Works with the AI tools you already use
Web Performance Vitals Auditor
by RuH
A diagnostic engine for Core Web Vitals that identifies root causes for slow LCP, INP, and CLS scores.
Secure checkout via Stripe
See it in action
You say
My LCP is 4.5s on mobile according to PageSpeed Insights. Here is my hero component code and the Lighthouse JSON. What is the bottleneck?
Your agent does
What you get
About this skill
The problem
Vague performance complaints like "the site feels slow" rarely lead to actionable fixes. Developers often waste hours on generic optimizations that fail to move the needle on Core Web Vitals or search rankings.
What it does
- Identifies the specific bottlenecks behind LCP, INP, and CLS scores using a systematic diagnostic process.
- Audits resource discovery paths to find delayed hero images, render-blocking scripts, and unoptimized font loading.
- Pinpoints main-thread execution issues causing interaction lag and poor responsiveness.
- Detects layout shift culprits like missing dimensions, unreserved ad space, and font metric mismatches.
- Provides a prioritized action plan ranked by estimated impact versus implementation effort.
Frameworks & tools
React, Next.js, Vue, Nuxt, WordPress, and Vanilla JS. Expert knowledge of Lighthouse reports, PageSpeed Insights JSON, and Chrome DevTools Performance profiles.
Why this beats prompting it yourself
Generic LLMs often suggest "lazy-loading all images," which can actually destroy your LCP score if applied to hero elements. This skill follows a strict "metric-first" logic, ensuring every recommendation is backed by a technical mechanism and a predicted outcome.
Use cases
- Pre-shipment PR reviews to catch performance regressions in new components.
- Debugging "Poor" Core Web Vitals ratings that are hurting SEO rankings.
- Optimizing bundle sizes and hydration overhead in heavy SSR/SSG frameworks.
- Converting messy Lighthouse JSON exports into an executive summary for stakeholders.
Known limitations
Requires an external data source (URL, Lighthouse report, or code) as it cannot crawl live sites independently. Performance estimates are directional and not exact measurements.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
More reviews for RuH5.0(1)
Feedback buyers left on other skills by the same creator.
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.