Converts UI images and/or OpenAPI specs into web application components with routing and service integration. Supports Angular and React (Vite). When UI images are provided, generates visual components using an integrated image-to-component procedure with screenshot validation. When only an OpenAPI spec is provided (no images), generates all pages directly using neutral default tokens. Supports any combination of images and OpenAPI spec.
How to install ui-creator?
lennix1337/genexus18mcp/ui-creator
$npx -y skills add lennix1337/genexus18mcp --skill ui-creatorInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/lennix1337/genexus18mcp" --skill "lennix1337/genexus18mcp/ui-creator"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/lennix1337/genexus18mcp" that are relevant to the current task. Run `npx skills add "https://github.com/lennix1337/genexus18mcp"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering.Jul 2026
- hyperframes-registryInstall, discover, and wire registry blocks and components into HyperFrames compositions.Jul 2026
- composition-patternsReact composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing…Jul 2026
- shadcnManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces.Jul 2026
- lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV…Jul 2026
- image-to-code-skillElite 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…Jul 2026
