Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    wcag accessibility auditor

    1

    Audit web apps for WCAG 2.2 compliance with prioritized remediation reports and code-level fixes.

    $14.29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    wcag accessibility auditor

    wcag accessibility auditor

    Example session with this skill installed

    Can you audit this React modal component for WCAG compliance? It uses a div with an onClick handler for the close button. [code snippet attached]

    • Read your context and instructions
    • Compiled the wcag accessibility auditor

    The modal fails WCAG 2.1.1 (Keyboard) and 4.1.2 (Name, Role, Value).

    Severity: Critical.
    Issue: Using a <div> with onClick instead of a <button> makes the close action unreachable via keyboard.

    Fix

    1. Change <div> to <button>.
    2. Add aria-label="Close".
    3. Implement an onKeyDown listener for the Escape key to close the modal.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Automated accessibility scans only catch about 30% of failures, leaving sites vulnerable to legal risk and unusable for many users. Developers often get buried in hundreds of minor warnings without knowing which ones actually block a user from completing a checkout or signup.

    What it does

    • Audits URLs, HTML, JSX, or Vue templates against WCAG 2.2 AA standards.
    • Categorizes findings by POUR principles (Perceivable, Operable, Understandable, Robust).
    • Prioritizes issues by actual user impact and legal exposure — not raw error counts.
    • Provides code-level remediation for complex ARIA patterns, keyboard traps, and focus management.
    • Flags gaps automated tools like axe-core or Lighthouse structurally miss, such as logical focus order and meaningful (not just present) alt text.

    Frameworks & tools

    Works with React, Vue, JSX, and raw HTML. References axe-core, Lighthouse, WAVE, and the WAI-ARIA Authoring Practices Guide.

    Why this beats prompting it yourself

    General LLMs often suggest "best guess" accessibility fixes that break ARIA semantics or ignore keyboard navigation entirely. This skill enforces strict WCAG 2.2 success-criterion citations and a systematic audit framework so no category — from color contrast to focus traps — gets skipped.

    Use cases

    • Reviewing pull requests for accessibility regressions before they ship.
    • Converting raw axe-core JSON reports into prioritized executive summaries.
    • Auditing custom UI components like modals and dropdowns for keyboard parity.
    • Preparing a site for ADA Title II/III or Section 508 compliance.

    Known limitations

    Cannot perform live screen reader testing. For the most accurate analysis of a live URL, provide HTML source or an axe-core/Lighthouse export rather than just a link.

    Cannot perform physical screen reader testing. Requires HTML source or automated tool exports (axe/Lighthouse) for the most accurate analysis of live sites.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    Requires

    @axe-core/cli
    Node.js

    Permissions

    Read Files
    Listed2 months ago
    Updated23 days ago

    What's inside

    Frequently Asked Questions

    While tools like Lighthouse catch basic errors, this skill identifies complex failures like logical focus order, keyboard traps, and ARIA semantic errors that automated scanners structurally miss.

    The skill is designed for frontend developers and supports raw HTML, JSX (React), and Vue templates, providing specific code-level remediation for these frameworks.

    No, you can simply provide HTML snippets, UI component code, or even export data from existing scanners to receive a prioritized remediation report.

    You will receive the AI agent skill, a systematic audit framework, and instructions on how to integrate it into your existing development workflow or PR review process.

    Yes, the skill is updated to reflect the latest WCAG 2.2 AA standards, ensuring your applications remain compliant with current legal requirements and accessibility best practices.

    While it provides deep code analysis, it cannot simulate live screen reader interactions; it is best used to prepare code for final human-led assistive technology testing.

    New in Agents & Orchestration