Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

accessibility-engineer无障碍工程师

Agent Skill

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。

总安装

1,307

周安装

55

GitHub Stars

8

下载量

458
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:accessibility-engineer(无障碍工程师)
来源仓库:https://github.com/mae616/design-skills
仓库路径:skills/accessibility-engineer
安装命令:
npx skills add https://github.com/mae616/design-skills --skill accessibility-engineer
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/mae616/design-skills --skill accessibility-engineer

简介

无障碍工程师用于辅助界面设计、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。
  • 该工具当前无额外说明,具体能力以来源仓库实现为准。

SKILL.md

Accessibility Engineer Skill

When to Apply

Apply this skill when the request involves:

  • Accessibility, a11y, WAI-ARIA, screen reader support, semantic HTML, keyboard navigation, focus management
  • アクセシビリティ対応、WAI-ARIA、スクリーンリーダー対応、セマンティックHTML、キーボード操作、フォーカス管理
  • Any UI implementation (should be applied alongside other skills)

Core Principles (Most Important)

  • Native elements first. Solve with proper HTML elements (button, a, label, input, etc.) before reaching for ARIA.
  • ARIA is minimal. Don't add role/aria-* to make things "seem" accessible. Only add when there's a real requirement.
  • Operable = Communicable. Not just visually—assistive tech must receive state, name, and purpose. This is the Definition of Done.
  • Keyboard is the baseline. Mouse-only UI is incomplete. Design focus movement and operations first.

Implementation Rules

1) Semantic Structure

  • Maintain heading order (h1h2 →...). Don't skip levels for styling.
  • Create landmarks for main regions (header, nav, main, footer, aside if needed).
  • Use ul/ol/li for lists, dl/dt/dd for definitions—not div substitutes.

2) Accessible Names

  • Buttons, links, inputs need "names" (labels read by screen readers).

- Priority: Visible text - Fallback: aria-label (when visible text isn't possible) - Composition: aria-labelledby (referencing existing elements)

  • Icon-only buttons/links MUST have names (e.g., "Search", "Close").

3) Forms (Required)

  • Associate label with input (for/id). Never use placeholder as the only label.
  • Communicate required/optional, errors, hints machine-readably (e.g., aria-describedby for helper text).
  • Errors must explain: what's wrong, why, and how to fix.

4) States and Announcements (Dynamic UI)

  • Use native disabled attribute first (button disabled, etc.).
  • For toggles, use aria-pressed / aria-expanded only when native elements aren't sufficient.
  • Use aria-live for async completion/failure announcements—but don't overuse.

5) Keyboard Operation and Focus

  • Design DOM order so tab sequence is logical. Don't force reorder with tabindex.
  • tabindex="0": minimal use to make something focusable.
  • tabindex="-1": only for programmatic focus movement.
  • Always preserve visible focus (focus-visible). Never hide it.
  • Dialogs/modals: define focus destination on open and return destination on close. Implement focus trap if needed.

6) Images and Media

  • Use alt based on purpose (decorative images get empty alt="").
  • For video/audio: confirm controls (play/stop) and alternatives (captions/transcript). Ask if unclear.

Anti-Patterns (Never Do This)

  • div with onClick acting as button (breaks keyboard/role).
  • Using role="button" as a workaround (use native button).
  • Adding aria-label everywhere (causes duplicate announcements when visible label exists).
  • Removing focus ring (invisible focus = inoperable).

Clarification Questions (Don't Assume)

  • Must this UI be completable with keyboard only? (If yes, enumerate operation steps and agree.)
  • For modal/drawer: what gets focus on open? What gets focus on close?
  • When are errors announced? Immediately? After submit?
  • Does video/audio need captions or text alternatives?

Output Format (For Implementation)

  1. Semantic structure (landmarks, headings, lists)
  2. Keyboard operation (Tab order, Enter, Space, Escape)
  3. ARIA usage (only where needed, with justification)
  4. States (disabled/loading/error) and announcements (aria-live if needed)
  5. Accessibility checklist self-assessment (OK / needs work)

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.11%
按下载量换算161

Claude

31.06%
按下载量换算142

Cursor

19.22%
按下载量换算88

Gemini CLI

10.79%
按下载量换算49

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills