- Home
- Skills
- Frontend & Web Apps
- A11y I18n Rules
A11y I18n Rules
Standardize your front-end for WCAG accessibility and ICU-based internationalization.
$5
Works with the AI Agents you already use
A11y I18n Rules
Example session with this skill installed
- Read your context and instructions
- Compiled the a11y i18n rules
- Generated the UI component
- File: components/Submit.tsx, line 1
- Rule: Semantic HTML block
- Fix: Replace div with a native <button> element.
- Prevents: Keyboard and screen-reader users cannot trigger the action as it lacks a tab stop and role.
Submit.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Interactive elements built with generic divs lack the keyboard and screen-reader support of native HTML. Hardcoded strings and directional CSS like "left" and "right" create technical debt that breaks layouts and grammar in non-English locales.
What it does
- Enforces semantic HTML over ARIA bolt-ons to ensure native screen-reader support.
- Identifies keyboard traps and manages focus order for modals, menus, and route changes.
- Migrates hardcoded strings to ICU MessageFormat to handle plurals, gender, and word order.
- Converts directional CSS to logical properties for RTL (Right-to-Left) layout compatibility.
- Automates WCAG AA contrast checks and reduced-motion preference compliance.
Frameworks & tools
React, Next.js, Vue, Tailwind CSS, ICU MessageFormat, and any modern front-end stack using CSS logical properties.
Why this beats prompting it yourself
General-purpose models often hallucinate ARIA attributes or use string concatenation that fails in translation. This skill applies a specific "trigger matrix" to catch silent failures like missing labels, incorrect tab order, and non-logical CSS properties before they reach production.
Use cases
- Converting a legacy "div-based" component library to accessible, semantic HTML.
- Pre-flighting a feature for international launch in RTL languages like Arabic or Hebrew.
- Refactoring hardcoded UI strings into a scalable, translation-ready message catalog.
- Ensuring complex UI patterns like modals and dropdowns meet keyboard navigation standards.
Known limitations
This tool identifies authoring-time errors but does not run live screen-reader audits, verify color contrast values against actual rendered pixels, or provide literal translations.
Authoring-time checks only. Does not run screen readers, perform live contrast audits, or generate translations.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 3 months ago
Permissions
No special permissions declared or detected