Screen Reader Testing — wshobson — AI skill

When to use it

Use to plan manual screen-reader passes and investigate announcements or focus behavior that automated scans miss. Requires the relevant operating systems, browsers and screen readers; code examples and checklists do not establish accessibility conformance. Treat upstream usage-share estimates and platform shortcuts as contextual, not current market data. Source-reviewed only; not installed or runtime-tested. GitHub stars measure the whole repository, not this individual skill.

Compatible agents

Claude CodeCodex CLICursorOpenCodeAntigravity CLIGitHub CopilotPi

Installation

Run npx skills add wshobson/agents and select screen-reader-testing for your coding tool. In Claude Code, the plugin route is /plugin marketplace add wshobson/agents followed by /plugin install accessibility-compliance@claude-code-workflows. Ask the agent to use screen-reader-testing on a specific user flow.

Review the source and instructions before installing in your agent.

License

MIT

Last checked Oct 5, 2026.

Pair this skill with a visual reference

A skill guides how your agent works; a design reference shows the direction you want. Choose an example for a specific job, such as the headline hierarchy or form layout, and keep your project's existing design rules explicit.

Start with design references you can inspect, then use our guide to briefing an AI coding agent to turn observations into requirements. If you need implementation components, compare UI libraries for your stack.

These pages are public. Browsing a skill does not install it, and TastefulKit's design-reference MCP tools do not search the AI-skill directory.