首页 / 全部技能 / 设计 / frontend-design
设计 · anthropics/skills

frontend-design

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

L1 基础 · 登记来源即可V1 已固定Dual-pass Audit
Author anthropicsGitHub anthropics/skills ↗Stars 174801License Apache-2.0(skill 目录自带 LICENSE.txt,全文 Apache License 2.0;anthropics/skills 仓库根无 LICENSE 文件,gh api license 字段为 null,各 skill 目录各自带许可)Commit 41bbe19d1a
管控等级描述 skill 的能力与建议配套的管控措施,不代表质量或安全认证,也不表示可用或不可用。是否使用由用户和管理者决定。不同 agent 宿主对权限的约束各不相同,请勿假定宿主一定会提供安全兜底。第三方 skill 版权归原作者,使用风险由使用者自行承担。

1实现原理 · 为什么它能做到

功能全部由 71 行单文件指令文本实现:零脚本、零工具、零外部文件。机制是「把反模板审美编码为可执行的上下文规则」,靠宿主模型执行 + 自律批判产出,不依赖任何自动化。

frontend-design/SKILL.md
git ls-files frontend-design/ = LICENSE.txt + SKILL.md(71 行,无 scripts/references/templates);全文 grep 无 URL/命令/代码围栏
目录内仅两个文件,SKILL.md 是唯一功能载体——这是纯 prompt 编排型 skill 的典型形态。

用「负样本校准法」避免模板化:先把当前 AI 生成视觉语汇归纳成 5 条带具体色值/模式的特征清单,让模型能自查输出是否落入模板簇——不是空喊『要有创意』,而是给出可比对的规避对象。

frontend-design/SKILL.md
For calibration, AI-generated design right now clusters around some traits: 1. a warm cream background (near #F4F1EA) with a high-contrast serif display and a terracotta or warm-clay accent (often near #D97757 — Anthropic's own Claude-interaction accent...); ... 5. template chrome that appears whatever the subject: a tracked-out ALL-CAPS eyebrow label above every heading; meta strings joined with middle dots ('A · B · C'); ... tinted near-black (#0B0B0B, #111) standing in for black; a monospace face for small data labels; a '→' appended to link and button text.
L38-43:具体到 hex(#F4F1EA/#D97757/#0B0B0B/#111)、rgba(0,0,0,.1)、字符('·'、'→')的负样本目录,是这套提示词的核心校准机制。

强制「题材定位」作为差异化来源:brief 缺题材时先自行提出 subject/audience/primary job 并与客户确认;题材的行业、物料、行话被规定为视觉选择的出发点。

frontend-design/SKILL.md
If the brief does not identify what the product or subject matter is, identify it yourself before designing, and confirm with the client. You can come up with one concrete subject, the design's audience, and the design's primary job, as a proposal. ... The subject's industry, subject matter, materials, and vernacular are where distinctive visual choices come from
L13:把『不同题材长得不一样』(玩具 vs 金融仪表盘)固化为前置步骤,而非留给模型临场发挥。

两遍流程 + uniqueness 自测门槛:先产出紧凑 token 计划(色/字/布局/原则),写代码前必须对照 brief 评审,凡读起来像『任何同类页都能套的默认』即修改并说明改了什么;确认相对独特后才动手写码。

frontend-design/SKILL.md
Work in two passes. First, brainstorm a short design plan based on the client's design brief: create a compact token system with color, type, layout, and principles. ... Then review that plan against the brief before building: if any part of it reads like the generic default you would produce for any similar page ... revise that part, say what you changed and why. Only after you've confirmed the relative uniqueness of your design plan should you start to write the code, following the revised plan.
L47-53:以『中间产物 + 显式评审门』把设计决策过程外化、可复核——代码编写被推迟到独特性确认之后。

内嵌排印与版式领域知识作为硬规则:字阶参照 The Elements of Typographic Style、行长 <80 字符、serif 行高略增;并给出『生成页最常见排版穿帮』的禁止清单。

frontend-design/SKILL.md
set a clear type scale following the default guidance of The Elements of Typographic Style ... Default to line lengths of less than 80 characters. Serif typefaces can have slightly longer line lengths; give serif body text slightly more line-height than a sans-serif. ... Avoid these default typographic treatments; they are the commonest tells of a generated page: - Accenting just a single word or phrase in a headline ... - Using all caps for labels.
L21-28:把书籍知识(Elements of Typographic Style)与反穿帮清单直接写进指令,替代模型默认排版直觉。

把「界面文案」提升为一等设计内容:CTA 用主动语态且精确("Save changes," not "Submit")、动作命名全程一致(Publish → toast 显示 Published)、错误/空状态写为引导语而非情绪。

frontend-design/SKILL.md
Use active voice as default. A CTA says exactly what happens when it is used: "Save changes," not "Submit." An action keeps the same name through the whole flow, so the button that says "Publish" produces a toast that says "Published." ... Treat failure and emptiness as moments for direction, not mood. Explain what went wrong and how to fix it ... Errors don't apologize, and they are never vague about what happened. An empty screen is an invitation to act.
L63-71:专节『More on writing in design』——文案被当作跟间距/色彩同等需要克制的设计材料,这是该 skill 覆盖面的特点之一。

结构诚实与动效克制规则:序号/分隔线等结构装置必须编码真实信息(如内容确为序列才用 01/02/03);非用户触发的动效只保留『单个编排队列时刻』,逐块 fade-slide-up + 全卡 hover 被点名批评为 AI 味。

frontend-design/SKILL.md
Many generic designs use numbered markers (01 / 02 / 03), but that's only appropriate if the content actually is a sequence — like a stepped process or a timeline. Before adding numbered markers, check the content really is a sequence. ... A single orchestrated moment — one page-load sequence or one reveal — lands better than scattered effects; fade-and-slide-up entrances on each section and hover transitions on every card are the generic default and read as AI-generated.
L30-32:把『装饰性信息装置』与『动效铺张』判定为模板信号,并给出判断条件(是否真序列、是否应答用户动作)。

质量底线与自批判闭环:单个记忆点 + 其余克制("Spend your boldness in one place")、响应式/键盘焦点/reduced motion/无障碍硬底线、条件性截图自评("a picture is worth 1000 tokens")、Chanel『出门前摘掉一件配饰』类比。

frontend-design/SKILL.md
Spend your boldness in one place. Let one element be the memorable thing, keep everything around it quiet and disciplined, and cut any decoration that does not serve the brief. Build to a quality floor without announcing it: responsive down to mobile, visible keyboard focus, reduced motion respected, visually accessible ... Critique your own work as you build, taking screenshots to review if your environment supports it — a picture is worth 1000 tokens.
L59:批评/复查被内置为流程最后一步;截图依赖宿主环境("if your environment supports it"),非强制。

2核心能力

01反模板差异化校准(识别并规避 AI 生成视觉语汇)
02题材/受众驱动的设计定位与简报补全
03计划-评审-构建两遍流程(含独特性自测与修改说明)
04设计 token 系统规划(4–6 命名色 / 字族角色 / 布局概念 + ASCII 线框 / 原则)
05排印指导(字族克制、字阶、行长、生成穿帮清单)
06结构诚实与动效节制判断(序号/装饰边界、单点编排时刻)
07界面文案写作规范(CTA 精确命名、流程内一致性、错误/空状态文案)
08CSS 实现注意(选择器特异性冲突,如 .section 与 .cta 的 padding/margin 抵消)

4管控建议与判定依据

建议配套管控措施
面向 Agent
可自动加载
面向管理者
登记来源与版本
判定依据(文件路径与关键语句摘要)
  • SKILL.md: 纯提示词指令与规则文本,无脚本执行与外部影响
审计说明: 纯指令 skill:无脚本执行、无网络外发、无凭证读取、无强制本地写入(grep 全目录零 URL/命令/围栏,git ls-files 仅 SKILL.md + LICENSE.txt),对应分级范式第一档 🟢 绿『合规使用』。执行质量与模型遵循度相关,但不构成安全接触面。

5第二遍独立确认

  • [ok] 目录文件清单(有无隐藏脚本/数据) — git ls-files frontend-design/ 仅 LICENSE.txt + SKILL.md;glob 无其他文件,无隐藏资源
  • [ok] SKILL.md 中 URL/CLI/API/包引用 — 正则扫 http|curl|fetch|exec|api_|npm|pip|gh |git |env[ 等零命中;全文本唯一 URL 是 LICENSE.txt 中官方许可地址 http://www.apache.org/licenses/(非功能依赖)→ external_deps 空数组成立
  • [ok] 代码围栏 / 注入标记(```、ignore previous、system-reminder 等) — 零命中;SKILL.md 为纯 markdown 叙述
  • [ok] 5 条 AI 特征清单及色值逐字存在 — L39-43 逐字含 #F4F1EA、#D97757、rgba(0,0,0,.1)、#0B0B0B、#111、'A · B · C'、'→',非编造
  • [ok] meta.license / stars / last_push 与源一致 — gh api repos/anthropics/skills:stars 174801、pushed_at 2026-09-03T16:37:14Z、license null(仓库根无 LICENSE,故 meta 以 skill 目录内 Apache-2.0 LICENSE.txt 为准并注明差异)
  • [ok] description 与正文能力是否夸大 — description 措辞为 'Guidance/Helps with',正文确为指南文本,未宣称自动化/保证结果——无吹牛
  • [ok] 『两遍流程/截图自批判』是否真被强制 — L47-53 流程顺序明确(评审→修改说明→才写代码),L59 截图附 'if your environment supports it' 条件;但执行严格性依赖宿主模型自律,源码内无强制检查点——此点已在 how_it_works 标注为执行面依赖
  • [ok] 行号/引用与文件实际内容对应 — 二次 grep 带行号比对全部引用段落,无张冠李戴;截断引用未扩写

6结论

  • 规避清单具体到可直接执行(hex/模式/字符),不是空泛『要独特』
  • 独特性评审被设为写代码的前置门槛,设计过程可复核、可解释
  • 覆盖面广:色彩/字体/布局/动效/文案/无障碍/实现级 CSS 注意一体,超过多数 prompt 型设计指南
  • 零依赖零工具:无脚本即无供应链面与执行风险,任何宿主可安全挂载
  • 边界清醒:承认模板特征『All traits are legitimate for some briefs』且 brief 原文优先,不搞审美独裁
  • 适合: 用 agent 宿主(Claude Code/Cursor/Codex 类)做新 UI 或重塑既有界面的开发者/设计师:brief 明确或可自行补题,追求『不像 AI 默认风』的差异化视觉与排印,且环境支持迭代截图自查。作为 Claude Code 等宿主内前端设计任务的挂载指南即插即用。
    不适合: 追求快速模板化/组件库一致输出的场景;需要代码化 design token、自动化设计管线或视觉回归工具链的团队;强品牌规范下不容风格实验的执行岗;以及期望 skill 自动产出完整可部署代码(它只给准则,代码仍由宿主模型生成)的用户。
    Install Agent-Ready
    ① Verified Mirror 2026-09-06
    Option A · Direct DownloadDownload frontend-design.tar.gz
    sha256: 67d68803068d5ae9…
    Option B · Copy Guide for Agent
    install.json
    agent 读 JSON 指南后会自动从本站下载安装,无需更多说明。
    ② Upstream GitHub
    GitHub Repo ↗
    Pinned to commit 41bbe19d1a.