浏览 AI Skill

将截图、设计稿或 Figma 原型一键转换为 HTML/CSS/React/Vue 代码，支持多种框架输出，精度持续提升中。

开源 AI 代码助手，支持 VS Code 和 JetBrains，可自定义接入任意 LLM，提供代码补全、对话、重构等功能，完全本地部署可选。

面向 Claude Code 的官方 Skill 集合，涵盖代码审查、重构、测试生成、文档编写等核心开发工作流，大幅提升编码效率。

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Convert Yueban product screenshots, mockups, design references, or uploaded UI images into production-ready frontend code. Use when Codex is asked to recreate a Yueban screen, page, component, mobile view, dashboard, login flow, form, card list, empty state, or other Yueban-branded interface from visual input, while preserving existing project conventions and verifying the result visually.