Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
NativeScript best practices and patterns for mobile applications
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
.ios.ts, .android.ts) when code exceeds 20 platform-specific lines.custom-native/index.ios.ts, custom-native/index.android.ts, custom-native/common.ts, custom-native/index.d.ts to keep platform-specific code organized and easy to import with single import elsewhere, replacing custom-native with the name of the custom code.ios or android (e.g., iosButtonStyle).primaryButtonStyle, userProfileView).@NativeClass() when extending native classes when neededstatic ObjCProtocols = [AnyUIKitDelegate]; to declare custom delegates if a delegate is required or used.let delegate = MyCustomDelegate.new() as MyCustomDelegate, and ensure it is retained in the class scope.__ANDROID__ and __APPLE__ for conditional platform code with tree-shaking.setTimeout, setInterval) to avoid memory leaks."@nativescript/tailwind": "^2.1.0" for consistent styling paired with "tailwindcss": "~3.4.0".GridLayout or StackLayout for flexible, responsive layouts. Place more emphasis on proper GridLayout usage for complex layouts but use StackLayout for simpler, linear arrangements.visibility: 'hidden' for elements that should not affect layout when hidden.GridLayout wisely to setup complex layouts.ns clean) after modifying files in App_Resources or package.json.itemTemplateSelector) for conditional layouts in ListView and RadListView.Observable or ObservableArray properties to reflect state changes efficiently..ios.ts, .android.ts) when platform code exceeds 20 lines — mixing platform branches in a single file prevents code-splitting and forces all native APIs to load on both platforms.| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Mixing platform branches in a single file | Cannot code-split by platform; all native APIs loaded on both platforms | Use .ios.ts and .android.ts files when platform-specific code exceeds 20 lines |
| Direct visual tree manipulation at runtime | Bypasses rendering pipeline; causes race conditions and layout flicker | Use data-binding and reactive state to drive layout updates |
| Unreferenced delegate instances | iOS GC collects them mid-execution; silent callback failures | Always retain delegates in class scope: this.delegate = MyDelegate.new() |
| Deeply nested layout containers | Each level adds layout passes; janky scrolling on mid-range devices | Use GridLayout for complex layouts; StackLayout only for simple linear arrangements |
| Leaking timers and event listeners | NativeScript does not GC native references; leaks accumulate across navigation | Always cancel timers and remove listeners in component teardown lifecycle |
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.