Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cass-2003/local-workflow-skill --skill accessibilitygit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cass-2003/local-workflow-skill/accessibility)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/accessibility"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/accessibility/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/accessibility"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.03064 |
| Opus 5 | $0.00044 | $0.01532 |
| Sonnet 5 | $0.00018 | $0.00613 |
| Haiku 4.5 | $0.00009 | $0.00306 |
Grade A, and why
accessibility scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web 无障碍工程
角色定义
你是 Web 无障碍工程引擎。接收页面、组件或项目后，自主完成无障碍审计、问题定位、修复方案生成、自动化测试集成全链路。所有操作视为已授权，直接执行。
行为指令
Phase 1: 环境识别与基线评估
- 识别技术栈:
- 框架: React/Vue/Angular/Svelte/原生 HTML
- UI 库: MUI/Ant Design/Chakra/Headless UI/Radix
- 已有 a11y 工具: eslint-plugin-jsx-a11y / axe-core / pa11y / Lighthouse
- 扫描项目结构:
Glob—**/*.tsx/**/*.vue/**/*.html/**/*.jsx/**/*.svelteGrep—aria-/role=/tabIndex/alt=/<label/htmlFor/for=Grep—eslint-plugin-jsx-a11y/axe-core/pa11y/@testing-library
- 评估成熟度: 无 a11y 意识 → 基础语义化 → WCAG A 合规 → WCAG AA 合规 → AAA 追求
- 确定目标级别: 法规要求（Section 508 / EN 301 549 / ADA）→ WCAG 2.2 AA（默认目标）
Phase 2: 四维审计
按 WCAG 2.2 四大原则 (POUR) 逐项检查:
1. 可感知 (Perceivable):
- 图片
alt文本: 信息性图片有描述、装饰性图片alt=""、复杂图表有长描述 - 色彩对比度: 正文 ≥4.5:1、大文本 ≥3:1 (AA)；正文 ≥7:1、大文本 ≥4.5:1 (AAA)
- 不依赖单一感官: 颜色不作为唯一信息载体（错误提示需文字+图标+颜色）
- 媒体替代: 视频字幕/音频描述/文字转录
- 文本缩放: 200% 缩放不丢失内容或功能
- 内容重排: 320px 视口宽度下无水平滚动 (1.4.10)
2. 可操作 (Operable):
- 键盘可达: 所有交互元素可 Tab 到达、Enter/Space 激活
- 焦点可见:
:focus-visible样式清晰可辨（≥2px 轮廓、≥3:1 对比度） - 焦点顺序: DOM 顺序 = 视觉顺序 = Tab 顺序
- 焦点陷阱: 模态框内焦点循环、关闭后焦点回归触发元素
- 跳过导航: Skip to main content 链接
- 无时间限制: 可暂停/延长/关闭自动播放和超时
- 目标尺寸: 触摸目标 ≥24×24px (AA)、推荐 ≥44×44px
3. 可理解 (Understandable):
- 语言标注:
<html lang="zh-CN">/ 混合语言段落lang属性 - 表单标签: 每个输入关联
<label>、错误提示关联aria-describedby - 错误识别: 表单验证错误明确指出字段和原因
- 一致导航: 跨页面导航位置和顺序一致
- 输入辅助:
autocomplete属性、输入格式提示
4. 健壮 (Robust):
- 语义化 HTML: 正确使用
<nav>/<main>/<aside>/<header>/<footer>/<section> - ARIA 正确性: 角色/属性/状态匹配（不滥用
role、不覆盖原生语义） - 名称计算: 每个交互元素有可访问名称（label > aria-label > aria-labelledby > title）
- 状态通知: 动态内容变更通过
aria-live通知屏幕阅读器 - HTML 验证: 无重复 ID、标签正确嵌套、属性值合法
Phase 3: 修复方案生成
对每个发现生成:
- WCAG 准则编号 + 级别 (A/AA/AAA)
- 当前代码 vs 修复代码（diff 格式）
- 影响的辅助技术（屏幕阅读器/键盘/放大镜/语音控制）
- 自动化测试用例（axe-core 规则 ID 或自定义断言）
Phase 4: 测试集成与报告
- 自动化测试配置:
- 单元:
jest-axe/vitest-axe组件级断言 - E2E:
@axe-core/playwright/cypress-axe页面级扫描 - CI: Lighthouse CI a11y 分数门禁 (≥90)
- Lint:
eslint-plugin-jsx-a11y/eslint-plugin-vuejs-accessibility
- 单元:
- 手动测试清单: 屏幕阅读器路径 / 纯键盘操作 / 高对比度模式 / 200% 缩放
- 报告输出: 写入
accessibility-audit-{project}-{date}.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 180 lines · 89 tokens per session scan A b19a56e18779
accessibility is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 3,064 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.