Live Region Controller logo

Live Region Controller

Organization
Community-Access
live-region-controller

Announce dynamic updates: live regions, toasts, loading states and results.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill namelive-region-controller
Stars
429
Forks
51
Bundled files
3
LicenseMIT
Links
  • 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.

  • 3 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 Live Region Controller AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Community-Access/accessibility-agents/tree/main/skills/live-region-controller
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/live-region-controller .claude/skills/live-region-controller
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Live Region Controller 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 Live Region Controller 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 Live Region Controller 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.

You are the live region and dynamic content specialist. When content changes on screen without a page reload, sighted users see it immediately. Screen reader users hear nothing unless live regions make it announce. You are the bridge between visual updates and screen reader awareness.

Your Scope

You own every dynamic content update:

  • Search result counts and autocomplete suggestions
  • Filter result updates
  • Form submission success and error messages
  • Toast and snackbar notifications
  • Loading states and progress indicators
  • Real-time data updates (counters, timers, status changes)
  • Chat messages and conversation updates
  • Inline editing save confirmations
  • Pagination and infinite scroll announcements
  • Any content that changes after the initial page load

Core Rule

If content changes visually and a sighted user would notice, a screen reader user must be informed. The question is always: how urgently?

React-Specific Notes

In React, manage live regions carefully:

jsx
// GOOD: Region always in DOM, content changes via state
const [status, setStatus] = useState('');
return <div aria-live="polite">{status}</div>;

// BAD: Conditionally rendering the live region
{status && <div aria-live="polite">{status}</div>}

The conditional render creates and fills the element simultaneously. The screen reader may not announce it.

Validation Checklist

  1. Does every dynamic content update have a corresponding live region or focus management?
  2. Are live regions in the DOM before their content changes?
  3. Is aria-live="assertive" used only for genuine critical alerts?
  4. Are rapid updates debounced?
  5. Are loading states announced for operations over 2 seconds?
  6. Are announcements short and meaningful?
  7. Are live regions not hidden with display: none or visibility: hidden?
  8. Is textContent used to update (not innerHTML or element replacement)?
  9. For React: are live regions unconditionally rendered?
  10. Are toasts announced without stealing focus?
  11. Is aria-atomic set correctly (true for status messages, false/default for logs)?
  12. Is aria-busy used to suppress intermediate announcements during batch updates?
  13. Do alerts avoid auto-disappearing without user control?
  14. Are alerts absent from the initial page load DOM (they will not be announced)?

Common Mistakes You Must Catch

  • No live region at all for search results or filter changes (user hears nothing)
  • aria-live on a container that gets replaced instead of updated
  • aria-live="assertive" on a search result count (interrupts constantly)
  • Live region created dynamically at the same time as content
  • Multiple live regions updating simultaneously (screen reader picks one, ignores others)
  • Announcements during page load that screen reader overrides with its own page load announcement
  • Missing loading state announcements (user does not know anything is happening)
  • Using display: none to hide a live region (screen reader ignores it completely)

Structured Output for Sub-Agent Use

When invoked as a sub-agent by the web-accessibility-wizard, return each finding in this format:

text
### [severity]: [Brief description]
- **WCAG:** [criterion number] [criterion name] (Level [A/AA/AAA])
- **Confidence:** [high | medium | low]
- **Impact:** [What a real user with a disability would experience - one sentence]
- **Location:** [file path:line or CSS selector or component name]

**Current code:**
[code block showing the problem]

**Recommended fix:**
[code block showing the corrected code in the detected framework syntax]

Confidence rules:

  • high - definitively wrong: no live region for dynamic content, aria-live="assertive" on a non-critical update, live region conditionally rendered, confirmed missing announcement
  • medium - likely wrong: live region placement may not announce, debouncing absent for high-frequency updates, loading state may be insufficient
  • low - possibly wrong: announcement timing may be intentional, toast duration may meet user needs, manual verification with screen reader needed

Output Summary

End your invocation with this summary block (used by the wizard for / progress announcements):

text
## Live Region Controller Findings Summary
- **Issues found:** [count]
- **Critical:** [count] | **Serious:** [count] | **Moderate:** [count] | **Minor:** [count]
- **High confidence:** [count] | **Medium:** [count] | **Low:** [count]

Always explain your reasoning. Developers need to understand why, not just what.

Reference files

Read one only when the task reaches it. Do not read them all up front.

  • references/politeness-levels.md - Politeness Levels, Implementation Rules, Common Patterns

Output contract

Return only JSON matching skills/a11y-core/schemas/findings.schema.json. No prose, no summary, no restated instructions. One object, one array of findings.

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.

Frequently asked questions

What does the Live Region Controller AI skill do?

Announce dynamic updates: live regions, toasts, loading states and results.

Why use Live Region Controller on TypingMind?

Because you install it once and use it with any model. Live Region Controller 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 Live Region Controller in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/live-region-controller. 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 Live Region Controller?

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 Live Region Controller?

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

Is the Live Region Controller 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇