- Home
- Skills
- Marketing & SEO
- GEO + SEO Audit Crawler: Get Found by AI Search
More screenshots
Works with the AI Agents you already use
GEO + SEO Audit Crawler: Get Found by AI Search
Turn any website into a scored GEO + SEO fix list: a real crawler checks 69 rules for Google and AI search (ChatGPT, Perplexity, Claude) and writes the fix files.
$19
About this skill
Your site looks fine in a browser, but AI answer engines may not be able to read it: a robots.txt that shuts out the answer crawlers, text that only appears after JavaScript runs, a sitemap full of dead URLs, broken schema. Measured, not promised: on the public httpx docs the tool's own fix files took the score 62 -> 72 with no hand edits. On a seeded shop site they took it 59 -> 62, and following the ranked fix list (26 edits) took it to 90 with 0 high issues.
GEO + SEO Audit ships a real crawler, not a checklist.
- Polite and contained crawl of a live site (robots.txt read first and obeyed, 1 request per second, page cap, only http(s) on the audited host) or a built static folder with no network at all.
- AI crawler access for 20 bots, split into answer bots (OAI-SearchBot, Claude-SearchBot, PerplexityBot, Googlebot...) and training bots (GPTBot, ClaudeBot, CCBot...). Blocked, partial (a few paths) or allowed; blocking training bots is never scored as an error.
- 69 rules in 10 categories: titles and descriptions, canonicals, hreflang, headings, broken links, sitemap.xml vs the crawl, llms.txt, JSON-LD per type (Organization, Product, Article, FAQPage, BreadcrumbList...), Open Graph, answerability, page weight, alt text, JavaScript-only pages.
- One-page HTML client report (
--report): score dial, category bars, AI crawler table, top fixes, before/after. - Fix files to review: llms.txt, a robots.txt that keeps every path rule, a merged sitemap.xml, JSON-LD per page, meta fixes.
- CI gate and deltas:
--min-score,--baseline.
Benchmark (commands and commits in the bundle)
| Site | Pages | Time | Score | Verified finding |
|---|---|---|---|---|
| python-httpx.org (live) | 23 | 30 s | 62 | same description on 23/23 pages |
| htmx.org (live) | 25 | 51 s | 69 | no Open Graph, blocking scripts on 25/25 |
| sqlite.org (live) | 25 | 50 s | 58 | HTML uncompressed, no sitemap |
| pipx docs (build) | 11 | local | 58 | sitemap of 11 <loc>None</loc> |
An independent red-team review found 4 high-severity bugs (including unsafe URL schemes and a robots.txt rewrite that dropped rules). All are fixed, each with a regression test (71 automated tests in total).
What it does not do: no JavaScript rendering, no Core Web Vitals, no backlinks, rankings or Search Console data, no CDN bot-blocking detection. It does not promise rankings or citations.
Works in Claude Code, Cursor, Codex CLI, Copilot and any SKILL.md agent.
Privacy: one readable Python file, standard library only. No telemetry, no API keys; the only network traffic is the crawl you ask for, and --local makes none.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 27 days ago
Requires
Permissions
Allowed Hosts