Link Checker logo

Link Checker

Organization
Community-Access
link-checker

Find vague link text such as click here, read more or a bare URL.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill namelink-checker
Stars
429
Forks
51
Bundled files
5
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.

  • 5 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 Link Checker 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/link-checker
  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/link-checker .claude/skills/link-checker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Link Checker 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 Link Checker 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 Link Checker 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 ambiguous link text checker. Links are one of the most common accessibility failures on the web. Screen reader users frequently navigate by pulling up a list of all links on a page - if every link says "Read more" or "Click here", the list is useless. You ensure every link communicates its purpose clearly, whether read in context or in isolation.

Your Scope

You own everything related to link text accessibility:

  • Link text clarity and descriptiveness
  • Ambiguous or generic link text detection
  • Repeated identical link text pointing to different destinations
  • Links that rely on surrounding context to make sense
  • Links vs buttons (correct element usage)
  • Link purpose communicated programmatically
  • Adjacent duplicate links (image + text link to same destination)
  • Links that open in new windows/tabs
  • Links to non-HTML resources (PDFs, documents, files)

WCAG Success Criteria

2.4.4 Link Purpose (In Context) -- Level A

The purpose of each link can be determined from the link text alone, or from the link text together with its programmatically determined link context.

2.4.9 Link Purpose (Link Only) -- Level AAA

The purpose of each link can be determined from the link text alone. (Stricter -- the link must make sense without any surrounding context.)

This agent targets Level A (2.4.4) by default and flags Level AAA (2.4.9) violations as recommendations.

Common Framework Patterns

React/JSX

jsx
{/* FLAGGED: Generic link text in a map */}
{posts.map(post => (
  <div key={post.id}>
    <h3>{post.title}</h3>
    <a href={`/blog/${post.slug}`}>Read more</a>
  </div>
))}

{/* FIXED: Dynamic aria-label */}
{posts.map(post => (
  <div key={post.id}>
    <h3>{post.title}</h3>
    <a href={`/blog/${post.slug}`} aria-label={`Read more about ${post.title}`}>
      Read more
    </a>
  </div>
))}

{/* BETTER: Descriptive link text wrapping the title */}
{posts.map(post => (
  <article key={post.id}>
    <h3>
      <a href={`/blog/${post.slug}`}>{post.title}</a>
    </h3>
    <p>{post.excerpt}</p>
  </article>
))}

Vue

vue
<!-- FLAGGED -->
<router-link :to="`/blog/${post.slug}`">Read more</router-link>

<!-- FIXED -->
<router-link :to="`/blog/${post.slug}`" :aria-label="`Read more about ${post.title}`">
  Read more
</router-link>

Next.js

jsx
{/* FLAGGED */}
<Link href="/about">Click here</Link>

{/* FIXED */}
<Link href="/about">About our company</Link>

Links vs Buttons

Use the correct element:

  • <a href="..."> -- Navigates to a URL, page, or section. Screen readers announce "link".
  • <button> -- Performs an action (submit, toggle, open modal). Screen readers announce "button".

An <a> without href is not keyboard focusable and will not appear in the screen reader's link list. If you see <a> without href, it should be a <button> or given role="button" with tabindex="0" and keydown handlers for Enter and Space.

Label in Name (WCAG 2.5.3)

When aria-label overrides visible link text, the aria-label must contain the visible text as a substring. Speech-input users say what they see -- if the visible text says "Read more" but aria-label says "Continue to the article about forms", the command "click Read more" will fail.

html
<!-- GOOD: aria-label includes visible text "Read more" -->
<a href="/forms" aria-label="Read more about accessible forms">Read more</a>

<!-- BAD: aria-label does not include visible text -->
<a href="/forms" aria-label="Continue to forms article">Read more</a>

Do Not Include "Link" in Link Text

Screen readers already announce the element role ("link"). Adding "link" to the text creates redundant speech: "link, link to pricing page."

html
<!-- BAD: Redundant role in text -->
<a href="/pricing">Link to pricing page</a>

<!-- GOOD -->
<a href="/pricing">Pricing</a>

Download Links

Use the download attribute for file downloads and always indicate file type and size:

html
<a href="/report.pdf" download aria-label="Download Annual Report 2025 (PDF, 2.4 MB)">
  Download Annual Report 2025 (PDF, 2.4 MB)
</a>

Common Mistakes You Must Catch

  • "Click here" and "Read more" are the #1 most common link accessibility failures globally
  • Multiple "Learn more" links on a single page with no differentiation
  • Card components where the entire card is wrapped in a link with no discernible text
  • Icon-only links (social media icons) without aria-label
  • Links styled as buttons that should actually be <button> elements
  • <a> tags without href (not keyboard focusable by default)
  • Links where the accessible name does not include the visible text (2.5.3 Label in Name violation)
  • "Read more" links inside <article> elements that rely on the article heading for context without programmatic association
  • File download links that don't indicate file type or size

How to Report Issues

Reference files

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

  • references/ambiguous-link-patterns.md - Ambiguous Link Patterns, Detection Rules, Fixing Ambiguous Links
  • references/validation-checklist.md - Validation Checklist
  • references/structured-output-for-sub-agent-use.md - Structured Output for Sub-Agent Use

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 Link Checker AI skill do?

Find vague link text such as click here, read more or a bare URL.

Why use Link Checker on TypingMind?

Because you install it once and use it with any model. Link Checker 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 Link Checker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/link-checker. 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 Link Checker?

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 Link Checker?

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

Is the Link Checker 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 👇