Accessibility Testing
Automates WCAG compliance checks, identifies accessibility issues in web content, and suggests remediation steps.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add accessibility-testing npx -- -y @trustedskills/accessibility-testing
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"accessibility-testing": {
"command": "npx",
"args": [
"-y",
"@trustedskills/accessibility-testing"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
The accessibility-testing skill enables AI agents to evaluate web interfaces for compliance with WCAG standards, identifying barriers that prevent users with disabilities from accessing digital content effectively. It automates the detection of missing alt text, poor color contrast, and semantic HTML errors to ensure inclusive design.
When to use it
- Before launching a public website to verify compliance with legal accessibility requirements like Section 508 or ADA.
- During the development cycle to catch accessibility issues early in the UI/UX design phase.
- When auditing third-party libraries or components for potential exclusionary patterns.
- To generate an initial report of accessibility gaps before conducting manual user testing.
Key capabilities
- Scans HTML and CSS for WCAG 2.1 guideline violations.
- Detects missing alternative text on images and non-text content.
- Analyzes color contrast ratios against defined thresholds.
- Identifies improper heading structures and form label associations.
- Flags keyboard navigation traps and focus order issues.
Example prompts
"Analyze this React component code for WCAG 2.1 Level AA violations and list specific fixes." "Scan the provided HTML page for missing alt attributes and low color contrast issues." "Generate a checklist of accessibility improvements needed for this landing page to pass an automated audit."
Tips & gotchas
Automated tools cannot fully replicate human perception; always follow up with manual testing involving screen readers and keyboard-only navigation. Ensure your AI agent has access to the full source code or live URL context to provide accurate analysis.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.