: Use when writing or running Unreal Engine tests - which test type fits (simple\u002Fcomplex automation tests, Automation Specs, functional tests, CQTest, Low-Level Tests, Gauntlet), naming and filters, latent tests, and the headless UnrealEditor-Cmd run with report export, exit handling and screenshot captures.\ntech_stack: Unreal Engine\nsource: informed by the Unreal Engine 5 Automation System, Automation Spec, Functional Testing and Gauntlet documentation; own wording\n---\n# Unreal Automation Testing\n\n## Overview\n\nUnreal's Automation System runs C++ tests inside the editor or a game process, from the Session Frontend or the command line. The fast, stable tests are plain C++ checks on rules and data; tests that need a world, actors and frames are slower and belong in functional test maps. Either way the run must be headless and its report read, because the editor's exit code alone is not a reliable verdict.\n\n**Core principle:** Rules tested as plain C++ in Automation Specs; world behaviour in functional tests; every run headless with a report you read.\n\n## Which test type\n\n| Question | Type |\n|---|---|\n| Does the damage formula \u002F inventory rule compute correctly? | Automation Spec or simple automation test |\n| Same check over many inputs | Complex automation test (`GetTests` + parameters) or a spec loop |\n| Does the door open when the player overlaps the trigger? | Functional test (`AFunctionalTest` in a test map) |\n| Readable fixtures and assertions in a newer codebase | CQTest (`TEST_CLASS`), if the project enabled the plugin |\n| Engine-free module code, fast native tests | Low-Level Tests (Catch2, `-Test` targets) |\n| Client\u002Fserver sessions, performance captures on devices | Gauntlet (via RunUAT) |\n\nFollow what the project already has. Without a convention, test names are dotted filters `\u003CProject>.\u003CSystem>.\u003CScenario>` and classes `F\u003CSystem>\u003CScenario>Test` \u002F `F\u003CSystem>Spec`.\n\n## Automation Spec\n\n```cpp\n#include \"Misc\u002FAutomationTest.h\"\n#include \"Combat\u002FDamageMath.h\"\n\nBEGIN_DEFINE_SPEC(FDamageMathSpec, \"Hero.Combat.DamageMath\",\n    EAutomationTestFlags::EditorContext | EAutomationTestFlags::ProductFilter)\n    FDamageInput Input;\nEND_DEFINE_SPEC(FDamageMathSpec)\n\nvoid FDamageMathSpec::Define() {\n    BeforeEach([this]() { Input = FDamageInput{ \u002F*Base*\u002F 100.f, \u002F*Armor*\u002F 0.f, \u002F*bCritical*\u002F false }; });\n\n    Describe(\"Apply\", [this]() {\n        It(\"returns the base damage with no armor\", [this]() {\n            TestEqual(TEXT(\"damage\"), FDamageMath::Apply(Input), 100.f);\n        });\n        It(\"halves damage at 50% armor\", [this]() {\n            Input.Armor = 0.5f;\n            TestNearlyEqual(TEXT(\"damage\"), FDamageMath::Apply(Input), 50.f, 0.001f);\n        });\n        It(\"never goes below zero\", [this]() {\n            Input.Armor = 2.f;\n            TestTrue(TEXT(\"non-negative\"), FDamageMath::Apply(Input) >= 0.f);\n        });\n    });\n}\n```\n\nSimple form for a single check:\n\n```cpp\nIMPLEMENT_SIMPLE_AUTOMATION_TEST(FInventoryStackOverflowTest, \"Hero.Inventory.AddBeyondStack_OverflowsToNextSlot\",\n    EAutomationTestFlags::EditorContext | EAutomationTestFlags::ProductFilter)\nbool FInventoryStackOverflowTest::RunTest(const FString& Parameters) {\n    FInventoryModel Inventory(\u002F*Slots*\u002F 4);\n    Inventory.Add(TEXT(\"potion\"), 7, \u002F*MaxStack*\u002F 5);\n    TestEqual(TEXT(\"slot 0\"), Inventory.Slot(0).Count, 5);\n    TestEqual(TEXT(\"slot 1\"), Inventory.Slot(1).Count, 2);\n    return true;\n}\n```\n\n- Keep the flags the project already uses; newer engine versions renamed the context *mask* constants, so copy from an existing test rather than from memory.\n- Test plain C++ types (`FInventoryModel`, `FDamageMath`) — the reason to keep rules out of actors (testable-game-logic).\n- `AddExpectedError(TEXT(\"...\"))` when a test deliberately triggers a logged error; an unexpected error log fails the test.\n\n## Latent tests\n\nWhen something takes frames (async load, a timer, a physics settle), use `LatentIt` with a done delegate, or latent commands in simple tests:\n\n```cpp\nLatentIt(\"loads the boss definition asynchronously\", EAsyncExecution::TaskGraphMainThread, [this](const FDoneDelegate& Done) {\n    UAssetManager::GetStreamableManager().RequestAsyncLoad(BossPath, [this, Done]() {\n        TestNotNull(TEXT(\"loaded\"), BossPath.ResolveObject());\n        Done.Execute();\n    });\n});\n```\n\nEvery latent path calls `Done` — including failure — or the run hangs until the timeout.\n\n## Functional tests\n\n- A test map (`\u002FGame\u002FTests\u002FMaps\u002FFTEST_Doors.umap`) holding `AFunctionalTest` actors (or a C++ subclass) next to the setup they test.\n- Override `StartTest()`, drive the scenario, and finish with `FinishTest(EFunctionalTestResult::Succeeded, TEXT(\"door opened\"))` or `Failed`; set a time limit on the actor.\n- They appear in the automation tree under the project's functional tests group with the map path; filter by that prefix.\n\n## Running headless\n\n```sh\nUE=\"\u002FUsers\u002FShared\u002FEpic Games\u002FUE_5.6\"            # from EngineAssociation; Windows: C:\\Program Files\\Epic Games\\UE_5.6\nmkdir -p \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\n\"$UE\u002FEngine\u002FBuild\u002FBatchFiles\u002FMac\u002FBuild.sh\" \u003CProject>Editor Mac Development -Project=\"$PWD\u002F\u003CProject>.uproject\" -WaitMutex \\\n  > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fbuild.log 2>&1 || { echo BUILD FAILED; tail -50 \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fbuild.log; }\n\"$UE\u002FEngine\u002FBinaries\u002FMac\u002FUnrealEditor-Cmd\" \"$PWD\u002F\u003CProject>.uproject\" \\\n  -ExecCmds=\"Automation RunTests Hero.;Quit\" -TestExit=\"Automation Test Queue Empty\" \\\n  -unattended -nullrhi -nosplash -nosound -log -ReportExportPath=\"\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\" \\\n  > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-tests.log 2>&1; echo \"exit=$?\"\n```\n\n- Build the editor target first; with `-unattended` an out-of-date module does not prompt, it fails.\n- The filter after `RunTests` is a prefix (`Hero.` runs everything under it); `Automation RunAll` runs every test including engine ones — avoid it.\n- Read `\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\u002Findex.json` (succeeded\u002Ffailed counts and per-test errors) and grep the log for `Test Completed. Result={Fail}` — do not trust the exit code alone.\n- `-nullrhi` disables rendering. Screenshot or rendering tests need a real RHI: replace it with `-RenderOffscreen` (game-visual-self-review).\n- First runs on a project compile shaders and build the derived data cache; give the command a long timeout or run it detached to the log.\n\n## Gauntlet\n\nFor multi-process scenarios (dedicated server + clients, soak and performance runs) the project defines Gauntlet test nodes and runs them through RunUAT, e.g. `RunUAT.sh RunUnreal -project=\u003CProject> -build=\u003Cpath> -test=\u003CTestNode>`. Use what the repository's CI already runs; do not invent a Gauntlet setup inside a feature task.\n\n## No engine on this machine\n\nNothing Unreal compiles without the engine. Write the spec next to the existing tests, keep it small and obviously correct, and report: `NOT RUN: UE 5.6 not installed (EngineAssociation 5.6) — FDamageMathSpec written in Source\u002FHero\u002FTests\u002FDamageMathSpec.cpp`.\n\n## Common Mistakes\n\n- Testing a rule by spawning an actor in a map when a plain C++ test would do.\n- Running tests without building the editor target first.\n- Reading the exit code, not the report.\n- Latent tests that miss `Done` on a failure path.\n- `RunAll` in a project with thousands of engine tests.\n\n## Red Flags\n\n- A new gameplay rule with only a functional test.\n- Screenshot tests run with `-nullrhi`.\n- A closing message claiming Unreal tests passed with no report path or result counts.\n","# Unreal Automation Testing\n\n## Overview\n\nUnreal's Automation System runs C++ tests inside the editor or a game process, from the Session Frontend or the command line. The fast, stable tests are plain C++ checks on rules and data; tests that need a world, actors and frames are slower and belong in functional test maps. Either way the run must be headless and its report read, because the editor's exit code alone is not a reliable verdict.\n\n**Core principle:** Rules tested as plain C++ in Automation Specs; world behaviour in functional tests; every run headless with a report you read.\n\n## Which test type\n\n| Question | Type |\n|---|---|\n| Does the damage formula \u002F inventory rule compute correctly? | Automation Spec or simple automation test |\n| Same check over many inputs | Complex automation test (`GetTests` + parameters) or a spec loop |\n| Does the door open when the player overlaps the trigger? | Functional test (`AFunctionalTest` in a test map) |\n| Readable fixtures and assertions in a newer codebase | CQTest (`TEST_CLASS`), if the project enabled the plugin |\n| Engine-free module code, fast native tests | Low-Level Tests (Catch2, `-Test` targets) |\n| Client\u002Fserver sessions, performance captures on devices | Gauntlet (via RunUAT) |\n\nFollow what the project already has. Without a convention, test names are dotted filters `\u003CProject>.\u003CSystem>.\u003CScenario>` and classes `F\u003CSystem>\u003CScenario>Test` \u002F `F\u003CSystem>Spec`.\n\n## Automation Spec\n\n```cpp\n#include \"Misc\u002FAutomationTest.h\"\n#include \"Combat\u002FDamageMath.h\"\n\nBEGIN_DEFINE_SPEC(FDamageMathSpec, \"Hero.Combat.DamageMath\",\n    EAutomationTestFlags::EditorContext | EAutomationTestFlags::ProductFilter)\n    FDamageInput Input;\nEND_DEFINE_SPEC(FDamageMathSpec)\n\nvoid FDamageMathSpec::Define() {\n    BeforeEach([this]() { Input = FDamageInput{ \u002F*Base*\u002F 100.f, \u002F*Armor*\u002F 0.f, \u002F*bCritical*\u002F false }; });\n\n    Describe(\"Apply\", [this]() {\n        It(\"returns the base damage with no armor\", [this]() {\n            TestEqual(TEXT(\"damage\"), FDamageMath::Apply(Input), 100.f);\n        });\n        It(\"halves damage at 50% armor\", [this]() {\n            Input.Armor = 0.5f;\n            TestNearlyEqual(TEXT(\"damage\"), FDamageMath::Apply(Input), 50.f, 0.001f);\n        });\n        It(\"never goes below zero\", [this]() {\n            Input.Armor = 2.f;\n            TestTrue(TEXT(\"non-negative\"), FDamageMath::Apply(Input) >= 0.f);\n        });\n    });\n}\n```\n\nSimple form for a single check:\n\n```cpp\nIMPLEMENT_SIMPLE_AUTOMATION_TEST(FInventoryStackOverflowTest, \"Hero.Inventory.AddBeyondStack_OverflowsToNextSlot\",\n    EAutomationTestFlags::EditorContext | EAutomationTestFlags::ProductFilter)\nbool FInventoryStackOverflowTest::RunTest(const FString& Parameters) {\n    FInventoryModel Inventory(\u002F*Slots*\u002F 4);\n    Inventory.Add(TEXT(\"potion\"), 7, \u002F*MaxStack*\u002F 5);\n    TestEqual(TEXT(\"slot 0\"), Inventory.Slot(0).Count, 5);\n    TestEqual(TEXT(\"slot 1\"), Inventory.Slot(1).Count, 2);\n    return true;\n}\n```\n\n- Keep the flags the project already uses; newer engine versions renamed the context *mask* constants, so copy from an existing test rather than from memory.\n- Test plain C++ types (`FInventoryModel`, `FDamageMath`) — the reason to keep rules out of actors (testable-game-logic).\n- `AddExpectedError(TEXT(\"...\"))` when a test deliberately triggers a logged error; an unexpected error log fails the test.\n\n## Latent tests\n\nWhen something takes frames (async load, a timer, a physics settle), use `LatentIt` with a done delegate, or latent commands in simple tests:\n\n```cpp\nLatentIt(\"loads the boss definition asynchronously\", EAsyncExecution::TaskGraphMainThread, [this](const FDoneDelegate& Done) {\n    UAssetManager::GetStreamableManager().RequestAsyncLoad(BossPath, [this, Done]() {\n        TestNotNull(TEXT(\"loaded\"), BossPath.ResolveObject());\n        Done.Execute();\n    });\n});\n```\n\nEvery latent path calls `Done` — including failure — or the run hangs until the timeout.\n\n## Functional tests\n\n- A test map (`\u002FGame\u002FTests\u002FMaps\u002FFTEST_Doors.umap`) holding `AFunctionalTest` actors (or a C++ subclass) next to the setup they test.\n- Override `StartTest()`, drive the scenario, and finish with `FinishTest(EFunctionalTestResult::Succeeded, TEXT(\"door opened\"))` or `Failed`; set a time limit on the actor.\n- They appear in the automation tree under the project's functional tests group with the map path; filter by that prefix.\n\n## Running headless\n\n```sh\nUE=\"\u002FUsers\u002FShared\u002FEpic Games\u002FUE_5.6\"            # from EngineAssociation; Windows: C:\\Program Files\\Epic Games\\UE_5.6\nmkdir -p \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\n\"$UE\u002FEngine\u002FBuild\u002FBatchFiles\u002FMac\u002FBuild.sh\" \u003CProject>Editor Mac Development -Project=\"$PWD\u002F\u003CProject>.uproject\" -WaitMutex \\\n  > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fbuild.log 2>&1 || { echo BUILD FAILED; tail -50 \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fbuild.log; }\n\"$UE\u002FEngine\u002FBinaries\u002FMac\u002FUnrealEditor-Cmd\" \"$PWD\u002F\u003CProject>.uproject\" \\\n  -ExecCmds=\"Automation RunTests Hero.;Quit\" -TestExit=\"Automation Test Queue Empty\" \\\n  -unattended -nullrhi -nosplash -nosound -log -ReportExportPath=\"\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\" \\\n  > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-tests.log 2>&1; echo \"exit=$?\"\n```\n\n- Build the editor target first; with `-unattended` an out-of-date module does not prompt, it fails.\n- The filter after `RunTests` is a prefix (`Hero.` runs everything under it); `Automation RunAll` runs every test including engine ones — avoid it.\n- Read `\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fue-report\u002Findex.json` (succeeded\u002Ffailed counts and per-test errors) and grep the log for `Test Completed. Result={Fail}` — do not trust the exit code alone.\n- `-nullrhi` disables rendering. Screenshot or rendering tests need a real RHI: replace it with `-RenderOffscreen` (game-visual-self-review).\n- First runs on a project compile shaders and build the derived data cache; give the command a long timeout or run it detached to the log.\n\n## Gauntlet\n\nFor multi-process scenarios (dedicated server + clients, soak and performance runs) the project defines Gauntlet test nodes and runs them through RunUAT, e.g. `RunUAT.sh RunUnreal -project=\u003CProject> -build=\u003Cpath> -test=\u003CTestNode>`. Use what the repository's CI already runs; do not invent a Gauntlet setup inside a feature task.\n\n## No engine on this machine\n\nNothing Unreal compiles without the engine. Write the spec next to the existing tests, keep it small and obviously correct, and report: `NOT RUN: UE 5.6 not installed (EngineAssociation 5.6) — FDamageMathSpec written in Source\u002FHero\u002FTests\u002FDamageMathSpec.cpp`.\n\n## Common Mistakes\n\n- Testing a rule by spawning an actor in a map when a plain C++ test would do.\n- Running tests without building the editor target first.\n- Reading the exit code, not the report.\n- Latent tests that miss `Done` on a failure path.\n- `RunAll` in a project with thousands of engine tests.\n\n## Red Flags\n\n- A new gameplay rule with only a functional test.\n- Screenshot tests run with `-nullrhi`.\n- A closing message claiming Unreal tests passed with no report path or result counts.\n",{"name":5,"source":24,"category":25,"tech_stack":26,"description":7},"informed by the Unreal Engine 5 Automation System, Automation Spec, Functional Testing and Gauntlet documentation; own wording","testing","Unreal Engine","main","910394a0b6db9fc8c9a8f36328ec421d3ebd8b38","catalog\u002Fagents\u002Fgame-developer\u002Fskills\u002Funreal-automation-testing",18,"https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper","https:\u002F\u002Ftasktrooper.ai","https:\u002F\u002Fgithub.com\u002Fmakifbaysal","Senior Software Developer","2026-11-15 04:50:29",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add makifbaysal\u002Ftasktrooper --skill unreal-automation-testing",{"tool":42,"command":43},"bunx","bunx skills add makifbaysal\u002Ftasktrooper --skill unreal-automation-testing",{"tool":45,"command":46},"pnpm","pnpm dlx skills add makifbaysal\u002Ftasktrooper --skill unreal-automation-testing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fgame-developer\u002Fskills\u002Funreal-automation-testing\u002FSKILL.md",true,[],[51,57,64,71,78,85],{"skillNo":52,"name":53,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7CSVEPQW6J6TD6CS2T5FPNZ","visual-craft","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fvisual-craft\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7CSVAQG91ETHQ0HBNZDG5FR","ux-copy","Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fux-copy\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CSV6H0J38659NDXHJQ8396","screen-mockup-html","Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fscreen-mockup-html\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CSV3JFRF3BM3XK52M7YEYR","performance-awareness","How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fperformance-awareness\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CSTZDH00YRF5SCT7BRT9QD","design-variants","Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-variants\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CSTV6P3SM3PAE28DB0RF77","design-system-authoring","Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-system-authoring\u002FSKILL.md",[],[]]