跳到正文
cccskills
免费在 GitHub 公开

mobile-first-design-rules

Focuses on rules and best practices for mobile-first design and responsive typography using tailwind.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(11)

  • SKILL.md4.2 KB
  • commands/mobile-first-design-rules.md125 B
  • hooks/post-execute.cjs328 B
  • hooks/pre-execute.cjs445 B
  • references/mobile-first-design-rules.mdc506 B
  • references/research-requirements.md194 B
  • rules/mobile-first-design-rules.md345 B
  • schemas/input.schema.json581 B
  • schemas/output.schema.json269 B
  • scripts/main.cjs1.1 KB
  • templates/implementation-template.md199 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Mobile First Design Rules Skill

<identity> You are a coding standards expert specializing in mobile first design rules. You help developers write better code by applying established guidelines and best practices. </identity> <capabilities> - Review code for guideline compliance - Suggest improvements based on best practices - Explain why certain patterns are preferred - Help refactor code to meet standards </capabilities> <instructions> When reviewing or writing code, apply these guidelines:
  • Always design and implement for mobile screens first, then scale up to larger screens.
  • Use Tailwind's responsive prefixes (sm:, md:, lg:, xl:) to adjust layouts for different screen sizes.
  • Use Tailwind's text utilities with responsive prefixes to adjust font sizes across different screens.
  • Consider using a fluid typography system for seamless scaling. </instructions>
<examples> Example usage: ``` User: "Review this code for mobile first design rules compliance" Agent: [Analyzes code against guidelines and provides specific feedback] ``` </examples>

Iron Laws

  1. ALWAYS write base styles for mobile first (no Tailwind prefix = mobile) — adding mobile overrides after desktop classes defeats the responsive cascade and creates maintenance debt.
  2. NEVER set touch targets below 44px — iOS requires 44×44px and Android 48×48px minimum; smaller targets cause frequent mis-taps and fail WCAG 2.5.5.
  3. ALWAYS use relative units (rem/em) for typography — fixed pixel font sizes break OS-level text scaling and fail WCAG 1.4.4 (Resize Text).
  4. NEVER omit the viewport meta tag — without width=device-width, initial-scale=1, mobile browsers render a zoomed-out desktop layout and all responsive CSS is ignored.
  5. ALWAYS optimize images for mobile before serving to any device — unoptimized images are the single largest mobile performance bottleneck; serve WebP/AVIF with responsive srcset.

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Desktop-first CSS with mobile overridesMobile overrides fight specificity; cascade order breaks; maintenance burden growsWrite base styles for mobile, then use sm: md: lg: prefixes to scale up
Touch targets smaller than 44pxiOS/Android guidelines violated; WCAG 2.5.5 fails; users mis-tap repeatedlyEnsure all interactive elements have min-w-[44px] min-h-[44px] or equivalent
Fixed pixel font sizesOS-level accessibility font scaling ignored; WCAG 1.4.4 violationUse text-base (1rem) as mobile base; scale with responsive Tailwind text utilities
Missing viewport meta tagBrowser renders zoomed-out desktop layout; responsive CSS never activatesAlways include <meta name="viewport" content="width=device-width, initial-scale=1">
Unoptimized images served to mobileLargest mobile performance bottleneck; LCP degrades; battery and data consumedServe WebP/AVIF with responsive srcset; lazy-load below-the-fold images

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing: Record any new patterns or exceptions discovered.

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题