vectorscope — GEO / AI search, an agent skill published by olexan-art/getlooploop-skills
GEO / AI searchEditor's choiceolexan-art/getlooploop-skillsMITGitHub ↗
Installs
—
not on skills.sh yet, so nothing is counted
Since we started
—
One reading so far. A direction needs two.
Our category
GEO / AI search
ours
Last read
Nov 6, 2026
GitHub
What it doesfrom the directory
Shows how an AI retriever or a RAG pipeline reads a public web page: the fetch, the text extraction, the cut into passages, the 26-passage cap, robots.txt rules for AI crawlers (GPTBot, ClaudeBot, PerplexityBot), structure checks and how generated the text sounds. The agent groups the passages, tests queries and writes a rewrite plan. Output: an HTML report. Compares 2 to 5 pages. Use when the user asks how AI reads or chunks a page, what is past a retrieval cap, if AI bots are blocked, how to make a page easier to cite, or names vectorscope. Also «як ШІ читає сторінку». For a full SEO or GEO audit, use ai-search-audit-full.
Installfrom the directory
npx skills add https://github.com/Olexan-art/getlooploop-skillsInstalling happens there, not here. We are an index with an opinion, not a mirror.
What is inside itfrom the directory
89 files, 2815.9 KB — names and sizes only.
What the auditors foundfrom the directory
A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.
No audit yet. The directory generates one after a skill's first install, so this is a fact about its age rather than about its safety.
Installs, reading by readingours
One reading so far. A direction needs two.