Front A11y logo

Front A11y

Community
Effeilo
front-a11y

Audit or fix accessibility issues (WCAG 2.1 AA) in HTML, Vue, Svelte, or Astro files. Checks images, ARIA, keyboard navigation, forms, and semantic HTML. Usage: /front-a11y [fix]

Overview

PublisherEffeilo
Repositoryclaude-code-frontend-skills
Skill namefront-a11y
Stars
3
Forks
0
Bundled files
14
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.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Front A11y 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/Effeilo/claude-code-frontend-skills/tree/main/front-a11y
  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/Effeilo/claude-code-frontend-skills.git /tmp/claude-code-frontend-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-frontend-skills/front-a11y .claude/skills/front-a11y
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Front A11y 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 Front A11y 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 Front A11y 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.

Audit or fix accessibility issues in the file that is currently open or explicitly mentioned by the user.

  • Default (no arguments): Audit mode : analyse the file and produce a structured report of all accessibility issues found.
  • If $ARGUMENTS contains fix: Fix mode : apply all automatically-fixable issues directly to the file, then report what was fixed and what requires manual attention.

Step 1 : Detect the file language

Look at the extension of the target file:

  • If .html → the language file is front-a11y-html.md
  • If .jsx or .tsx → the language file is front-a11y-jsx.md
  • If .vue → the language file is front-a11y-vue.md
  • If .svelte → the language file is front-a11y-svelte.md
  • If .astro → the language file is front-a11y-astro.md
  • Otherwise → inform the user that this file type is not supported. Supported types: .html, .jsx, .tsx, .vue, .svelte, .astro.

The path of this skill file is always available from context. Resolve all sub-file paths relative to it.


Step 2 : Load the shared rules

Read front-a11y-rules.md (located in the same directory as this skill file). It contains all accessibility rules, their severity levels, detection criteria, and fix instructions.


Step 3 : Load the language-specific notes

Read the language file identified in Step 1 (located in the same directory as this skill file). It contains syntax notes for that language, detection nuances that override or extend the shared rules, and framework-specific additional rules.


Step 4 : Apply both

Apply all rules from front-a11y-rules.md, adjusted by the syntax notes and detection nuances from the language file. Then apply the framework-specific rules from the language file.


Output rules

Audit mode

  • Do not modify the file.
  • Output a structured accessibility report using this format:
## Accessibility Audit : filename.ext

### 🔴 Critical
**[line N] Short issue title**
Element: `<img src="hero.jpg">`
Problem: The `alt` attribute is missing.
Fix: Add `alt="[description]"` for meaningful images, or `alt=""` for decorative ones.

---

### 🟠 Major
...

### 🟡 Minor
...

---

### Summary
| Severity | Count |
|---|---|
| 🔴 Critical | N |
| 🟠 Major | N |
| 🟡 Minor | N |
| **Total** | **N** |
  • Group issues by severity: Critical → Major → Minor.
  • If a severity has no issues, omit that section.

Fix mode

  • Apply all automatically-fixable issues directly to the file.
  • Output the complete corrected file : do not truncate.
  • Preserve all original formatting and indentation.
  • After the file, output a Fix Report:
## Fix Report : filename.ext

### ✅ Fixed
- [line N] Short description of applied fix
- ...

### ⚠️ Requires manual attention
- [line N] Short description + suggested action
- ...

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 Front A11y AI skill do?

Audit or fix accessibility issues (WCAG 2.1 AA) in HTML, Vue, Svelte, or Astro files. Checks images, ARIA, keyboard navigation, forms, and semantic HTML. Usage: /front-a11y [fix]

Why use Front A11y on TypingMind?

Because you install it once and use it with any model. Front A11y 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 Front A11y in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Effeilo/claude-code-frontend-skills/tree/main/front-a11y. 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 Front A11y?

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 Front A11y?

As many as you like. As long as a model supports skills, you can use Front A11y with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Front A11y AI skill free?

It is published on GitHub by Effeilo. Check the repository for licensing terms. 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 👇