From ai-agent-kit
Use when building or reviewing user-facing UI (web, mobile, desktop) for accessibility: semantic HTML, ARIA, keyboard navigation, screen readers, contrast, focus management, motion sensitivity, WCAG conformance.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-agent-kit:accessibilityThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
UI that everyone can use — including people who navigate with keyboard only,
UI that everyone can use — including people who navigate with keyboard only, screen readers, voice control, magnifiers, or who have reduced motion / color sensitivity. Not a checkbox at the end; built in from the first prototype.
Target: WCAG 2.2 Level AA as the minimum bar for production UI.
| Concept | Best practice |
|---|---|
| Structure | Use semantic HTML (<main>, <nav>, <header>), correct heading hierarchy |
| Keyboard | Logical tab order, visible focus states, no keyboard traps |
| Forms | Associate labels with inputs (for/id), provide clear error messages |
| Screen Readers | Provide descriptive alt text, use ARIA attributes correctly |
| Key commands | npx playwright test --grep @a11y, lighthouse http://localhost:3000 |
Extended how-to, patterns, anti-patterns, and checklists: SKILL.deep.md
npx claudepluginhub petrovc/ai-agent-kit --plugin ai-agent-kitFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.