ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and…
Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.
$ npx -y skills add DevelopersGlobal/ai-agent-skills --skill frontend-engineering --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/frontend-engineeringContext preview
The summary Claude sees to decide when to auto-load this skill.
Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.
name: frontend-engineering description: Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance. category: build applies-to: [claude, gemini, cursor, copilot, any] version: 1.0.0
Frontend code touches every user. Poor UI engineering causes accessibility barriers, performance degradation, and broken experiences on non-standard devices. This skill enforces the discipline of building UI that works for everyone.
1. Every interactive element has a visible focus state. 2. All images have meaningful alt text (or `alt=""` for decorative). 3. Color contrast ratio ≥ 4.5:1 for normal text. 4. All functionality operable by keyboard alone. 5. Use semantic HTML: `<button>` not `<div onclick>`, `<nav>` not `<div class="nav">`.
**Verify:** Run axe DevTools or Lighthouse accessibility audit. Score ≥ 90.
6. LCP (Largest Contentful Paint) < 2.5s: Optimize images, preload critical resources. 7. FID/INP < 100ms: Avoid long tasks on the main thread. 8. CLS (Cumulative Layout Shift) < 0.1: Reserve space for dynamic content. 9. Lazy load below-the-fold images and non-critical JS. 10. Bundle size: measure before and after. No unneeded dependencies.
**Verify:** Lighthouse performance score ≥ 80. CWV within targets.
11. Test at 320px, 768px, 1024px, 1440px viewports. 12. No horizontal scrolling at any standard viewport. 13. Touch targets ≥ 44px × 44px.
14. Server state vs. client state are separate concerns — don't mix. 15. No prop drilling more than 2 levels — use context or state management. 16. Loading, error, and empty states handled for every async operation.
**Verify:** Loading, error, and empty states all visible in Storybook/dev environment.
| Excuse | Rebuttal | |--------|----------| | "Accessibility is for edge cases" | 1 in 4 adults has a disability. It's not an edge case. | | "We'll optimize performance later" | Users leave after 3 seconds. "Later" is too late. |
AI agent skills for production grade applications
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and…
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.