Rgaa Information Structure logo

Rgaa Information Structure

Community
MTeelokee
rgaa-information-structure

Audit a web page for RGAA v4.1.2 Theme 9 – Information structure accessibility compliance. Checks that headings are used to structure information, the document structure is coherent (header/nav/main/footer landmarks), lists use proper markup (ul/ol/dl), and quotations are correctly marked up. Use this skill when someone asks to check heading structure, landmark regions, semantic HTML structure, RGAA Theme 9, or content organization accessibility.

Overview

PublisherMTeelokee
Repositoryrgaa-accessibility-audit
Skill namergaa-information-structure
Stars
6
Forks
1
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MTeelokee on GitHub. Read the source before you install it.

Installation

Install the Rgaa Information Structure 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/MTeelokee/rgaa-accessibility-audit/tree/main/skills/rgaa-information-structure
  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/MTeelokee/rgaa-accessibility-audit.git /tmp/rgaa-accessibility-audit
mkdir -p .claude/skills
cp -r /tmp/rgaa-accessibility-audit/skills/rgaa-information-structure .claude/skills/rgaa-information-structure
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rgaa Information Structure 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 Rgaa Information Structure 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 Rgaa Information Structure 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.

RGAA Information Structure Accessibility Audit (Theme 9)

Audits a web page against the 4 criteria of RGAA v4.1.2 Theme 9: Information Structure.

Audit procedure

Step 1: Gather structural data

javascript
(() => {
  const structure = {};

  // Headings hierarchy
  structure.headings = [];
  document.querySelectorAll('h1,h2,h3,h4,h5,h6,[role="heading"]').forEach(el => {
    const level = el.tagName?.match(/H(\d)/)?.[1] || el.getAttribute('aria-level');
    structure.headings.push({
      level: parseInt(level),
      text: el.textContent.trim().substring(0, 80),
      tag: el.tagName.toLowerCase(),
      ariaLevel: el.getAttribute('aria-level'),
      isHidden: getComputedStyle(el).display === 'none' || getComputedStyle(el).visibility === 'hidden',
      ariaHidden: el.getAttribute('aria-hidden')
    });
  });

  // Landmark regions
  structure.landmarks = [];
  const landmarkSelectors = {
    'banner': 'header, [role="banner"]',
    'navigation': 'nav, [role="navigation"]',
    'main': 'main, [role="main"]',
    'contentinfo': 'footer, [role="contentinfo"]',
    'complementary': 'aside, [role="complementary"]',
    'search': '[role="search"], search',
    'form': '[role="form"]',
    'region': '[role="region"]'
  };

  Object.entries(landmarkSelectors).forEach(([type, selector]) => {
    document.querySelectorAll(selector).forEach(el => {
      structure.landmarks.push({
        type: type,
        tag: el.tagName.toLowerCase(),
        role: el.getAttribute('role'),
        ariaLabel: el.getAttribute('aria-label'),
        ariaLabelledby: el.getAttribute('aria-labelledby'),
        text: el.textContent.trim().substring(0, 40)
      });
    });
  });

  // Lists
  structure.lists = {
    ul: document.querySelectorAll('ul').length,
    ol: document.querySelectorAll('ol').length,
    dl: document.querySelectorAll('dl').length,
    liOutsideList: document.querySelectorAll('li:not(ul > li):not(ol > li):not(menu > li)').length,
    dtOutsideDl: document.querySelectorAll('dt:not(dl > dt)').length,
    ddOutsideDl: document.querySelectorAll('dd:not(dl > dd)').length,
    roleList: document.querySelectorAll('[role="list"]').length,
    roleListitem: document.querySelectorAll('[role="listitem"]').length
  };

  // Quotations
  structure.quotations = {
    blockquote: document.querySelectorAll('blockquote').length,
    q: document.querySelectorAll('q').length,
    cite: document.querySelectorAll('cite').length
  };

  return JSON.stringify(structure, null, 2);
})()

Step 2: Evaluate criteria

Criterion 9.1 – Information is structured by appropriate use of headings.

Check heading hierarchy:

  • There should be at least one <h1> on the page
  • Heading levels should not skip (e.g., h1 → h3 without h2)
  • Headings should reflect the actual content organization
  • Content sections should start with a heading
  • Headings should not be empty

Criterion 9.2 – Document structure is coherent.

Check landmarks/sectioning:

  • The page has a <header> or [role="banner"]
  • The page has a <nav> or [role="navigation"] (at least one)
  • The page has a <main> or [role="main"] (exactly one)
  • The page has a <footer> or [role="contentinfo"]
  • Multiple landmarks of the same type have distinguishing aria-label values
  • The <main> is not nested inside another landmark (except the document itself)
  • Content outside landmarks should be minimal

Criterion 9.3 – Lists are correctly structured.

  • Unordered lists use <ul> > <li>
  • Ordered lists use <ol> > <li>
  • Definition lists use <dl> > <dt> + <dd>
  • No <li> outside of <ul>, <ol>, or <menu>
  • No <dt> or <dd> outside of <dl>
  • [role="list"] contains [role="listitem"] children
  • Visual lists (items separated by line breaks or commas) that represent a list of items should use proper list markup

Criterion 9.4 – Quotations are correctly marked up.

  • Block quotations use <blockquote>
  • Inline quotations use <q>
  • <blockquote> and <q> are not used for non-quotation purposes (like indentation)
  • The cite attribute references the source when applicable

Step 3: Generate report

Present the heading tree visually (indented by level), list all landmarks, and flag any structural issues.

WCAG references: 9.1.3.1 (A), 9.2.4.1 (A), 9.2.4.6 (AA), 9.2.4.10 (AAA)

Frequently asked questions

What does the Rgaa Information Structure AI skill do?

Audit a web page for RGAA v4.1.2 Theme 9 – Information structure accessibility compliance. Checks that headings are used to structure information, the document structure is coherent (header/nav/main/footer landmarks), lists use proper markup (ul/ol/dl), and quotations are correctly marked up. Use this skill when someone asks to check heading structure, landmark regions, semantic HTML structure, RGAA Theme 9, or content organization accessibility.

Why use Rgaa Information Structure on TypingMind?

Because you install it once and use it with any model. Rgaa Information Structure 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 Rgaa Information Structure in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MTeelokee/rgaa-accessibility-audit/tree/main/skills/rgaa-information-structure. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rgaa Information Structure?

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 Rgaa Information Structure?

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

Is the Rgaa Information Structure AI skill free?

Yes. It is published on GitHub by MTeelokee 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 👇