seo-deep-audit

SEO Deep Audit — orchestrator: provide a domain -> get everything

One entry point for a complete audit. When given a domain without a specified scope, work at maximum depth: run the entire chain of skills and tools yourself, collect everything, and consolidate it into one report + task plan. Narrow the work only when EXPLICITLY instructed ("only robots," "quick," "lite," "no rendering," "check only headings"). The map of "which tool retrieves what" is in the sf-boundaries skill.

If you need a plan for exactly what to collect before expensive runs, start with audit-roadmap (Recon lite -> roadmap with priorities, scale, site type, and YAGNI), and then this skill executes the roadmap.

Default rule

• No scope clarification -> MAX. Run every phase below.
• Explicitly narrowed scope -> only that scope. "only sitemap" -> only the sitemap portion; "quick/lite" -> --profile lite + skip expensive agent-level phases.
• Never ask "should I do a full audit?" — a full audit is the default. Clarify only what makes progress impossible (no domain; SF is not installed and no exports are available).

Pipeline (all phases by default)

Phase 0 — Reconnaissance (what kind of site is this?). The seo-recon skill — three toolkit tools:

seohead domain-profile --domain <domain>   # registration, DNS, ASN, geography, TLS, flags
seohead cdn-check       --url https://<domain>   # CDN + actual cache behavior, HTTP/2-3, TTFB
seohead tech-detect     --url https://<domain>   # CMS/framework/server, analytics, pixels

Remember the stack: if tech-detect found an SPA/Next.js/Nuxt, mark JS rendering as required (Phase 2). Some findings from domain-profile.flags and cdn-check.findings go directly into the report.

Phase 1 — Crawl evidence (96-check registry). SEOHEAD is the analyzer and adapter here, not the crawler. Check the environment first with seohead sf doctor; live mode requires a separately installed, actively licensed Screaming Frog CLI.

seohead sf run --crawl https://<domain> --out report --tasks

The full profile is the default (maximum available coverage), and the sitemap is automatically obtained from robots. The registry contains 96 checks, but only checks supported by the available exports and enabled SF modules can run. If the output contains many skipped results (MIXED_CONTENT/STRUCTURED_DATA/SPELLING/DOM_*), enable them once through the sf-config skill (create audit.seospiderconfig); the tool will pick it up automatically. If SF/a license is not available, request exports and use mode B (--exports-dir); see sf-analyzer/sf-config.