Senior Frontend
React, Next.js, TypeScript, Tailwind CSS, accessibility, and performance.
$skillfish add ~skills/senior-frontend Real Conversations
See how the Senior Frontend skill responds to actual requests. These are representative examples of what your AI agent will produce.
Our Next.js marketing site has LCP of 8.2s on mobile (Lighthouse). Hero section has a 1.2MB PNG, loaded with a standard img tag. Bundle is 340KB gzipped.
LCP fixes — ordered by impact:
1. Hero image (biggest win — likely 4-5s savings):
// Replace <img> with Next.js Image — automatic WebP/AVIF conversion + lazy sizing
import Image from 'next/image';
<Image
src="/hero.png"
alt="Hero"
width={1440}
height={800}
priority // LCP image — preload, don't lazy-load
quality={80}
sizes="(max-width: 768px) 100vw, 1440px"
/>
Result: 1.2MB PNG → 120KB AVIF on modern browsers (140KB WebP fallback).
2. Bundle size (340KB gzipped is too large for a marketing site):
npx @next/bundle-analyzer
# Look for: moment.js (~67KB), lodash (~70KB), large icon libraries loaded whole
Swap lodash → lodash-es with tree-shaking, replace moment with date-fns.
3. Font loading (common hidden LCP killer):
// In next/font — self-hosted, preloaded, no FOUT
import { Inter } from 'next/font/google';
const inter = Inter({ subsets: ['latin'], display: 'swap' });
Expected LCP after fixes:
| Change | LCP delta |
|---|---|
| Hero image → next/image | -3.5s |
| Bundle tree-shaking | -0.8s |
| Font optimization | -0.4s |
| Total estimate | ~3.5s |
Get Started
How to install and use this skill in your preferred environment.
Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.
Models & Context
Which AI models and context windows work best with this skill.
Recommended Models
Larger models produce more detailed, production-ready outputs.
Context Window
This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.
All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.
Pro tips for best results
Be specific
Include numbers — users, budget, RPS — so the skill can size the architecture.
Share constraints
Compliance needs, team size, and existing stack all improve the output.
Iterate
Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.
Combine skills
Pair with companion skills below for end-to-end coverage.
Ready to try Senior Frontend?
Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.
$skillfish add ~skills/senior-frontend