agentsclimarketplace

Aeo llm visibility audit

Skill saurabhshuklagrowisto/saurabh-ai-systems/claude-skills/aeo-llm-visibility-audit

AI architect for GTM and martech. I design and ship production agentic systems for B2B sales and marketing: lead scraping and scoring with an eval gated learning loop, autonomous CRM enrichment, ABM pipelines, live dashboards that refresh themselves, MCP servers and Claude skills. Built at Growisto.

Install
npx -y skills add saurabhshuklagrowisto/saurabh-ai-systems --skill aeo-llm-visibility-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Measures whether a brand shows up when buyers ask AI assistants (ChatGPT, Perplexity, Gemini) about its category, and turns the gaps into a content plan. Takes a brand name and a set of real buyer questions, checks which brands each engine names, and returns a share-of-voice score, the competitors winning the answers, and the exact questions where the brand is invisible. Use to audit AI/answer-engine discoverability (AEO/GEO), to prioritise content that AI assistants will cite, or to track share of voice in AI answers over time.

SKILL.md

2.5 KB, as published. Nobody here has run it

AEO / LLM Visibility Audit Skill

Search is moving from ten blue links to one AI answer. This skill measures the new page one: when your buyer asks ChatGPT, Perplexity, or Gemini for the best tool in your category, does your brand get named — and if not, who does, and on which questions.

When to use

  • To baseline and track answer-engine optimisation (AEO/GEO) — visibility inside AI-generated answers.
  • To decide which content to write next: the questions where you are invisible are your highest-leverage targets.
  • To benchmark share of voice against named competitors in AI answers over time.

When NOT to use

  • For classic Google SEO rank tracking — that is a different surface; use an SEO tool.
  • For brand sentiment — this measures presence in answers, not tone.

Method

  1. Take the real questions your buyers type into AI assistants.
  2. For each question, across each engine, capture which brands the answer names.
  3. Score: share of voice = the share of answers that name you; list the competitors named most; flag the questions where you appear in zero engines (true content gaps).

Inputs

  • brand — your brand name
  • questions — the buyer questions to test
  • answers — for each (question, engine), the brands named. In production these come from live API calls to each assistant; the demo ships a sampled set so the logic runs with no keys.

Output (JSON)

share_of_voice_pct, answers_checked, mentions, top_competitors[], and gap_questions[] — the questions to target first.

Run it

python scripts/aeo_score.py         # built-in sample
python scripts/aeo_score.py in.json # your own brand + questions + answers

Zero dependencies, no API keys. To go live, replace the sampled answers with real calls to the ChatGPT / Perplexity / Gemini APIs; the scoring stays identical. A scheduled n8n version of this exact logic ships in pipeline-automation/aeo-llm-visibility-monitor.json.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.