Index of every page on this site: llms.txt
All skills
Run it yourself

Full SEO audit of a site from its real Search Console + GA4 data — indexation health, CTR anomalies, decaying pages, striking-distance keywords, quick wins. Use when asked to "audit my site", "SEO audit", "why is my organic traffic down", or "SEO health check".

Use this Skill: https://skilld.dev/gh/ryze-ai-adgent/open-seo-mcp-skills/seo-audit

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈69 tokens for metadata: the name and description. ≈608 when used: this file.

Description uses 3.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈273 characters, or 3.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

SEO Audit

Requires

The free Ryze MCP connector (https://connector.get-ryze.ai/mcp). Claude Code: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp. claude.ai / Desktop / Cursor: add it as a custom connector with the same URL. Setup: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp?utm_source=github&utm_content=open-seo-mcp-skills

Audit the user's site using their own data via the Ryze MCP. No estimates — everything below comes from their actual GSC/GA4.

Workflow

  1. Pick the property. google_search_console__listSites. If several, use the one matching the user's domain; confirm only when ambiguous.
  2. Indexation. google_search_console__getIndexationSummary — indexed vs not-indexed counts and reasons. Flag anything unusual (large "Crawled — currently not indexed", spikes in excluded pages).
  3. Performance baseline. google_search_console__runRawSearchAnalytics: last 90 days vs previous 90, dimensions query and page (two calls each period). Compute clicks/impressions/CTR/position deltas.
  4. Find the problems:
    • Decaying pages — pages whose clicks dropped >30% period-over-period
    • CTR anomalies — queries with position ≤ 5 but CTR < 2% (title/meta problem)
    • Striking distance — queries at position 8–20 with high impressions (one push from page 1)
    • Cannibalization — same query, multiple ranking pages splitting clicks
  5. Spot-check pages. For the 3–5 worst pages, google_search_console__inspectUrl — canonical, indexing state, last crawl.
  6. Cross-check traffic. google_analytics__runRawReport — organic sessions + conversions by landing page, same periods. A page can hold rankings but lose revenue; call that out.
  7. AI traffic. google_analytics__getAIReferrals for the same window — note whether AI engines are becoming a meaningful channel for this site.

Output

A report with: verdict up top (one paragraph, is the site healthy or not and the #1 issue), then sections — Indexation, Losers, Quick wins (striking distance + CTR fixes, ranked by impressions), Cannibalization — each with a table and the specific fix. End with a prioritized 5-item action list.

Fallbacks

If GSC isn't connected, say so and point to Ryze connector setup (https://help.get-ryze.ai/claude/connect) — do not substitute third-party estimates for the site's own data.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning24d3 checks · Risk SAFE
  • Gen Agent Trust Hub24d

    The skill performs an SEO audit using data from Google Search Console and Google Analytics via a custom connector. A low risk of indirect prompt injection exists because the skill processes untrusted external data from site reports without specific sanitization.

  • Socket24d

    No alerts

  • Snyk24d

    Risk: MEDIUM · 1 issue

Signed by skilld at f587b0a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated 4 weeks ago

README badge

README badge for ryze-ai-adgent/open-seo-mcp-skills/seo-audit