What it does
Takes a PageSpeed Insights or Search Console Core Web Vitals report and translates each failing metric (LCP, INP, CLS) into a specific likely cause on the site, such as an unpreloaded hero image, a layout shift from an ad slot, or slow server response time, ranked by expected impact so the highest-leverage fix is listed first.
Install
This skill isn't packaged in an installable registry. It's a plain SKILL.md file you can copy directly. Copy it from the SKILL.md tab and save it at the path for your assistant:
Use it in your AI assistant
Claude Code
.claude/skills/core-web-vitals-explainer/ (or ~/.claude/skills/core-web-vitals-explainer/ for all projects)
GitHub Copilot (VS Code)
.github/skills/core-web-vitals-explainer/
OpenAI Codex
.codex/skills/core-web-vitals-explainer/
Cursor
.cursor/skills/core-web-vitals-explainer/ (or ~/.cursor/skills/core-web-vitals-explainer/ globally)
Compatibility
Any WordPress site; needs a PageSpeed Insights, Chrome UX Report, or Search Console export to work from.
The complete SKILL.md for this skill:
---
name: core-web-vitals-explainer
description: Use when a user pastes a PageSpeed Insights or Search Console Core Web Vitals report and wants to know what it means and what to fix first.
---
# Core Web Vitals Explainer
## When to use
The user has a Core Web Vitals report (LCP, INP, CLS scores) and wants to understand what's actually causing the failing metrics on their specific site, and which fix to prioritize.
## Procedure
1. Read the reported scores for each metric (Largest Contentful Paint, Interaction to Next Paint, Cumulative Layout Shift) and note which ones fail the recommended threshold.
2. For a failing LCP, check likely causes on the site: unoptimized or unpreloaded hero images, slow server response time, render-blocking CSS/JS above the fold.
3. For a failing CLS, check likely causes: images or ads without reserved dimensions, web fonts causing a layout swap, injected banners or cookie notices that push content down after load.
4. For a failing INP, check likely causes: heavy JavaScript execution on interaction, too many third-party scripts competing for the main thread.
5. Rank the identified causes by expected impact on the score, not just by how easy each fix sounds.
6. Present a short prioritized fix list (top 3) in plain language, with the specific plugin, setting, or template change that would address each one.
## Guardrails
- Never claim a specific fix will move the score by an exact number, describe expected impact directionally (high, medium, low) rather than inventing precise metrics.
- Do not recommend disabling functionality (like removing a needed plugin or ad) as the fix without noting the tradeoff involved for the site's actual business needs.