Back to Skills

lighthouse-audit

guia-matthieu
Updated 2 days ago
6 views
111
20
111
View on GitHub
Otherautomation

About

This skill automates Google Lighthouse audits to measure Core Web Vitals, SEO, and accessibility metrics. Developers can use it to check page performance, audit technical SEO issues, and compare optimization results. It supports batch auditing multiple URLs for monitoring and reporting.

Quick Install

Claude Code

Recommended
Primary
npx skills add guia-matthieu/clawfu-skills -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/guia-matthieu/clawfu-skills
Git CloneAlternative
git clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/lighthouse-audit

Copy and paste this command in Claude Code to install this skill

Documentation

Lighthouse Audit

Automate Google Lighthouse audits to measure and track Core Web Vitals, SEO, and accessibility - the same metrics Google uses for search ranking.

When to Use This Skill

  • Performance optimization - Measure LCP, FID, CLS before and after changes
  • SEO audits - Check technical SEO issues (meta tags, structured data, etc.)
  • Accessibility checks - Identify a11y issues for compliance
  • Client reporting - Generate professional performance reports
  • Monitoring - Track scores over time across multiple pages

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures analysis frameworksMetric definitions
Identifies patterns in dataBusiness interpretation
Creates visualization templatesDashboard design
Suggests optimization areasAction priorities
Calculates statistical measuresDecision thresholds

Dependencies

pip install click pandas jinja2
# Also requires Chrome and Lighthouse CLI
# npm install -g lighthouse
# Or use Chrome DevTools built-in Lighthouse

Commands

Single URL Audit

python scripts/main.py audit https://example.com --categories performance,seo
python scripts/main.py audit https://example.com --format html --output report.html

Batch Audit

python scripts/main.py batch urls.txt --output results/
python scripts/main.py batch urls.txt --categories performance --format csv

Compare Before/After

python scripts/main.py compare https://example.com --baseline scores.json
python scripts/main.py compare https://example.com --baseline-url https://staging.example.com

Monitor Over Time

python scripts/main.py history https://example.com --days 30
python scripts/main.py history https://example.com --plot

Examples

Example 1: Full Site Performance Audit

# Create URL list
cat > urls.txt << EOF
https://example.com/
https://example.com/pricing
https://example.com/features
https://example.com/blog
EOF

# Run batch audit
python scripts/main.py batch urls.txt --categories performance,seo,accessibility

# Output: results/audit_2024-01-15/
# ├── example.com_.json
# ├── example.com_pricing.json
# ├── example.com_features.json
# ├── example.com_blog.json
# └── summary.csv

Example 2: Before/After Comparison

# Save baseline
python scripts/main.py audit https://example.com --output baseline.json

# Make optimizations...

# Compare
python scripts/main.py compare https://example.com --baseline baseline.json

# Output:
# Core Web Vitals Comparison
# ─────────────────────────────
# Metric         Before    After    Change
# LCP            3.2s      1.8s     -44% ✓
# FID            120ms     45ms     -63% ✓
# CLS            0.25      0.08     -68% ✓
# Performance    52        89       +37 pts

Example 3: Generate Client Report

# Full audit with HTML report
python scripts/main.py audit https://client-site.com \
  --format html \
  --output client-report.html \
  --include-screenshots

# Output: Professional HTML report with:
# - Executive summary
# - Core Web Vitals scores
# - Screenshots of issues
# - Prioritized recommendations

Audit Categories

CategoryChecksImpact
performanceLCP, FID, CLS, TTFB, Speed IndexSearch ranking
seoMeta tags, headings, links, mobileSearch visibility
accessibilityWCAG compliance, contrast, labelsCompliance
best-practicesHTTPS, security, modern APIsTrust
pwaService worker, manifest, offlineApp-like experience

Core Web Vitals Thresholds

MetricGoodNeeds ImprovementPoor
LCP (Largest Contentful Paint)≤2.5s2.5s-4.0s>4.0s
FID (First Input Delay)≤100ms100ms-300ms>300ms
CLS (Cumulative Layout Shift)≤0.10.1-0.25>0.25
INP (Interaction to Next Paint)≤200ms200ms-500ms>500ms

Output Formats

FormatUse CaseContent
jsonAutomation, storageFull raw data
csvSpreadsheets, analysisSummary scores
htmlClient reportsVisual report
mdDocumentationMarkdown summary

Skill Boundaries

What This Skill Does Well

  • Structuring data analysis
  • Identifying patterns and trends
  • Creating visualization frameworks
  • Calculating statistical measures

What This Skill Cannot Do

  • Access your actual data
  • Replace statistical expertise
  • Make business decisions
  • Guarantee prediction accuracy

Related Skills

Skill Metadata

  • Mode: centaur
category: seo-tools
subcategory: performance
dependencies: [lighthouse, click, pandas]
difficulty: beginner
time_saved: 3+ hours/week

GitHub Repository

guia-matthieu/clawfu-skills
Path: skills/seo-tools/lighthouse-audit
0
ai-skillsanthropicclaude-codeclaude-skillsmarketingmcp-server

Related Skills

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

cost-optimization

Other

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

View skill

quantizing-models-bitsandbytes

Other

This skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.

View skill

dispatching-parallel-agents

Other

This Claude Skill dispatches multiple agents to investigate and fix 3+ independent problems concurrently. It is designed for scenarios involving unrelated failures that can be resolved without shared state or dependencies. The core capability is parallel problem-solving, assigning one agent per independent problem domain to maximize efficiency.

View skill