agentleFS
Fay1YeeFay1Yee/design-agent-skills/skills/web-design-guidelines/SKILL.md

web-design-guidelines

Skill1 starsChanged 3 months agoMITView on GitHub

Perform a read-only audit of web UI code against the current Vercel Labs Web Interface Guidelines and return concise file-and-line findings covering accessibility, interaction, forms, motion, typography, images, performance, navigation, theming, touch, and internationalization. Use when a user asks to review UI code, check accessibility, audit UX, or run a pre-release web quality check. Fetch the official MIT-licensed guideline source before each audit; do not edit project files unless the user separately requests implementation. / 根据当前 Vercel Labs Web Interface Guidelines 对 Web UI 代码执行只读审计,输出带文件和行号的精简问题清单。

176 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use canvas-procedural-animation, intelligent-routing and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LinHao-citySkill

    canvas-procedural-animation

    Use p5.js/canvas for local procedural character effects: particles, weather, squash/stretch, walk cycles, and environmental motion.

    Also in 5 projects that use this

  • SKB3002Skill

    intelligent-routing

    Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

    Also in 5 projects that use this

  • VercelSkill

    vercel-optimize

    Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.

    Also in 15 projects that use this

  • thongdn-itSkill

    nuqs

    nuqs (type-safe URL query state) best practices for Next.js applications. This skill should be used when writing, reviewing, or refactoring code that uses nuqs for URL state management. Triggers on tasks involving useQueryState, useQueryStates, search params, URL state, query parameters, nuqs parsers, or Next.js routing with state.

    Also in 4 projects that use this

  • LinHao-citySkill

    pose-library-design

    Design reusable 2D character pose libraries, action cycles, and expression states for data-driven animation.

    Also in 4 projects that use this

  • stophobiaSkill

    surprise-me

    Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

    Also in 4 projects that use this

  • +2 more from LinHao-city

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 173 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat that document as an external MIT-licensed source.

    line 18
  2. Distinctive:

    Read the current guideline source.

    line 25
  3. Distinctive:

    Use the official document to determine the exact current rules.

    line 40
  4. Distinctive:

    Do not report an issue without a matching code location.

    line 56
  5. Distinctive:

    Do not treat an automated heuristic as proof when manual verification is required.

    line 57
  6. Distinctive:

    Do not invent browser, assistive-technology, or runtime behavior that was not tested.

    line 58
  7. Distinctive:

    Keep brand-system and product-specific rules outside this general web baseline.

    line 60
  8. Distinctive:

    Use one line per finding:

    line 69

“Common” is measured: kept by at least 6 in 10 of the 173 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Web Design Guidelines Audit / Web 设计规范审计

Audit the requested files against the latest official guideline source. Keep evidence and recommendations tied to the inspected code.

根据最新官方规则审计指定文件,所有结论都必须对应到已检查的代码证据。

Load the guideline source / 加载规则源

Retrieve the current guideline document from:

https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md

Treat that document as an external MIT-licensed source. Record the retrieval date or commit when available. If the source cannot be reached, report the limitation and stop instead of substituting remembered rules.

从上述 Vercel Labs 官方地址读取当前规则,并记录读取日期或 Commit。无法获取时说明限制并停止,不用记忆中的规则替代。

Audit workflow / 审计流程

  1. Confirm the requested file or glob scope.
  2. Read the current guideline source.
  3. Inspect every in-scope file before issuing findings.
  4. Apply only rules relevant to the detected framework and UI surface.
  5. Return each actionable finding with severity, file, line, evidence, violated rule, and a concise remediation direction.
  6. State No findings when the inspected scope contains no supported issue.
  7. 确认文件或 Glob 范围。
  8. 读取当前官方规则。
  9. 在输出结论前检查所有范围内文件。
  10. 仅应用与当前框架和界面相关的规则。
  11. 每条问题输出严重级别、文件、行号、证据、对应规则和精简修复方向。
  12. 范围内无有证据支持的问题时输出 No findings。

Review surfaces / 检查范围

Use the official document to determine the exact current rules. Typical surfaces include:

  • semantics, accessible names, keyboard behavior, focus, and announcements;
  • forms, validation, errors, loading, empty, and disabled states;
  • reduced motion, transition safety, and interaction feedback;
  • typography, truncation, wrapping, and numeric presentation;
  • responsive layout, touch targets, overflow, and zoom/reflow;
  • images, icons, lazy loading, dimensions, and alternative text;
  • navigation, URLs, deep links, state persistence, and browser behavior;
  • performance-sensitive rendering and DOM patterns;
  • theming, color-scheme metadata, localization, and internationalization.

具体规则以当次读取的官方文档为准,通常覆盖语义与可访问性、表单与状态、动效、排版、多端布局、图像、导航、性能、主题和国际化。

Evidence rules / 证据规则

  • Do not report an issue without a matching code location.
  • Do not treat an automated heuristic as proof when manual verification is required.
  • Do not invent browser, assistive-technology, or runtime behavior that was not tested.
  • Separate guideline violations from project-specific design preferences.
  • Keep brand-system and product-specific rules outside this general web baseline.
  • 没有对应代码位置时不输出问题。
  • 需要人工验证的项目不能仅凭自动化启发式判定。
  • 未测试的浏览器、辅助技术或运行时行为不得虚构。
  • 通用 Web 基线与项目特定的品牌规范分开记录。

Output format / 输出格式

Use one line per finding:

[severity] path/to/file:line — evidence — violated rule — remediation direction

Finish with:

  • audited scope;
  • guideline source and retrieval date;
  • finding counts by severity;
  • checks that still require browser, keyboard, screen-reader, zoom, or performance verification;
  • confirmation that the audit did not modify project files.

最后附上审计范围、规则源与读取日期、严重级别统计、待手动验证项和未修改项目文件的确认。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.