メニュー
Scan a frontend project for WCAG 2.2 accessibility violations and fix them. Usage: /a11y-audit [path]
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
A brief description of what this skill does
Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending
Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost anal...
Answer Engine Optimization (AEO) specialist agent. Use when content needs to be optimized for citation by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) rather than for traditional search rankings. Orchestrates the aeo skill — runs E-E-A-T audit, generates optimization variants in conservative/balanced/aggressive modes, and maintains a citation tracking ledger. Industry-aware (8 industries with calibrated thresholds). Distinguishes AEO from SEO and refuses to optimize for one channel at the expense of the other. Voice — pragmatic content strategist; respects existing SEO investments; insists on real first-person evidence over fabricated authority signals.
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimi...
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to ...
| name | a11y-audit |
| description | Scan a frontend project for WCAG 2.2 accessibility violations and fix them. Usage: /a11y-audit [path] |
| argument-hint | [path] |
Scan a frontend project for WCAG 2.2 accessibility issues, show fixes, and optionally check color contrast.
/a11y-audit # Scan current project
/a11y-audit ./src # Scan specific directory
/a11y-audit ./src --fix # Scan and auto-fix what's possible
Run the a11y scanner on the target directory:
python3 {skill_path}/scripts/a11y_scanner.py {path} --json
Parse the JSON output. Group findings by severity (critical → serious → moderate → minor).
Display a summary:
A11y Audit: ./src
Critical: 3 | Serious: 7 | Moderate: 12 | Minor: 5
Files scanned: 42 | Files with issues: 15
For each finding (starting with critical):
engineering-team/a11y-audit/skills/a11y-audit/references/framework-a11y-patterns.mdAuto-fixable issues (apply without asking):
alt="" on decorative imageslang attribute on <html>tabindex values > 0 → set to 0type="button" on non-submit buttons:focus-visible stylesIssues requiring user input (show fix, ask to apply):
If CSS files are present, run the contrast checker:
python3 {skill_path}/scripts/contrast_checker.py --batch {path}
For each failing color pair, suggest accessible alternatives.
Generate a markdown report at a11y-report.md:
engineering-team/a11y-audit/skills/a11y-audit/SKILL.mdengineering-team/a11y-audit/skills/a11y-audit/scripts/a11y_scanner.pyengineering-team/a11y-audit/skills/a11y-audit/scripts/contrast_checker.pyengineering-team/a11y-audit/skills/a11y-audit/references/wcag-quick-ref.mdengineering-team/a11y-audit/skills/a11y-audit/references/aria-patterns.mdengineering-team/a11y-audit/skills/a11y-audit/references/framework-a11y-patterns.md