Results for “lucide-react”

Establishes or validates a canonical Icon wrapper component, size token scale, stroke weight conventions, and illustration usage standards for a project, creating src/components/ui/icon.tsx and documenting the system.

Implements Apple's Liquid Glass design system for iOS 26 apps, covering SwiftUI, UIKit, and WidgetKit integration with glass effects, morphing transitions, and customization.

Implement Apple's Liquid Glass design system for iOS 26+ with dynamic glass materials, blur, reflection, and interactive morphing in SwiftUI, UIKit, and WidgetKit.

Action (adaz-action)

iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI, UIKit, and WidgetKit.

Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via helper script.

Action (ajaz-action)

iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI, UIKit, and WidgetKit.

Add and tune animated liquid-metal WebGL borders with the React `metal-fx` package. Use when buttons, icon controls, chips, tabs, cards, or selected surfaces need a metallic active, selected, hover, focus, or premium border; when implementing the MetalFx component from metal.jakubantalik.com; or when troubleshooting its presets, themes, strength, glow, reflections, sizing, radius, animation, accessibility, SSR, or performance.

当遇到令人情绪激动或陷入僵局的情境，需要跳出固有反应模式以做出更优决策时

Action (axaz-action)

Minimal, unopinionated state management library for React with simple hook-based API, no providers, and minimal boilerplate for global state without Redux complexity.

Converts Stitch designs into modular Vite and React components, or syncs existing components to match updated designs.

Action (araz-action)

Conversão pixel-perfeita de Figma para React usando coderio. Gera código pronto para produção (TypeScript, Vite, TailwindCSS V4) com alta fidelidade visual. Inclui tratamento robusto de erros, recuperação de checkpoints e execução simplificada via script auxiliar.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

融合未来蓝图与虚空凝视能力，通过批判性思维构建未来愿景，突破传统界限，创造新的未来可能性。

Converts Stitch screen designs into production React components, fetching and caching assets locally, extracting design tokens, and archiving existing pages before replacement.

Conduz investigação de incidentes com método: triagem, hipóteses, mitigação, RCA e postmortem, priorizando evidências e confirmação humana.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Prompting paradigm combining reasoning traces with actions for LLM agents to interact with external tools

Converts Stitch designs into modular Vite and React components, or syncs/updates existing React components to align with the latest Stitch designs, using system-level networking and AST-based validation.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Logic (adao-logic)

Action (akaz-action)

Action (aqaz-action)

Migrates a Stitch screen to production React: fetches and caches wireframes, archives existing pages, converts to shadcn/ui components with semantic tokens, and documents the design system layers.

Action (avaz-action)

Build accessible React interfaces with Chakra UI, covering theming, responsive styles, color mode, and component composition.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Radix UI unstyled accessible React components. Headless primitives. USE WHEN: user mentions "Radix", "Radix UI", "headless components", "unstyled primitives", asks about "accessible components", "Radix primitives" DO NOT USE FOR: shadcn/ui (use shadcn-ui skill), styled component libraries (Material-UI, Chakra), Vue/Svelte (use Headless UI)

Refines overly bold or aggressive designs into a calmer, more sophisticated aesthetic while preserving effectiveness and usability.