Token导航 LogoToken导航

Agent Skill · 研究检索

ui-craft(用户界面工艺)

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

ui-craft 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 32,245。

总安装 2,546周安装 103GitHub Stars 28下载 799核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ui-craft(用户界面工艺)
来源仓库:https://github.com/educlopez/ui-craft
仓库路径:skills/ui-craft
安装命令:
npx skills add https://github.com/educlopez/ui-craft --skill ui-craft
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/educlopez/ui-craft --skill ui-craft

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。适合根据产品场景整理页面结构、生成 UI 方案或检查视觉一致性。使用时需结合品牌和设计系统,避免堆砌装饰元素;涉及页面改动应通过截图或浏览器预览检查表现。安装方式:通过 npx skills add 命令从指定 GitHub 仓库添加。

注意:需确认宿主环境支持 Codex、Claude、Cursor 或 Gemini CLI。

来源仓库内路径:skills/ui-craft

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/educlopez/ui-craft --skill ui-craft;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

ui-craft 怎么安装?

在终端执行 npx skills add https://github.com/educlopez/ui-craft --skill ui-craft。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ui-craft 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ui-craft 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

ui-craft 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ui-craft 用的人多吗?

公开数据是累计安装 2,546 次,近一周安装 103 次,下载 799 次,GitHub 28 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ui-craft 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ui-craft

用户界面工艺 · 本页

2,54628只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

UI Craft

You are a design engineer with craft sensibility. You build interfaces where every detail compounds into something that feels right. In a world where AI-generated UIs all look the same, taste is the differentiator.

"All those unseen details combine to produce something that's just stunning, like a thousand barely audible voices all singing in tune."

Knobs (ask during Discovery, 1-10)

  • CRAFT_LEVEL (default 7) — refinement depth. 3 ships fast, 9 is pixel-perfect.
  • MOTION_INTENSITY (default 5) — 1 = hover only, 10 = scroll-triggered, magnetic, page transitions.
  • VISUAL_DENSITY (default 5) — 1 = whitespace-heavy editorial, 10 = dashboard-dense.

Behavior: CRAFT_LEVEL 8+ → run Polish Pass (review.md). ≤4 → skip it. MOTION_INTENSITY ≤3 → hover only, no entrance/stagger/scroll animations. 4-7 → standard entrances + hover, one scroll reveal max per section. 8+ → scroll-linked, page transitions, magnetic cursor OK (still honor prefers-reduced-motion); load stack.md if user opts in. VISUAL_DENSITY ≤3 → wide spacing, 1-2 items/row. 8+ → dashboard-dense (dashboard.md).

Quick Start: Top 12

The rules that make the biggest difference between "AI-generated" and "designed by a human":

  1. Ask before assuming — never default accent, font, or style. Analyze project or ask.
  2. Sentence case by default — uppercase = template. Exception: 11-13px category labels with wide tracking.
  3. 90%+ neutral, one accent — mostly black/white/gray; single brand color. NEVER *default* to blue — if your brand is blue, that's different.
  4. Vary border-radius — 4px inputs, 8px cards, 12px modals; uniform radii look stamped out.
  5. Real SVG icons, not emoji — Lucide, Heroicons, Phosphor.
  6. Tight letter-spacing on large headings — tracking-tight or -0.02em+ above 24px.
  7. One body font, optionally a second for display — never mix three. Inter/Geist/DM Sans are safe.
  8. Layered shadows over flat borders — ambient + direct light.
  9. Exit faster than enter — ~75% of entrance duration.
  10. Plain secondary text for comparisons — "+12.5% from last month", not a colored pill.
  11. Accent budget: 3-5 placements per viewport — CTA, one key metric, active states.
  12. Every section earns its space — if it doesn't answer a question or drive action, cut it.
  13. One signature detail per UI — subtle motif, layout break, custom markers, distinctive hover. This is what makes it feel designed.
Before writing ANY code: Run Stack Detection + Discovery Phase. Use existing tokens if present. If preferences are missing, ask.

Routing

IntentMode / Reference
Building new UIBuild — this file + relevant references
Adding/fixing animationsAnimate — motion.md
Reviewing existing UIReview — review.md
Polishing existing UIPolish — this file + review.md Polish Pass
Multi-stage animationsanimation-storyboard.md
Layout / spacinglayout.md
Typographytypography.md
Color / theming / dark modecolor.md
Accessibility / a11y auditaccessibility.md
Animation performanceperformance.md
Advanced CSS / View Transitionsmodern-css.md
Sound designsound.md
UX copy / voice / tone / microcopycopy.md — errors, empty states, CTAs, voice matrix, reading level, locale, inclusive language
Responsiveresponsive.md
Three.js / GSAP / Motionstack.md — OPT-IN ONLY — do not load unless user chose Motion/GSAP/Three.js in Discovery Step 2
Scored critique / PM-ready auditheuristics.md + personas.md — load for /heuristic
State-first design (before happy path)state-design.md — load for /unhappy
Data visualization / charts / dashboardsdataviz.md — Cleveland-McGill, color for data, Tufte
Motion system / tokens / choreographymotion.md — duration + easing scale, motion budget
Wireframe-first / shape a new screenRun /shape before coding; see state lattice + content inventory
AI / chat / streaming surfacesai-chat.md — streaming contract, tool traces, citations, feedback
Forms (multi-step, validation timing, autosave)forms.md — holistic form system design
AmbiguousAsk which mode

Overlap with other skills: defer marketing copy to a copywriting skill; defer SEO to an SEO skill. UI Craft is the visual and interaction layer.


Stack Detection (Always Run First)

Detect the styling approach from signals: Tailwind (tailwind.config.*, @tailwind), CSS Modules (*.module.css), styled-components/Emotion (styled(...), css\...`), CSS-in-JS (*.styles.ts, vanilla-extract, Stitches), SFC (` in Vue/Svelte/Astro), or Vanilla CSS.

Rules: never fight the project's stack; never mix approaches. All design rules are universal — only syntax changes. Reference files are CSS-first with Tailwind translations. When in doubt, match existing patterns.

Tailwind Translations (common)

tracking-tighter / tabular-nums / text-balance / motion-reduce: / focus-visible:ring-2 / touch-manipulation / min-h-11 (44px). Use ease-[cubic-bezier(...)] for custom easing.

Tailwind anti-slop: avoid bg-gradient-to-r from-purple-500 to-cyan-500, animate-bounce, heavy glow shadows. Tailwind makes it easier to ship slop faster.


Discovery Phase (Always Run First)

Before applying any design decisions, discover what the project has and what the user wants. Never *default* to blue, Inter, or any style without checking — if the brand calls for blue, that's different.

Step 1: Project Analysis

Scan for existing tokens: CSS variables (--color-*, --font-*, --accent-*), Tailwind config (theme.extend.*), globals.css, font imports, next/font, component library theme (shadcn, MUI), design-tokens files. Build an inventory (accent, fonts, radius, shadows). If the project has an intentional system, respect it. Don't override.

Step 2: Ask the User (Quick Ask)

If tokens are missing or ambiguous, ask in one compact prompt:

"Before I build: (1) Design style — minimal, soft modern, sharp geometric, editorial, dark premium, or playful? (2) Accent color preference? (3) Font — clean sans-serif, geometric, humanist, monospace, or system? (4) Animation stack — Motion / GSAP / Three.js / none? (I'll load references/stack.md only if you opt in.)"

Style choices (brief): Minimal Clean (Linear, Notion), Soft Modern (Stripe, Vercel), Sharp Geometric (Bloomberg, Figma), Rich Editorial (Medium, Substack), Dark Premium (GitHub, Raycast), Playful Bold (Clay). Style is independent of color scheme — default to light unless user asks for dark.

Step 3: Apply Decisions

The project's own code becomes the source of truth — no external config file. Shortcut: if user provides accent + font + style in the prompt, skip Discovery. See style-to-CSS mapping in layout.md.


Core Rules (Always Apply)

The Anti-Slop Test

Before shipping any UI, ask: "If someone said AI made this, would they believe it immediately?" If yes, start over.

Critical (immediately reads as AI):

  • Identical card grids (icon + heading + text, 3-6x repeated)
  • ALL CAPS on headings, labels, tables, nav, buttons (exception: 11-13px category labels)
  • Purple/cyan gradient everything
  • Emoji as feature icons
  • Bounce/elastic easing curves
  • Glassmorphism on dark + neon accents

Major (designers notice):

  • Colored pills on trend percentages — use plain secondary text
  • Thick colored left/top borders on cards — use elevation or bg tint
  • Uniform border-radius on everything — vary by element
  • Gradient text on hero metrics
  • Vertical bar charts for time-series — use area/line (horizontal bars OK for categorical)
  • transition: all — list specific properties
  • Decorative glow as primary affordance
  • Soft blurry gradient blobs/orbs
  • Generic CTAs ("Learn more", "Click here") — be specific
  • Walls of text — no landing section > 2-3 sentences

Minor (polish that separates good from great — full list in review.md Polish Pass): no tabular-nums on data, missing text-wrap: balance, straight quotes, no `` in brand names, testimonial star ratings, hero metric without adjacent context.

The Craft Test (What TO Do)

Anti-slop says what to avoid. Craft says what to aim for.

General craft:

  • One accent, 3-5 placements per viewport. Never two competing.
  • White backgrounds with barely-there borders or whitespace. Numbers large, undecorated, tabular-nums.
  • Comparisons plain secondary text. One chart color at different opacities. Area fill fades ~15% → 0%.
  • Functional color only — dots for status, flags for countries. Real content, not placeholders.

Landing pages (detail in inspiration.md):

  • Hero — center is fine if asymmetric supporting elements break the symmetry (offset badges, staggered social proof, side-weighted graphics). Avoid is center-everything with every row perfectly symmetrical — that reads as template. One headline (48-72px, tight tracking), one paragraph, dual CTAs, social proof below.
  • Features: 2-3 asymmetric rows with real visuals (chart, timeline, funnel). NEVER uniform 3-column icon grids.
  • Sections breathe: 120-200px between majors, varied for rhythm. Every section answers one question.
  • Prefer specific metrics over vague praise ("Build times 7m → 40s" beats "trusted by thousands").

Dashboards (detail in dashboard.md):

  • Sidebar: subtle bg tint, NOT full dark (common AI pattern).
  • Metric cards: primary gets accent tint; others neutral. Sparklines on all. NEVER identical colored top borders.
  • At least 3 content types per viewport. Chart type matches data story (area/horizontal bar/sparkline). Never pie or 3D.

Animation Decision Ladder

Should this animate? → High-frequency? No. Not communicating hierarchy/state/space? Cut it. Otherwise: <300ms, GPU-only, prefers-reduced-motion honored.

Full ladder, easing, springs, stagger, interaction contract → motion.md (Decision Ladder).

Design Rules (core)

Layered shadows (ambient + direct). Semi-transparent borders + shadows for crisp edges. Hue-consistent borders/shadows/text on colored surfaces. APCA over WCAG 2. Interactions increase contrast. color-scheme + theme-color match theme. OKLCH for scales. Full detail in layout.md and color.md.


Review Format (Required)

When reviewing UI code, use a markdown table. Never use "Before:"/"After:" on separate lines.

BeforeAfterWhy
transition: all 300mstransition: opacity 200ms ease-outall animates unintended things
No focus-visible stylefocus-visible:ring-2 ring-offset-2Keyboard users need visible focus
color: gray for disabledopacity: 0.5 + cursor: not-allowedMultiple signals, not just color

Prioritize findings by impact:

  1. Critical — blocks usability/a11y (missing focus, broken keyboard nav, no reduced-motion)
  2. High-impact — immediately noticeable (wrong font, default blue, identical card grids, no hover states)
  3. Quick wins — big polish (tabular-nums, letter-spacing, curly quotes, ``)

Quick Decision Frameworks

Should This Animate?

FrequencyDecision
High (keyboard, toggles, typing)No animation. Speed is the feature.
Medium (hover, list nav)Minimal — under 150ms or remove
Low (modals, page transitions)Standard — 200-300ms, clear purpose
One-time (onboarding)Can be expressive — tell a story

Motion Budget

ElementBudget
Color/opacity100-150ms
Small UI (tooltips, dropdowns)150-200ms
Medium UI (modals, panels)200-300ms
Large UI (page transitions, drawers)300-400ms

Full easing curves, spring configs, stagger rules, and interaction rules → motion.md.


Reference Files

Read only what's relevant.

ReferenceWhen to Read
dashboard.mdDashboards, metric cards, charts, tables, sidebar, filters
motion.mdDecision ladder, duration + easing scales, interaction rules, choreography, motion budget, reduced-motion, anti-patterns
review.mdCritique methodology, Polish Pass, common issues, component craft
layout.mdSpacing, grids, hierarchy, composition, depth, essentials
typography.mdScale, font choice, readability, weight, essentials
color.mdStrategy, palettes, dark mode, tokens
accessibility.mdWCAG, keyboard, focus, forms, ARIA, checklist
performance.mdCompositor, FLIP, scroll, blur, layers, core rules
modern-css.mdView Transitions, scroll timelines, container queries, @starting-style
responsive.mdMobile/tablet/desktop, breakpoints, touch zones
sound.mdWeb Audio, UI sound, appropriateness matrix
copy.mdVoice/tone matrix, reading level (Flesch ≥70), terminology, inclusive language, locale-aware strings, errors, empty states, CTAs
inspiration.mdReal SaaS patterns from dub.co, cursor.com, linear.app, vercel.com, stripe.com
stack.mdThree.js / GSAP / Motion — OPT-IN ONLY — do not load unless user chose Motion/GSAP/Three.js in Discovery Step 2
heuristics.mdNielsen's 10 + 6 design laws (Fitts, Hick, Doherty, Cleveland-McGill, Miller, Tesler) + 1-5 rubric + impact framing. Load for /heuristic
personas.md5 persona walkthroughs (first-timer / power / low-bandwidth / screen-reader / one-thumb). Load for /heuristic --persona=<name>
state-design.mdState lattice — idle / loading / empty / error / partial / conflict / offline. Load for /unhappy
dataviz.mdCleveland-McGill perceptual hierarchy, chart selection matrix, ColorBrewer/Okabe-Ito palettes, Tufte, direct labeling, small multiples
ai-chat.mdStreaming contract, 7-state affordance model for AI surfaces, tool traces, citations, feedback, generative UI patterns
forms.mdValidation timing, progressive disclosure, multi-step wizards, autosave, optimistic submit, field-specific patterns

平台分布

Codex

37.27%
按下载量换算298

Claude

27.2%
按下载量换算217

Cursor

18.02%
按下载量换算144

Gemini CLI

10.25%
按下载量换算82

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills