agentleFS
Sign inStart free
UXMagicaiUXMagicai/seosorted-skills/skills/ai-visibility-tracker/SKILL.md

ai-visibility-tracker

Skill0 starsChanged 39 days agoMITView on GitHub

Track how often ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews mention or cite the user's brand versus competitors, using SEOsorted's tracked buyer prompts and scans. Use when the user asks about AI visibility, GEO, AEO, LLM visibility, share of voice in AI answers, whether ChatGPT recommends them, or "are we showing up in AI search".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

AI visibility tracker

Steps

  1. track_ai_search_visibility operation: "summary". If there is no data yet, go to step 3.
  2. operation: "prompts" to see which buyer questions are tracked. Good prompts are what a buyer actually types: "best X for Y", "X vs Y", "how do I solve Z". Propose additions for gaps (each product line, each competitor comparison, the main problem) and add with operation: "add_prompts" (EDITOR) — each prompt is {text, topic}, up to 25 per call. The plan sets how many prompts can be tracked; respect the limit the tool reports.
  3. operation: "scan" to run a fresh scan (one AI-visibility scan credit). Poll check_job_status.
  4. Present:
    • Visibility score and share of voice against each competitor.
    • Per engine: mentioned / cited / absent.
    • Prompts where competitors appear and the brand does not — the gap list.
    • Pages of the site that engines already cite (defend these).

Why engines skip the site

  • operation: "readiness" — AI-readiness score out of 100: robots.txt access for AI crawlers, text visible without JavaScript, backlink strength, JSON-LD on key pages, with a fix brief. Free; refresh: true re-checks in the background.
  • operation: "citations" — third-party pages AI answers cited that name the brand, and whether they link here. Unlinked ones → link-building-playbooks (unlinked mentions).

Next

  • Gap prompts → ai-citation-outreach to find the pages engines cite for them and get mentioned there.
  • Engines cite video for a topic → youtube-citation-strategy.
  • Few AI crawler visits → ai-crawler-analytics.

Guardrails

AI answers vary run to run. Talk in trends across scans, not single answers. Report "not mentioned" as a finding, never as an error.

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.

Check your setup, free