Communitygithub.com

leonxlnx/taste-skill

构建精致编辑风格界面。暖色调单色板、排版对比、扁平 bento 网格、柔和粉彩。无渐变、无重阴影。

taste-skill 是什么?

此技能(/taste-skill)定义了一个名为“高级实用极简主义与编辑型 UI”的前端工程协议。它专注于生成高度精致、极致简约、类似高端工作台平台的“文档风格”Web 界面。该协议强制使用高对比度的暖色调单色板、精心设计的排版层次、充裕的结构性宏空白空间、bento 网格布局以及超扁平组件架构,并刻意采用柔和的粉彩色作为点缀。它明确拒绝标准的通用 SaaS 设计模式,禁止使用常见字体(如 Inter、Roboto)、通用图标库(如 Lucide、Feather)、默认 Tailwind 阴影、渐变、霓虹色、3D 玻璃态以及 emoji。该协议还指定了一套详细的组件规格(包括 bento 盒子、按钮、标签、手风琴和键盘快捷键 UI)、图标与图像使用指南(偏好 Phosphor 图标和单色连续线条插图),以及一套微妙的交互动画系统(例如随滚动淡入、悬停卡片微提升、列表交错显现)。执行时,它要求首先建立宏观空白,然后约束排版内容宽度,立即应用自定义排版层次和颜色变量,并确保所有元素严格遵循 `1px solid #EAEAEA` 的边框规则。该技能旨在与 Claude Code、Cursor 或 Codex 等 AI 代理配合使用,可应用于 React、Tailwind 或 Vue 等前端框架。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/leonxlnx/taste-skill/tree/main/skills/minimalist-skill

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

协议:高级实用极简主义 UI 架构师

1. 协议概述

名称:高级实用极简主义与编辑型 UI 描述:一项先进的前端工程指令,用于生成高度精致、极致简约、类似高端工作台平台的“文档风格”Web 界面。本协议严格遵循高对比度的暖色调单色板、独特的排版层次、精心设计的结构性宏空白空间(macro-whitespace)、bento 网格布局以及带有刻意柔和粉彩色点缀的超扁平组件架构。它主动拒绝标准的通用 SaaS 设计趋势。

2. 绝对负面约束(禁止元素)

AI 必须严格避免以下通用的前端开发默认项:

  • 禁止使用 "Inter"、"Roboto" 或 "Open Sans" 字体。
  • 禁止使用通用的细线图标库,如 "Lucide"、"Feather" 或标准的 "Heroicons"。
  • 禁止使用 Tailwind 默认的重阴影(例如 shadow-md、shadow-lg、shadow-xl)。阴影必须几乎不存在,或经过高度自定义,使其极度扩散且不透明度极低(< 0.05)。
  • 禁止使用主色背景填充大元素或大区域(例如,没有亮蓝色、绿色或红色的英雄区域(hero section))。
  • 禁止使用渐变、霓虹色或 3D 玻璃态(玻璃拟态)(超出细微的导航栏模糊效果)。
  • 禁止对大容器、卡片或主要按钮使用 rounded-full(药丸形状)。
  • 禁止在代码、标记、文本内容、标题或 alt 文本中使用 emoji。请替换为合适的图标或干净的 SVG 基本元素。
  • 禁止使用通用占位名称,如 "John Doe"、"Acme Corp" 或 "Lorem Ipsum"。请使用真实的、符合上下文的内容。
  • 禁止使用 AI 文案写作的陈词滥调:"Elevate"、"Seamless"、"Unleash"、"Next-Gen"、"Game-changer"、"Delve"。请使用平实、具体的语言。

3. 排版架构

界面必须依靠极端的排版对比和优质字体选择来营造编辑感。

  • 主要无衬线字体(正文、UI、按钮):使用干净、几何或具有特色的系统原生字体。目标:font-family: 'SF Pro Display', 'Geist Sans', 'Helvetica Neue', 'Switzer', sans-serif。
  • 编辑型衬线字体(英雄区域标题和引文):目标:font-family: 'Lyon Text', 'Newsreader', 'Playfair Display', 'Instrument Serif', serif。应用紧凑的字间距(letter-spacing: -0.02em 到 -0.04em)和紧凑的行高(1.1)。
  • 等宽字体(代码、按键、元数据):目标:font-family: 'Geist Mono', 'SF Mono', 'JetBrains Mono', monospace。
  • 文本颜色:正文文本绝不能是纯黑色(#000000)。使用接近黑色的深灰色/木炭色(#111111 或 #2F3437),并设置宽松的行高(line-height)为 1.6 以保证可读性。次要文本应为柔和的灰色(#787774)。

4. 调色板(暖色调单色 + 点缀粉彩)

色彩是一种稀缺资源,仅用于语义或细微点缀。

  • 画布 / 背景:纯白色 #FFFFFF 或暖色骨白色/米白色 #F7F6F3 / #FBFBFA。
  • 主要表面(卡片):#FFFFFF 或 #F9F9F8。
  • 结构边框 / 分隔线:超浅灰 #EAEAEA 或 rgba(0,0,0,0.06)。
  • 点缀色:仅使用高度去饱和、褪色的粉彩色,用于标签、内联代码背景或细微的图标背景。
    • 浅红色:#FDEBEC(文字色:#9F2F2D)
    • 浅蓝色:#E1F3FE(文字色:#1F6C9F)
    • 浅绿色:#EDF3EC(文字色:#346538)
    • 浅黄色:#FBF3DB(文字色:#956400)

5. 组件规范

  • Bento 盒子特性网格:
    • 使用不对称的 CSS Grid 布局。
    • 卡片必须精确设置 border: 1px solid #EAEAEA。
    • 圆角必须清晰:最大 8px 或 12px。
    • 内边距必须充裕(例如 24px 到 40px)。
  • 主要行动号召按钮:
    • 实心背景 #111111,文字色 #FFFFFF。
    • 轻微圆角(4px 到 6px)。无盒子阴影。
    • 悬停状态应为微妙的颜色变化至 #333333,或微缩放 transform: scale(0.98)。
  • 标签与状态徽章:
    • 药丸形状(border-radius: 9999px),非常小的排版(text-xs),大写并带有宽字间距(letter-spacing: 0.05em)。
    • 背景必须使用定义的柔和粉彩色。
  • 手风琴(常见问题):
    • 去除所有容器框。仅使用 border-bottom: 1px solid #EAEAEA 分隔项目。
    • 切换状态使用干净、锐利的 + 和 - 图标。
  • 快捷键微 UI:
    • 使用 <kbd> 标签将快捷键渲染为物理按键:border: 1px solid #EAEAEA,border-radius: 4px,background: #F7F6F3,使用等宽字体。
  • 模拟操作系统窗口装饰:
    • 在模拟软件界面时,将其包裹在一个极简容器中,顶部有一根白色条,包含三个小的浅灰色圆形(模仿 macOS 窗口控件)。

6. 图标与图像指令

  • 系统图标:使用 "Phosphor Icons (Bold 或 Fill 权重)" 或 "Radix UI Icons",以获得技术感、笔画稍粗的美学效果。统一所有图标的笔画宽度。
  • 插图:单色、粗糙的连续线条墨水草图,背景为白色,包含单个偏移的几何形状,填充柔和的粉彩色。
  • 摄影:使用高质量、去饱和的图像,色调偏暖。应用细微叠加层(opacity: 0.04 暖色颗粒),使照片融入单色调色板。切勿使用过饱和的库存照片。当没有真实素材时,使用可靠的占位符,如 https://picsum.photos/seed/{context}/1200/800。
  • 英雄区域与分区背景:分区不应显得空旷和平淡。使用极低不透明度的细微全宽背景图像、柔和的径向光斑(radial-gradient 暖色调,opacity: 0.03)或极简的几何线条图案来增加深度,同时不破坏干净的美学。

7. 微妙动效与微动画

动感应感觉无形——存在但从不分散注意力。目标是安静的精致,而非炫技。

  • 滚动进入:元素进入视口时柔和淡入。使用 translateY(12px) + opacity: 0,在 600ms 内以 cubic-bezier(0.16, 1, 0.3, 1) 解析。使用 IntersectionObserver,绝不使用 window.addEventListener('scroll')。
  • 悬停状态:卡片通过极其微妙的阴影变化抬升(box-shadow 在 200ms 内从 0 0 0 过渡到 0 2px 8px rgba(0,0,0,0.04))。按钮在 :active 时响应 scale(0.98)。
  • 交错显现:列表和网格项以级联延迟进入(animation-delay: calc(var(--index) * 80ms))。切勿一次性挂载所有内容。
  • 背景环境动效:可选。在英雄区域背后,一个非常缓慢移动的径向渐变斑点(animation-duration: 20s+,opacity: 0.02-0.04)。必须应用于 position: fixed; pointer-events: none 层。切勿用于滚动容器。
  • 性能:仅通过 transform 和 opacity 进行动画。不使用触发布局的属性(top、left、width、height)。谨慎使用 will-change: transform,仅用于活跃动画元素。

8. 执行协议

当被要求编写前端代码(HTML、React、Tailwind、Vue)或设计布局时:

  1. 首先建立宏观空白。在分区之间使用巨大的垂直内边距(例如,在 Tailwind 中使用 py-24 或 py-32)。
  2. 将主要排版内容宽度限制为 max-w-4xl 或 max-w-5xl。
  3. 立即应用自定义排版层次和单色颜色变量。
  4. 确保每个卡片、分隔线和边框严格遵守 1px solid #EAEAEA 规则。
  5. 为所有主要内容块添加滚动进入动画。
  6. 通过图像、环境渐变或细微纹理确保分区具有视觉深度——避免空旷的平面背景。
  7. 提供的代码应原生反映出这种高端、整洁、编辑型美学,无需手动调整。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

leonxlnx/design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

leonxlnx/design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

leonxlnx/gpt-taste

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

leonxlnx/image-taste-frontend

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.

leonxlnx/image-to-code

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.

leonxlnx/industrial-brutalist-ui

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/minimalist-ui

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

leonxlnx/redesign-existing-projects

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

leonxlnx/stitch-design-taste

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

leonxlnx/taste-skill

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

leonxlnx/taste-skill

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/taste-skill

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/taste-skill

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/taste-skill

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

leonxlnx/taste-skill

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

leonxlnx/taste-skill

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.

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

leonxlnx/taste-skill

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

相关技能