Is the Screen Reader Testing skill free?

Yes. The skill itself is free from wshobson/agents. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Screen Reader Testing SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Screen Reader Testing?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Screen Reader Testing with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Screen Reader Testing

Screen reader testing playbook for VoiceOver, NVDA, and JAWS with ARIA fixes.

by wshobson · wshobson/agents

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 10, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 18, 2026 · 47d2fdf

Given a modal with an icon-only close button and no dialog role, it produced the exact aria-label and role=dialog fixes plus concrete VoiceOver and NVDA test scripts a generic answer skipped entirely.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Screen Reader Testing does

Reference guide for testing web apps with VoiceOver, NVDA, JAWS, and TalkBack, covering keyboard commands, per-reader test scripts, and a device/browser coverage priority matrix. Triggers when validating screen reader compatibility, debugging ARIA/assistive-tech issues, or checking form and dynamic-content accessibility. Includes copy-paste ARIA fixes for common failures like unlabeled icon buttons, silent live regions, and unannounced form errors.

How to install Screen Reader Testing

git clone https://github.com/wshobson/agents
cd agents
mkdir -p ~/.claude/skills
cp -r plugins/accessibility-compliance/skills/screen-reader-testing ~/.claude/skills/screen-reader-testing

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Screen Reader Testing

/screen-reader-testing Screen reader testing playbook for VoiceOver, NVDA, and JAWS with ARIA fixes.

It also activates on plain-language prompts like these:

Test this form with VoiceOver and NVDA for accessibility issues
Fix this unlabeled icon button so screen readers announce it
Check why this live region isn't being announced by JAWS

Frequently asked questions

Is the Screen Reader Testing skill free?: Yes. The skill itself is free from wshobson/agents. SkillProof publishes the install command and an independent test verdict at no cost.
Does Screen Reader Testing work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Tested · Works. Given a modal with an icon-only close button and no dialog role, it produced the exact aria-label and role=dialog fixes plus concrete VoiceOver and NVDA test scripts a generic answer skipped entirely.
What is the Screen Reader Testing SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Screen Reader Testing?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Screen Reader Testing with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.