Skip to content
Automation
Skill

/ui-a11y

Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe.

From plugin
lihongwei-cn
5200 skills1 agent
Install
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill ui-a11y --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/ui-a11y

Context preview

The summary Claude sees to decide when to auto-load this skill.

Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe.

SKILL.md

ui-a11y.SKILL.md
name: ui-a11y
description: "Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe."
category: design
risk: safe
source: community
source_repo: bitjaru/styleseed
source_type: community
date_added: "2026-04-08"
author: bitjaru
tags: [ui, accessibility, wcag, audit, styleseed]
tools: [claude, cursor, codex, gemini]

UI Accessibility Audit

Overview

Part of [StyleSeed](https://github.com/bitjaru/styleseed), this skill audits components and pages for accessibility issues with an emphasis on the Toss seed's mobile UI patterns. It combines WCAG 2.2 AA checks with practical code fixes for touch targets, focus states, contrast, labels, and reduced motion.

When to Use

  • Use when reviewing a page or component for accessibility regressions
  • Use when a StyleSeed UI looks polished but has uncertain keyboard or contrast behavior
  • Use when adding new interactive controls to a mobile-first screen
  • Use when you want a prioritized list of issues and fixable items

Audit Areas

Perceivable

  • text contrast
  • non-text contrast for controls and graphics
  • alt text for images
  • labels for meaningful icons
  • no information conveyed by color alone

Operable

  • touch targets at least 44x44px
  • keyboard reachability for all interactive controls
  • logical tab order
  • visible focus indicators
  • reduced-motion support for nonessential animation

Understandable

  • visible labels or `aria-label` on inputs
  • error text associated with the correct field
  • clear wording for errors and validation
  • document language set appropriately

Robust

  • semantic HTML where possible
  • correct use of ARIA when semantics alone are insufficient
  • no faux buttons or links without the right roles and behavior

Output

Return: 1. Issues found, grouped by severity 2. Safe autofixes that can be applied directly 3. Items that need manual review or product judgment 4. A short summary of the accessibility risk level

Best Practices

  • Fix semantics before layering on ARIA
  • Use the design system tokens only if they still meet contrast requirements
  • Treat touch target failures as real usability defects, not polish issues
  • Prefer partial, verified fixes over speculative accessibility changes

Additional Resources

  • [StyleSeed repository](https://github.com/bitjaru/styleseed)
  • [Source skill](https://github.com/bitjaru/styleseed/blob/main/seeds/toss/.claude/skills/ui-a11y/SKILL.md)

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Read more
Ships withlihongwei-cn

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

Get the whole plugin
Stats
5
Stars
1
Forks
Maintained
Maintenance
Python
Language
MIT
License
1mo ago
Last commit
4mo ago
Created

Repo: LiHongwei-cn/lihongwei-cn

Other skills on lihongwei-cn.

cheat-on-content
Skill

cheat-on-content

给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…

cheat-bump
Skill

cheat-bump

提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…

cheat-init
Skill

cheat-init

cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…

cheat-migrate
Skill

cheat-migrate

把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…

cheat-persona
Skill

cheat-persona

从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…