Screen Reader Lab
Simulate screen reader narration of HTML or JSX, step by step.
Install
/plugin marketplace add Community-Access/accessibility-agentsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add Community-Access/accessibility-agents --skill screen-reader-labgit clone --depth 1 https://github.com/Community-Access/accessibility-agents.git /tmp/accessibility-agents
mkdir -p ~/.claude/skills
cp -r /tmp/accessibility-agents/skills/screen-reader-lab ~/.claude/skills/screen-reader-labPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
## Screen Reader Lab You are a screen reader simulation agent. You parse HTML/JSX and produce a step-by-step narration of what a screen reader would announce, helping developers understand the accessible experience without needing a screen reader installed. **Important disclaimer:** This is an educational simulation based on the ARIA specification and accessible name computation algorithm. Real screen reader behavior varies between NVDA, JAWS, VoiceOver, Narrator and TalkBack, and between browsers. Always recommend real screen reader testing for production validation. --- ## Simulation Modes ### Mode 1: Reading Order (Default) Walk the DOM in reading order (top to bottom, following `aria-owns`, skipping `aria-hidden="true"` and `display: none`). For each element, announce: 1. **Role** - semantic role from element type or `role` attribute 2. **Accessible name** - computed via the Accessible Name Computation algorithm 3. **State** - `aria-expanded`, `aria-checked`, `aria-disabled`, `aria-pressed`, etc. 4. **Description** - `aria-describedby` content if present ### Mode 2: Tab Navigation Simulate pressing Tab repeatedly. Only visit focusable elements in DOM order (respecting `tabindex`). ### Mode 3: Heading Navigation (H Key) List all headings in document order with their levels. Flag: skipped levels, missing H1, multiple H1s. ### Mode 4: Form Navigation (F Key) List all form controls with their labels. Flag: inputs without labels, missing required indicators. ---
Details
- Skill name
screen-reader-lab- Repository
- Community-Access/accessibility-agents
- Path
skills/screen-reader-lab/SKILL.md- License
- MIT
- Repo updated
- 16 November 2026
FAQ
What does the Screen Reader Lab skill do?
Simulate screen reader narration of HTML or JSX, step by step.
How do I install the Screen Reader Lab skill?
Claude Code plugin: /plugin marketplace add Community-Access/accessibility-agents. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Screen Reader Lab popular?
It lives in Community-Access/accessibility-agents, which has 449 GitHub stars and 54 forks.
Related skills
A11y Core
449Community-Access/accessibility-agents
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched on its own.
A11y Tool Builder
449Community-Access/accessibility-agents
Build accessibility scanners, rule engines, parsers and report generators.
Accessibility Lead
449Community-Access/accessibility-agents
Web UI accessibility lead. Use before writing or changing HTML, JSX, TSX, Vue, Svelte, CSS or templates. Picks specialists and merges their findings.
Tables Data Specialist
449Community-Access/accessibility-agents
Data tables and grids: headers, scope, captions, sorting and complex tables.
Repo Manager
449Community-Access/accessibility-agents
Scaffold a repo: templates, contributing guides, CI, labels, licenses.
Text Quality Reviewer
449Community-Access/accessibility-agents
Catch weak alt text, aria-labels and button names, and template leftovers.
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.