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 Onevium/awesome-claude-skills --skill accessibility-auditgit clone --depth 1 https://github.com/Onevium/awesome-claude-skillsWrote 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/onevium/awesome-claude-skills/accessibility-audit)<a href="https://agentmods.dev/skills/onevium/awesome-claude-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/onevium/awesome-claude-skills/accessibility-audit/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/onevium/awesome-claude-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/onevium/awesome-claude-skills/accessibility-audit.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 | $0.00100 | $0.01135 |
| Opus 5.5 | $0.00040 | $0.00454 |
| Sonnet 5.5 | $0.00020 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
accessibility-audit 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 1mo 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.
What it actually says
无障碍审查
基于真实实现执行证据化审查。默认目标为 WCAG 2.2 AA；AAA 或项目自己的更高标准必须单独标注，不能混写成 AA 硬要求。
1. 确认范围与操作模式
- 优先审查用户点名或本轮刚修改的文件；不明确且会改变结论时再询问。
- 读取完整页面、相关样式、组件和交互代码，确认框架、目标设备及用户指定标准。
- 用户只要求审查时，仅输出发现；用户明确要求修复时，才修改文件并验证。
2. 对比度与颜色
- 普通文本对比度至少
4.5:1；大号文本至少3:1。 - UI 组件、图标、边界和必要状态提示应满足非文本对比要求。
- 不允许只靠颜色表达成功、失败、选中或链接；同时提供文字、图标、形状或下划线等信号。
- 能解析颜色时给出实际比值、要求值和对应前景/背景；不能解析时明确说明限制。
- 纯白和纯黑、调色板风格等属于设计建议，不得伪装成 WCAG 失败。
3. 语义与结构
- 标题层级应连续、可理解，通常只有一个页面级主标题；不要把视觉字号当成语义层级。
- 优先使用原生元素：操作用
<button>，导航用<a href>，表单控件关联<label>。 - 有意义图片提供说明用途的
alt；装饰图片使用alt=""。 - 表单不能只依赖 placeholder 充当标签。
- 原生 HTML 能表达语义时不要用 ARIA 重新造轮子；检查角色、名称、状态和值是否一致。
4. 键盘与焦点
- 所有可操作元素都能按合理顺序通过键盘到达，不使用大于
0的tabindex修补顺序。 - 对话框支持焦点进入、约束与恢复，并能按 Escape 关闭；菜单、选项卡等遵循对应键盘模式。
- 焦点指示必须可见。删除默认轮廓时必须提供可靠替代；
2px轮廓和明显对比可作为强健目标，但标注其与 AA/AAA 门槛的区别。 - 长页面或重复导航较多时检查“跳到主要内容”链接。
5. 动效、表单与点击目标
- 尊重
prefers-reduced-motion；避免每秒闪烁三次以上，并为持续动效提供停止方式。 - 错误信息具体、与字段关联并可被辅助技术读取；必填状态不能只靠颜色。
- 使用合适的
type、autocomplete和输入提示，避免妨碍密码管理器或移动键盘。 - WCAG 2.2 AA 的点击目标通常至少容纳
24×24 CSS px，或满足相应间距/等效控件等例外；触屏界面优先采用44×44 CSS px的增强目标。
6. 输出与验证
按“阻塞 / 重要 / 建议”分组。每条发现包含文件与行号、失败机制、适用标准、修复方向和验证方式，合并重复项并删除低置信度猜测。
若获准修复：先处理阻塞项，再处理重要项；完成后重新检查对比度、键盘路径、焦点、表单错误和响应式布局。最后汇总已修复、未修复及无法验证的项目。
示例
输入：“审查这个注册表单的 WCAG 2.2 AA 问题，只给报告。”
**输出：**报告指出提交控件使用不可聚焦的 <div onclick>、输入框缺少关联标签、辅助文字对比度仅 2.8:1；分别给出代码位置、AA 要求和修复建议，但不修改文件。
来源与许可
本 Skill 基于 Trystan Sarrade 的 claude-design-system-prompt 进行中文化与 Claude Skill 规范适配。上游与本改编均按 MIT License 发布，详见 LICENSE.txt。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 65 lines · 100 tokens per session scan A 2497dc905d63
accessibility-audit is a skill published in the GitHub repository Onevium/awesome-claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,135 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.