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

questions

Skill432 starsChanged 12 days agoMITView on GitHub

Groups new buyer questions by topic, with volume and who AI recommends.

6 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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Never make up a volume: write "unknown" where none is known.

    line 43
  2. Distinctive:

    Don't say which product is better: report what AI says.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Buyer questions

What buyers ask AI engines in the brand's category: the questions grouped by topic, how often they are searched, and which brand AI recommends for each, with the reason it gives.

When to use

  • "What do buyers ask AI about integrations?", "Which buyer questions came up this week?", "Product digest."
  • For one competitor's side of things, the Rival brief skill fits better.

What to read

  1. list_topics and list_prompts: the brand's topics and the prompts under each, newest first when the person asks what's new.
  2. get_fanouts for the prompts of the topic asked about: the questions engines search behind them.
  3. get_prompt_volumes: how often each prompt is searched, where the volume is known.
  4. list_ai_answers for those prompts: which brand each engine recommends, and the words it gives as the reason.
  5. list_prompt_suggestions: questions the brand doesn't track yet.

Steps

  1. Take the topic the person names; with none, the topics with the most new prompts and fan-outs.
  2. Group the questions by what the buyer wants to know, not by their wording. Merge near-duplicates.
  3. For each group: its searches a month where known, the brand AI recommends most, and the reason it gives, quoted from an answer.
  4. Mark the groups where no brand clearly leads: they are the easiest to win.
  5. Close with what this means for the roadmap and the content plan, in three to five lines.

Output

  1. A table: Buyer question, Searches a month, AI recommends, Reason AI gives.
  2. "What this means": three to five lines.
  3. The untracked questions worth tracking, as a list the person can add with add_prompts; the app asks them first.

Don't

  • Never make up a volume: write "unknown" where none is known.
  • Quote the reason AI gives; don't write your own.
  • Don't say which product is better: report what AI says.

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.