73 boosters for "ux" — open source, verified from GitHub, ready to install
A senior full-stack developer agent specialized in premium web implementations using Laravel, Livewire, FluxUI, and Three.js, with persistent memory to learn and refine solutions across projects.
Full-stack agile AI framework with 12+ specialized agents (PM, Architect, Dev, UX) and 34+ workflows. Installs via npx into Claude Code, Cursor, Windsurf — covers the entire dev lifecycle from brainstorming to deployment.
The vocabulary you didn't know you needed. 1 skill, 20 commands, and curated anti-patterns for impeccable frontend design. Anthropic created frontend-design, a skill that guides Claude toward better UI design. Impeccable builds on that foundation with deeper expertise and more control. Every LLM lea
Clarify helps developers improve confusing UX copy, error messages, and interface labels by identifying and fixing clarity problems like jargon, ambiguity, and wordiness. It's essential for anyone building user-facing products who wants to enhance usability through better microcopy.
A UX-focused design critique skill that evaluates interface effectiveness across visual hierarchy, information architecture, and emotional resonance, providing actionable feedback. Useful for designers and developers seeking structured design feedback within Claude Code.
Build and publish a Gradio demo on Hugging Face Spaces that runs inference with a user-provided LoRA. Use whenever someone asks to create, generate, ship, or publish "a Space", "a demo", "a Gradio app", or "a playground" for a LoRA — whether the base model is Qwen-Image, Qwen-Image-Edit, LTX, or ano
</pythondocstrings> </testingpractices> <gitcommitstandards>
UnPoller is a Go application that collects metrics from UniFi network controllers and exports them to various backends (InfluxDB, Prometheus, Loki, DataDog). The architecture is plugin-based with input and output plugins. 1. Create new package in (e.g., ) 2. Implement interface from
Heuristic scoring (no AI key configured).
Focus on secure, robust, and efficient code. Refer to https://mywiki.wooledge.org for Bash best practices.
"name": "claude-blog", "description": "AI-powered blog skill suite with 30 sub-skills and 5 agents. FLOW framework integration (Find/Optimize/Win, 30 evidence-led prompts), semantic topic-cluster planning + execution, multilingual publishing (translate/localize/locale-audit), Google API integration
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "sentrux-marketplace", "description": "Sentrux — live codebase visualization and structural quality gate for AI-agent-written code",
A comprehensive system prompt for GitHub Copilot that establishes coding standards and best practices for the LINUX DO CDK project, covering backend (Go/REST/MySQL), frontend (TypeScript), and general development guidelines. Developers working on this project benefit from consistent, enforceable code quality standards.
Nuxt SEO is a meta-module that simplifies SEO configuration for Nuxt applications, enabling developers to manage robots.txt, sitemaps, OG images, and structured data from a single integration.
Web 端视觉设计 SKILL。两阶段工作流：先出规范（DESIGN.md），再出代码。 DESIGN.md 是显式文件产物，保存到项目目录，可跨项目复用、可手动修改、可给其他工具消费。 1. 项目里已经有 DESIGN.md 了吗？→ 有则沿用/修改/重建
You are the game engine for an interactive learning experience. Read and follow all instructions in .
"description": "MCP server exposing SSH control for Linux and Windows systems via Model Context Protocol.", "ssh-mcp": "build/index.js" "prepare": "npm run build",
Blazing fast Rust CLI tool that turns 55+ websites into CLI interfaces, reusing Chrome's login state. Zero credentials needed. Single 4.7MB binary, zero runtime dependencies. 1. 账号安全：自动化行为可能触发平台风控 3. 最佳实践：执行前向用户展示将发布的内容，等待确认
XerahS is a cross platform reimagining of the ShareX user interface built with Avalonia. It targets modern UX modular architecture and long term maintainability while preserving core workflows speed and reliability. It provides a foundation for future desktop experiences on Windows, macOS, and Linux
This Copilot prompt establishes coding standards and best practices for the LINUX DO Credit project, covering backend (Go/PostgreSQL/Redis), frontend (TypeScript), and general development guidelines. It benefits developers working on this specific project by ensuring consistent code quality and architectural decisions.
"description": "A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — powered by Naksha. Assembles specialist roles — UI designer, UX researcher, content designer, Figma expert, data viz, email, social, motion, presentation, brand strategy, illustration, video, conversat
你是 OpenClaw 内部负责操作 Codex CLI 的执行器。你的职责不是“给用户解释 Codex 是什么”，而是基于当前仓库提供的 runtime 层，把 Codex 任务稳定启动、持续跟踪、必要时接管和汇报。 可以借鉴 的 runtime/session 思路，但不照搬 Claude 专用逻辑。 优先直接使用 Codex review，而不是自己拼一套“审查 prompt 模拟 review”：
"name": "symfony-ux-skills", "description": "AI agent skills for the Symfony UX frontend stack: Stimulus, Turbo, TwigComponent, LiveComponent, Icons, and Map.", "name": "Simon Andre",
