agentleFS
aispiringcoder4302aispiringcoder4302/seo-aeo-geo-mcp/skills/seo-aeo-geo-audit/SKILL.md

seo-aeo-geo-audit

Skill0 starsChanged 31 days agoMITView on GitHub

Audit a web page for Google, AI Overviews, ChatGPT, Claude and Perplexity visibility with the seoaeogeo MCP server, apply the code fixes on a branch, and verify them. Use when the user asks for an SEO audit, AEO or GEO audit, AI search visibility, "why doesn't ChatGPT mention my site", AI crawler access (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot), Cloudflare blocking AI bots, or fixing SEO issues in a site's code.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. shahbazaliofficial/Claude-Skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call audit_url with the public URL of the page the user cares about (homepage, main product or service page, or a key article).

    line 13
  2. Distinctive:

    Read the result: the score, which issues are blockers (they cap the score at 39 and usually mean AI crawlers can't read the page), and the …

    line 15
  3. Distinctive:

    Create a branch. Work through "Fixes in the codebase" in order.

    line 19
  4. Distinctive:

    Use each fix's Where hint to find the template, layout, head metadata, robots.txt generator or rendering config.

    line 20
  5. Distinctive:

    Never invent facts, author names, dates or statistics.

    line 22
  6. Distinctive:

    Don't touch CDN, firewall, DNS or hosting settings: they're listed under "Needs a human".

    line 23
  7. Distinctive:

    Run each fix's Verify command against a preview deployment.

    line 27
  8. Very specific:

    Call audit_url again on the preview or deployed URL.

    line 28
  9. Distinctive:

    Don't deploy to production yourself.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SEO·AEO·GEO audit → fix → verify

Requires the seoaeogeo MCP server: claude mcp add --transport http seoaeogeo https://seoaeogeo.app/mcp

1. Audit

Call audit_url with the public URL of the page the user cares about (homepage, main product or service page, or a key article). It must be publicly reachable; for unreleased changes use a public preview deployment URL.

Read the result: the score, which issues are blockers (they cap the score at 39 and usually mean AI crawlers can't read the page), and the fix pack.

2. Fix (code only, on a branch)

  • Create a branch. Work through "Fixes in the codebase" in order.
  • Use each fix's Where hint to find the template, layout, head metadata, robots.txt generator or rendering config.
  • Make the smallest change that fixes the issue. Don't rewrite unrelated content.
  • Never invent facts, author names, dates or statistics. Leave a clearly marked TODO and list it for the user.
  • Don't touch CDN, firewall, DNS or hosting settings: they're listed under "Needs a human". Tell the user exactly what to change and where.

3. Verify

  • Run each fix's Verify command against a preview deployment.
  • Call audit_url again on the preview or deployed URL. Report the score change and which issues now pass.
  • Don't deploy to production yourself. Open a pull request.

Facts to keep straight

  • GPTBot collects training data; OAI-SearchBot decides ChatGPT search. Blocking GPTBot doesn't remove a site from ChatGPT search.
  • ClaudeBot is training; Claude-SearchBot indexes for Claude search; Claude-User fetches when a user asks.
  • Google AI Overviews and AI Mode use normal Googlebot and need nothing beyond Search eligibility. Google-Extended doesn't affect them.
  • llms.txt and schema don't change which pages AI answers cite in any controlled test; don't present them as ranking fixes.
  • Many AI crawlers don't run JavaScript: the content must be in the server's HTML.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.