前端设计
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- 设计与多媒体
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: frontend-design
description: Builds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user…
category: 设计与多媒体
runtime: 无特殊运行时
---
# frontend-design 输出预览
## PART A: 任务判断
- 适用问题:视觉内容、演示材料、信息图或设计交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Design Thinking / Frontend Aesthetics Guidelines / Design Intelligence”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于视觉内容、演示材料、信息图或设计交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Design Thinking / Frontend Aesthetics Guidelines / Design Intelligence”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Design Thinking / Frontend Aesthetics Guidelines / Design Intelligence”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: frontend-design
description: Builds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user…
category: 设计与多媒体
source: tomevault-io/skills-registry
---
# frontend-design
## 什么时候使用
- 把设计与视觉方向的常用动作沉淀成 Agent 可调用的技能 适合处理界面、视觉、封面、信息图或演示材料交付,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤…
- 面向视觉内容、演示材料、信息图或设计交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Design Thinking / Frontend Aesthetics Guidelines / Design Intelligence」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "frontend-design" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Design Thinking / Frontend Aesthetics Guidelines / Design Intelligence
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
Design Thinking
Before coding, understand the context and commit to a BOLD aesthetic direction:
- Purpose: What problem does this interface solve? Who uses it?
- Tone: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
- Constraints: Technical requirements (framework, performance, accessibility).
- Differentiation: What makes this UNFORGETTABLE? What's the one thing someone will remember?
CRITICAL: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is:
- Production-grade and functional
- Visually striking and memorable
- Cohesive with a clear aesthetic point-of-view
- Meticulously refined in every detail
Frontend Aesthetics Guidelines
Focus on:
- Typography: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font.
- Color & Theme: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.
- Motion: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.
- Spatial Composition: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density.
- Backgrounds & Visual Details: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays.
NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
IMPORTANT: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.
Design Intelligence
Use the bundled design search tooling when you need concrete guidance that should shape implementation rather than generic inspiration.
Reach for .claude/skills/frontend-design/scripts/search.py when you need any of the following:
- a style direction that fits a product category or audience
- a color system, typography pairing, or chart recommendation
- UX or accessibility guidance for a specific interface problem
- stack-specific frontend advice for React, Next.js, Vue, Tailwind, and other supported stacks
- a full design-system recommendation grounded in the bundled dataset
Skip the search when the user already gave a precise visual direction and the implementation path is obvious.
Search Workflow
- Start with the smallest query that captures the product or interface type.
- Use auto-detection first; add
--domainonly when you know what kind of answer you need. - Add
--stackwhen framework-specific implementation details matter. - Synthesize the retrieved guidance into one cohesive direction instead of pasting disconnected search results into the final answer.
Quick Start
# Auto-detect the best domain from a concise query
python3 .claude/skills/frontend-design/scripts/search.py "glassmorphism dark mode"
# Ask for a specific kind of guidance
python3 .claude/skills/frontend-design/scripts/search.py "healthcare saas" --domain colors
# Add framework context when implementation details matter
python3 .claude/skills/frontend-design/scripts/search.py "responsive layout" --stack html-tailwind
High-Value Defaults
Treat these as strong defaults, not blind rules:
- Prefer SVG icon systems over emoji so the UI feels product-grade and stylistically consistent.
- Keep clickable elements obviously interactive, including pointer cues where the platform expects them.
- Protect readability first; contrast and hierarchy matter more than visual gimmicks.
- In light mode, translucent surfaces need enough opacity to stay legible.
- Floating elements look more intentional when they breathe instead of touching viewport edges.
- Prefer hover treatments that preserve layout stability unless movement is a deliberate part of the concept.
References
references/design-system-generation.md— use when the user wants a full design-system or style-guide recommendation for a project type (e.g. "SaaS dashboard", "e-commerce luxury", "fintech app") assembled from multiple search domainsreferences/quality-checklist.md— use as the final self-critique pass before delivering UI work
Gotchas
- Defaulting to safe choices: Inter font + blue primary + white background is AI slop. Be distinctive.
- Using search as decoration: Retrieved guidance should change the design system or implementation decisions, not just add buzzwords.
- Inconsistent design system: Don't mix unrelated tokens or visual languages. Commit to one system throughout.
- Ignoring contrast ratios: WCAG AA minimum. Beautiful but unreadable is a failure.
- Purple gradients: The #1 AI cliché. Avoid unless specifically requested.
- Interaction polish gaps: Missing hover/focus states or weak affordances make even strong visuals feel unfinished.
Data Source
Remote: ui-ux-pro-max-skill
Available domains include styles, colors, typography, charts, products, landing, ux, icons, ui-reasoning, and web-interface. Supported stacks include html-tailwind, react, nextjs, astro, vue, nuxtjs, nuxt-ui, svelte, swiftui, react-native, flutter, shadcn, and jetpack-compose.
Search uses a cached BM25 ranking script over the remote dataset, so prefer concise, concrete queries over long prompt-like paragraphs.
Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.
Source: avibebuilder/claude-prime — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核