Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Comprehensive best practices for React Native and Expo applications. Contains rules across multiple categories covering performance, animations, UI patterns, and platform-specific optimizations.
Reference these guidelines when:
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | List Performance | CRITICAL | list-performance- |
| 2 | Animation | HIGH | animation- |
| 3 | Navigation | HIGH | navigation- |
| 4 | UI Patterns | HIGH | ui- |
| 5 | State Management | MEDIUM | react-state- |
| 6 | Rendering | MEDIUM | rendering- |
| 7 | Monorepo | MEDIUM | monorepo- |
| 8 | Configuration | LOW | fonts-, imports- |
list-performance-virtualize - Use FlashList for large listslist-performance-item-memo - Memoize list item componentslist-performance-callbacks - Stabilize callback referenceslist-performance-inline-objects - Avoid inline style objectslist-performance-function-references - Extract functions outside renderlist-performance-images - Optimize images in listslist-performance-item-expensive - Move expensive work outside itemslist-performance-item-types - Use item types for heterogeneous listsanimation-gpu-properties - Animate only transform and opacityanimation-derived-value - Use useDerivedValue for computed animationsanimation-gesture-detector-press - Use Gesture.Tap instead of Pressablenavigation-native-navigators - Use native stack and native tabs over JS navigatorsui-expo-image - Use expo-image for all imagesui-image-gallery - Use Galeria for image lightboxesui-pressable - Use Pressable over TouchableOpacityui-safe-area-scroll - Handle safe areas in ScrollViewsui-scrollview-content-inset - Use contentInset for headersui-menus - Use native context menusui-native-modals - Use native modals when possibleui-measure-views - Use onLayout, not measure()ui-styling - Use StyleSheet.create or Nativewindreact-state-minimize - Minimize state subscriptionsreact-state-dispatcher - Use dispatcher pattern for callbacksreact-state-fallback - Show fallback on first renderreact-compiler-destructure-functions - Destructure for React Compilerreact-compiler-reanimated-shared-values - Handle shared values with compilerrendering-text-in-text-component - Wrap text in Text componentsrendering-no-falsy-and - Avoid falsy && for conditional renderingmonorepo-native-deps-in-app - Keep native dependencies in app packagemonorepo-single-dependency-versions - Use single versions across packagesfonts-config-plugin - Use config plugins for custom fontsimports-design-system-folder - Organize design system importsjs-hoist-intl - Hoist Intl object creationRead individual rule files for detailed explanations and code examples:
rules/list-performance-virtualize.md
rules/animation-gpu-properties.md
Each rule file contains:
For the complete guide with all rules expanded: AGENTS.md
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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
中文简介正在准备中。当前显示原文说明。