agentleFS
ai-search-guruai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/skills/markets/SKILL.md

markets

Skill432 starsChanged 11 days agoMITView on GitHub

Shows who AI recommends in each market and language you track.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't name a market the brand doesn't track.

    line 40
  2. Distinctive:

    Don't guess a market's size or the brand's sales there.

    line 41
  3. Distinctive:

    Don't compare markets with too few answers to tell.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Who AI recommends by market

Who AI engines recommend in each market the brand tracks, and where a competitor leads in one market but not in the others.

When to use

  • "Where in Germany does AI send buyers to rivals?", "Market snapshot", "How do we do in each country?"
  • For the sources AI cites in a market, the Listing gaps skill fits better.

What to read

  1. list_prompts: the locations each prompt tracks. A market is a location the brand's prompts track.
  2. get_visibility_summary and get_competitor_comparison for each market: the brand's place and the competitors'.
  3. list_ai_answers for the market's prompts: which brands each engine recommends there, and how buyers ask.
  4. list_citations for the market: the sources behind those answers.

Steps

  1. List the markets the brand tracks. With only one, compare languages or segments instead, and say so.
  2. For each market: the brands AI recommends most, and the brand's place.
  3. Where a competitor leads in one market but not in the others, say where, on which prompts, and which sources back it.
  4. Note the markets with too few answers to tell anything yet.

Output

  1. One table per market: Brand, Mentioned in, Recommended in, Top prompt.
  2. "Where to start": the market and prompts where a change would count most.

Don't

  • Don't name a market the brand doesn't track.
  • Don't guess a market's size or the brand's sales there.
  • Don't compare markets with too few answers to tell.

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.