From aj-geddes-useful-ai-prompts-4
Audits web page performance measuring Core Web Vitals (LCP, FID, CLS, FCP); identifies bottlenecks and recommends optimizations for speed, UX, and SEO.
npx claudepluginhub joshuarweaver/cascade-code-languages-misc-1 --plugin aj-geddes-useful-ai-prompts-4This skill uses the workspace's default tool permissions.
- [Overview](#overview)
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Web performance audits measure load times, identify bottlenecks, and guide optimization efforts to create faster, better user experiences.
Minimal working example:
Core Web Vitals (Google):
Largest Contentful Paint (LCP):
Measure: Time to load largest visible element
Good: <2.5 seconds
Poor: >4 seconds
Impacts: User perception of speed
First Input Delay (FID):
Measure: Time from user input to response
Good: <100 milliseconds
Poor: >300 milliseconds
Impacts: Responsiveness
Cumulative Layout Shift (CLS):
Measure: Visual stability (unexpected layout shifts)
Good: <0.1
Poor: >0.25
Impacts: User frustration
---
Additional Metrics:
First Contentful Paint (FCP):
// ... (see reference guides for full implementation)
Detailed implementations in the references/ directory:
| Guide | Contents |
|---|---|
| Performance Metrics | Performance Metrics |
| Performance Analysis Process | Performance Analysis Process |
| Optimization Strategies | Optimization Strategies |
| Monitoring & Continuous Improvement | Monitoring & Continuous Improvement |