claudex
cskiro/claudex
Conducts thorough WCAG 2.2 Level AA accessibility audits for React and TypeScript applications with specialized MUI framework awareness. It applies risk-based severity scoring rather than strict conformance levels to prioritize real-world impact.
7 3No licenseUpdated 2026-02-13
61
GoodOverview
The accessibility-audit skill provides a systematic approach for evaluating web applications against accessibility standards. It coordinates static analysis using ESLint rules, runtime verification through axe-core and Playwright, and manual validation workflows. Built-in awareness of Material-UI (MUI) components prevents common false positives, while a custom impact-by-likelihood scoring rubric helps developers focus on critical user barriers first.
Capabilities
- ▸WCAG 2.2 Level AA compliance auditing
- ▸Static code analysis via eslint-plugin-jsx-a11y
- ▸Runtime verification using jest-axe and Playwright
- ▸MUI framework false-positive filtering
- ▸Risk-based severity scoring (Impact x Likelihood)
- ▸Manual keyboard navigation and screen reader testing guidance
Best for
Performing pre-release WCAG 2.2 Level AA compliance checks on React applications, Identifying keyboard traps, screen reader issues, and contrast failures in MUI-based user interfaces, Generating structured accessibility audit reports in Markdown and JSON formats
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
61Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%50 → +7.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%37 → +4.4
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%75 → +7.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%29 → +2.3
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total71.5 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Static and runtime scanning tools execute locally against the codebase without transmitting sensitive source code externally.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.