seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Uses live web data via the Bright Data CLI for accurate detection of JS-injected schema, hreflang, canonicals, and live SERP-based ranking checks. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page spe
Security Assessment
Detected risks:
About seo-audit
The seo-audit skill audits, reviews, and diagnoses SEO issues on a site using the Bright Data CLI (bdata) to access live, JavaScript-rendered web data. This lets it detect JS-injected schema markup, client-side hreflang and canonicals, and live SERP results that simple fetching or curl would miss.
It auto-routes between a single-page deep audit and a site-wide audit (sitemap-stratified sampling with a configurable page budget), and runs signal-driven SERP checks only when a target keyword or diagnostic prompt is present. Its workflow gathers pages (robots.txt, sitemap, and sampled URLs fetched in parallel), detects site type, walks a five-tier framework (crawlability and indexation, technical foundations, on-page optimization, content quality, and authority and links), and formats a report where every finding has Issue, Impact, Evidence (a runnable bdata command plus an output excerpt), Fix, and Priority. A hard rule is to never fabricate findings and to route anything bdata cannot measure to an Out-of-Scope Notes section pointing at the right tool.
It is most useful when a user reports ranking drops, indexing problems, or general SEO concerns and wants an evidence-backed technical audit with actionable, prioritized fixes.
FAQ
When should I use this skill?
To audit, review, or diagnose technical and on-page SEO issues, including ranking drops, indexing problems, and meta or schema reviews.
Why does it use Bright Data?
The bdata CLI renders JavaScript, so it can detect JS-injected schema, hreflang, and canonicals and return parsed SERP results, which curl or simple fetching cannot.
What are its two modes?
A single-page deep audit (about 5-10 bdata calls) and a site-wide audit using sitemap-stratified sampling (default 10-15 pages, about 20-40 calls).
What does a finding look like?
Each finding has Issue, Impact, Evidence (a runnable bdata command plus an output excerpt), Fix, and Priority, and findings are never fabricated.
What about things bdata cannot measure?
They go to an Out-of-Scope Notes section pointing to the right tool, for example PageSpeed Insights for field Core Web Vitals or Search Console for coverage detail.
Install seo-audit
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
brightdata/skills