Strictly enforces the local design system, accessibility (WCAG 2.2 AA), and world-class design craft for any web or responsive UI work. Use this skill whenever the user asks to build, edit, style, refactor, or review ANY frontend component, page, layout, form, or markup — even casual requests like "make this look nicer", "add a button", "build a card", "fix this CSS", or "create a settings page". Trigger on any mention of HTML, CSS, JSX/TSX, Tailwind, components, styling, layouts, responsive design, accessibility, or visual polish. Do NOT skip this skill just because the request seems small — every UI change must pass through the design system rules.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "design-system-guardian" with this command: npx skills add agebold/skillsmp-agebold-agebold-design-system-guardian
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
本地知识库问答技能。当用户需要基于个人知识库文档（PDF/Markdown/Word）进行问答、生成报告、制作思维导图、或上传文件到向量库时触发。触发词包括："基于知识库"、"基于mysql查询"、"基于某个分区"、"查一下知识库"、"帮我写报告"、"生成思维导图"、"根据文档"、"从我的资料"、"结合我的笔记"、"整理成报告"、"做个导图"、"上传知识库"、"有新文件"、"索引文档"、"建向量库"、"有哪些分区"、"分区列表"、"创建知识库"、"初始化知识库"、"知识库列表"。
Conducts open-ended Q&A on image content based on computer vision and large language models, supporting any questions to receive natural language responses. | 大模型视觉问答（VQA）技能，基于计算机视觉和大语言模型对图片内容进行开放式问答，支持任意提问得到自然语言回答
Customizes safety zones, identifies babies crawling out or approaching dangerous areas such as bedsides/windowsills, and immediately alerts to protect baby safety. | 虚拟围栏越界预警技能，自定义安全区域，识别婴儿爬出、靠近床边/窗台危险区域立即报警，守护宝宝安全
从已有录屏/产品演示视频生成官网宣传片的工作流。 当用户提到以下场景时触发： - "把录屏转成宣传片"、"用录屏做产品视频" - "把演示视频做成官网介绍" - "Remotion 切片"、"视频分镜" - "产品宣传视频生成"、"screen recording to promo video" - "多个视频合并成宣传片"、"产品视频剪辑" - 用户想用 Remotion 把长视频切成短片段做宣传片 本技能覆盖从原始录屏素材到完整 Remotion 宣传片的完整流程： 环境准备 → 目标确认 → 素材识别（人工/自动）→ 分镜策划 → 结构化规格 → Remotion 实现 → 字幕轨 → 中文配音（edge-tts）→ BGM → 渲染出片 每个阶段都有具体检查清单、常见问题和决策框架。 **本 skill 不适用的情况**（见"不适用场景"章节）： - 从技术文档/幻灯片生成视频（无源视频素材） - 需要 AI 生成视频画面本身（仅处理已有素材的剪辑组合）