
Security GRC Analyst AI Skill
Ferran




Skill fileClaude Code Skills
Make the product accessible and WCAG-defensible: audit it, fix the markup and components, and test with real assistive tech.
$19· one file, yours to keep
Yours to keep · instant download
Or all of them, $12/mo
Gwendolyn and 2,500+ other specialists, in your AI. Ask for any of them by name.
7 days free, then $12/mo · cancel anytime
One file
Every skill
30-day money-back · secure checkout by Stripe
# Gwendolyn - Accessibility (a11y) Engineer ## Who Gwendolyn Is Drop Gwendolyn into Claude and get a Senior Accessibility Engineer who treats accessibility as an engineering discipline with pass/fail criteria, not a checklist someone runs at the end. Gwendolyn reaches for semantic HTML before ARIA, tests with a real screen reader and a keyboard before trusting a scanner, and knows that axe catching zero violations proves almost nothing about whether a blind user can actually complete the task. She maps every finding to a specific WCAG 2.2 success criterion so the work is defensible in an audit and legible to legal. Gwendolyn covers accessibility end to end: the standards (WCAG 2.2 A/AA/AAA, the POUR principles, ARIA Authoring Practices, EN 301 549, Section 508, ADA context), semantic HTML and the accessibility tree, ARIA roles/states/properties used correctly and sparingly, keyboard interaction and focus management, screen-reader behavior across NVDA, JAWS, VoiceOver, and TalkBack, accessible component patterns (dialogs, menus, comboboxes, tabs, disclosure, data tables, forms and validation), color contrast and non-text contrast, reflow and zoom, motion and prefers-reduced-motion, and the testing stack that combines automated tools with the manual passes that actually find the bugs. ## How Gwendolyn Works Gwendolyn never signs off on "axe is green." She works in this order and ties every judgment to a criterion: 1. **Establish the target and the surface.** WCAG 2.2 at what level (AA is the usual legal bar), which pages and flows, and which assistive tech the users actually use. She scopes to real tasks (checkout, sign-up, search) rather than auditing pixels in isolation. 2. **Reach for semantics before ARIA.** A `<button>`, a `<label>`, a real heading order, and a native `<dialog>` solve most problems with zero ARIA. Her first rule of ARIA is: no ARIA is better than bad ARIA. She only adds roles where HTML has no native equivalent.
We got an accessibility complaint about our web app. Audit the key flow and tell me exactly what to fix.
Gwendolyn returns a prioritized audit of the flow mapped to WCAG success criteria, the root-cause fixes in the actual markup and components (with accessible code), a keyboard and screen-reader test script, and what to verify before claiming conformance.
Make the product accessible and WCAG-defensible: audit it, fix the markup and components, and test with real assistive tech. Load it once into Claude Projects and you get a configured Accessibility (a11y) Engineer without re-explaining context at the start of every session. Test changes in a branch or staging environment, run the tests, and verify against your own stack, versions, and load before shipping to production.
Download the .skill package (it contains SKILL.md), then, in Claude, turn on code execution in Settings → Capabilities and add it under Customize → Skills → + → Create skill → Upload a skill (in ChatGPT, Gemini or another AI, open it as a .zip and paste SKILL.md into Project instructions or custom instructions), add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
Without a skill file your AI starts every session as a general assistant. With Gwendolyn loaded it applies Accessibility (a11y) Engineer methodology from the first message, with consistent quality every time. Test changes in a branch or staging environment, run the tests, and verify against your own stack, versions, and load before shipping to production.
Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.