Havuz

面向 AI Agent 的 HarmonyOS / ArkUI 设计与动效 Skill、规则库与评测基线 · Design & motion Skills, rule library and evaluation baseline for HarmonyOS / OpenHarm

A zero-dependency WCAG 2.2 accessibility audit engine, written from the W3C specifications. Runs entirely in the browser and reports what it

划词即理解的 AI 阅读工具 — Select text anywhere on macOS or windows system and get instant AI translate / explain / summarize in a floating bar. Tauri

A calm, visual recipe finder with search, favorites, meal planning, pantry inventory, shopping lists, and price estimates.

Wrap your React app in <A11yer> and accessibility is automatically handled.

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strate

Accessible, source-owned flag components for shadcn/ui.

Open-source design-system drift scanner — audit tokens, components, a11y & docs; score adoption; hand fixes to your coding agent. Local-firs

Semantic HTML component library for React and Web Components

Headless + styled UI components for Vue-Lynx — build native iOS, Android & web apps from one Vue codebase. Radix/Reka-style primitives, a st

Baseline-aware modern CSS Agent Skill: small SKILL.md router + on-demand references. Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCo

A skill graph for design engineering: animation, transitions, taste, typography, color, components, anti-patterns.

Guided product tours and onboarding walkthroughs for React, Vue, Solid, Angular and vanilla JS. Accessible, SSR-verified, zero dependencies.

A free, fully local, minimal-setup voice dictation app for macOS - built specifically for developers.

The open-source Liquid Glass UI system for React and the web. 40 accessible components, CSS-first glass materials, zero runtime dependencies

A SwiftUI design system: 54 components, 5 theme presets (10 light/dark themes), 39 style protocols with 115 built-in styles, plus popups, to

Zero-dependency lightbox for images, video, iframes & custom renderers. Native View Transitions morph, WCAG 2.2 AA, hooks + plugins, control

Design CLI for Claude Code, Codex and Antigravity: describe the UI in plain words, get production-grade web, Figma and SwiftUI output throug

Open-source desktop AI agent that sees what you see — one hotkey over any window, it answers, acts, or guides you step-by-step.

BCI-assisted neurodivergent productivity suite — self-reported or EEG-driven cognitive metrics + an agentic AI task planner (Claude) that ad

AI-agent skill for creating, auditing, and maintaining Penpot design systems, prototypes, tokens, and design-to-code workflows via the offic

Anti-AI Slop UI/UX steering skills — filter, palette, and research tool for Kiro, Claude Code, Cursor, Windsurf, Copilot, and more. Build in

Focused Agent Skills for complete Flutter and Dart app delivery, based on real-world projects.

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Persian-first UI/UX intelligence and RTL audit CLI for AI coding assistants

Material Design 3 component library on web standards — 56+ components for React, Angular, Vue, Svelte, or plain HTML. WCAG 2.1 AA, SSR, them

Debug-only in-app MCP server for iOS/macOS/Android/Flutter/ReactNative. Gives LLM agents Playwright-like control over native apps — UI, stat

The open-source Claude skill for UI/UX design. 84 UI styles, 192 color palettes, 74 font pairings, 99 UX guidelines & 161 industry rules acr

Machine-enforced frontend UI/UX skill pack for AI agents. Registry + lazy loading: a 2,154-token router loads one skill per request out of 4

Elegant, themeable, accessible components for SolidJS.

BALDR-accessibility-scan est un outil d'audit d'accessibilité numérique conçu pour évaluer la conformité des sites web aux référentiels RGAA

Open-source dotted maps and animated 3D globes for designers. 21 looks, PNG, SVG, GLB, WebM, MP4 and GIF export, embeds, a React component,

Accessible Angular 22 UI library (standalone, signals, zoneless, SSR) ported from BlatUI — 155 components, 16 blocks, 70 charts, 34 template

Source-preserving mixed RTL/LTR text for AI chat, Markdown, web and Android. Per-block direction, inline isolation, streaming and bidi-contr

Open-source Chrome and Firefox extension for readable mixed Arabic and English text.

Open-source Android AI chat, on-device agent, local models, Live2D, Skills, MCP, and Vibe Coding

AI-powered dyslexia intervention platform — adaptive reading exercises that adjust to each learner's specific decoding errors.

MCP server for production-grade UI and brand design — 37 tools: anti-slop quality gates, OKLCH tokens with auto dark mode, WCAG 2.1 audits,

🔢 Live-formatting React number input — headless, i18n-first (Persian ۱۲۳, Arabic ١٢٣…), WAI-ARIA spinbutton, ~2.2 KB core

A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambigui

🧠 The UI's brain in a state machine. Write once, run it on any JS runtime.

Agent-native creative progress bar toolkit with Gallery, CLI, Skill, and MCP integration.

Pure-Rust native GUI framework with web-grade aesthetics and first-class headless PNG rendering — winit + wgpu + vello + parley + taffy

Agent-ready CLI for static page inspection, search triage, and browser handoff.

AI-powered English learning assistant for Chinese elderly users, with RAG, ReAct Agent, two-stage retrieval, and 5-dim evaluation framew

前端工程视觉与色彩全栈守卫：静态配色校验、渲染后视觉计量、证据驱动的 UI 评审闭环与规则演进治理。A full-lifecycle frontend visual guard: static contrast checks, post-render metrics, evide