Screen Reader Lab

Organization

Community-Access

screen-reader-lab

Simulate screen reader narration of HTML or JSX, step by step.

Overview

Publisher	Community-Access
Repository	`accessibility-agents`
Skill name	`screen-reader-lab`
Stars	429
Forks	51
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Community-Access on GitHub. Read the source before you install it.

Installation

Install the Screen Reader Lab AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Community-Access/accessibility-agents/tree/main/skills/screen-reader-lab
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Community-Access/accessibility-agents/tree/main/skills/screen-reader-lab

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git 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-lab

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Screen Reader Lab in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Screen Reader Lab on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Screen Reader Lab is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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, and Narrator. 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:

Role — semantic role from element type or role attribute
Accessible name — computed via the Accessible Name Computation algorithm
State — aria-expanded, aria-checked, aria-disabled, aria-pressed, etc.
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.

Accessible Name Computation

Follow the algorithm from accname-1.2:

aria-labelledby — concatenate text of referenced elements
aria-label — use directly
Native label association — <label for="id">, wrapping <label>
Element content — text content for <button>, <a>, headings
title attribute — fallback
placeholder — last resort (not recommended)

If no name is computed, annotate: [No accessible name — screen reader will announce role only or skip entirely]

Process

Phase 1 — Input

Ask the user what to simulate (file path, code snippet) and which mode.

Phase 2 — Parse and Simulate

Read the file, parse HTML/JSX, build the accessibility tree, walk in selected mode.

Phase 3 — Findings

Report elements with no accessible name, ARIA issues, tab order problems, heading hierarchy issues, form labeling gaps, and recommended fixes.

Phase 4 — Follow-Up

Offer to run a different mode, simulate a different component, or delegate to aria-specialist or testing-coach.

Output contract

Answer the question. Keep the answer to what was asked, cite the criterion or API by name, and stop. Do not append a checklist that was not requested.

Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md. Authoritative specifications for this skill: skills/a11y-core/references/sources.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB

Frequently asked questions

What does the Screen Reader Lab AI skill do?

Simulate screen reader narration of HTML or JSX, step by step.

Why use Screen Reader Lab on TypingMind?

Because you install it once and use it with any model. Screen Reader Lab is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Screen Reader Lab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/screen-reader-lab. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Screen Reader Lab?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Screen Reader Lab?

As many as you like. As long as a model supports skills, you can use Screen Reader Lab with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Screen Reader Lab AI skill free?

Yes. It is published on GitHub by Community-Access under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Architecture Decision Records

affaan-m

CommunityPopular

コーディングセッション中にアーキテクチャ決定を構造化ADRとして記録し、自動的に決定の瞬間を検出し、コンテキスト、検討された代替案、根拠を記録します。今後の開発者がコードベースの形成理由を理解するためのADRログを維持します。

Automation Audit Ops

ECC用の証拠ベースの自動化インベントリとオーバーラップ監査ワークフロー。ユーザーがどのジョブ、フック、コネクタ、MCPサーバー、またはラッパーがライブか、壊れているか、冗長であるか、修正前に不足しているかを知りたい場合に使用します。

Grok

Delegate coding to xAI Grok Build CLI (features, PRs).

Setup Wizard Generator

NousResearch

OrganizationPopular

Generate a bash wizard guiding a human through manual setup.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Screen Reader Lab

Simulation Modes

Mode 1: Reading Order (Default)

Mode 2: Tab Navigation

Mode 3: Heading Navigation (H Key)

Mode 4: Form Navigation (F Key)

Accessible Name Computation

Process

Phase 1 — Input

Phase 2 — Parse and Simulate

Phase 3 — Findings

Phase 4 — Follow-Up

Output contract

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now