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

faq

Skill432 starsChanged 11 days agoMITView on GitHub

An FAQ block from the top fan-outs and your brand facts, with FAQPage schema.

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use claude-buddy, face-enroll and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • autonomous-aiSkill

    claude-buddy

    Coordinate with the Claude Buddy companion (Claude Desktop + Claude Code on the user's Mac) — voice-approve tool permission prompts and stay aware of Claude activity.

    Also in 3 projects that use this

  • autonomous-aiSkill

    face-enroll

    Manage the device's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or HAL's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are friends; strangers stay unnamed until promoted via one of the enroll flows.

    Also in 3 projects that use this

  • +10 more from autonomous-ai

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    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:

    If the page or topic is unclear, ask which one first.

    line 17
  2. Distinctive:

    No tracking numbers (visibility, share of voice, rankings) in the FAQ: it is public content.

    line 40
  3. Distinctive:

    Don't invent prices, figures, customers or awards.

    line 41
  4. Distinctive:

    Don't mark up questions and answers that aren't visible on the page.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 6 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

FAQ from fan-outs

An FAQ block that answers the questions AI engines search for, and the FAQPage structured data that goes with it.

When to use

  • "Write an FAQ for our pricing page", "Add FAQ schema to this draft", "What questions should this page answer?"
  • If the page or topic is unclear, ask which one first.

What to read

  1. get_fanouts for the brand, or the topic of the page: the searches the engines run behind its answers. These are the best questions.
  2. get_prompt_insights or list_prompts for the topic: the prompts people ask, and where the demand is.
  3. list_ai_answers for one or two of those prompts: what AI says now, and what it gets wrong or leaves out.
  4. get_draft when the person names a draft: its passages, so the FAQ doesn't repeat them.

Steps

  1. Pick the top fan-outs for the page: 5 to 8 questions. Merge near-duplicates, and phrase each the way a buyer would ask it.
  2. Write the answers from the brand's facts: 40 to 80 words each, the first sentence answering on its own. Use only facts from the person's messages, the brand's approved facts they give, its own pages read in this chat, or the draft. Any other fact is a [placeholder], such as [plan limits] or [support hours].
  3. Save the FAQ and its FAQPage schema as a draft when the person wants it kept, with create_draft; the app asks them first when it should. In an agent's run nobody is there to ask: always save it with its tool, and the app holds it for approval where the agent's mode needs it.

Output

  1. The FAQ as HTML: a heading, then each question as a subheading with its answer.
  2. The FAQPage structured data as JSON-LD, in a code block, repeating each question and answer exactly as the visible FAQ says them.
  3. One line on where the questions came from (fan-outs, prompts).

Don't

  • No tracking numbers (visibility, share of voice, rankings) in the FAQ: it is public content.
  • Don't invent prices, figures, customers or awards.
  • Don't mark up questions and answers that aren't visible on the page.

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.