agentleFS
frontmost-aifrontmost-ai/aeo-skills/skills/question-gaps/SKILL.md

question-gaps

Skill1 starsChanged 3 days agoMITView on GitHub

Rank the buyer questions where AI apps mention rivals and not the business, and give the reason for each loss. Use for "where do I lose in ChatGPT" or "why does AI not mention me". Needs a Frontmost AI project.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this guidance to find the questions that a business loses in AI answers and to explain each loss.

    line 8
  2. Very specific:

    If a tool returns setup_required, give the person the url from the result.

    line 14
  3. Very specific:

    If a tool returns plan_required, say that this data needs a paid Frontmost AI plan, and stop.

    line 15
  4. Very specific:

    If the Frontmost AI tools are not available, use the mention-check skill.

    line 16
  5. Distinctive:

    Never invent the data, and never fill a gap with a guess.

    line 17
  6. Very specific:

    Call get_questions for the project and the scan in the request.

    line 26
  7. Distinctive:

    Keep the questions with at least one lost answer.

    line 28
  8. Distinctive:

    If no reason fits, say "the answers do not show why".

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Question gaps

Use this guidance to find the questions that a business loses in AI answers and to explain each loss.

Before you start

This skill reads a Frontmost AI project through the Frontmost AI tools that this plugin connects.

  • If a tool returns setup_required, give the person the url from the result. Stop until they say that set-up is done.
  • If a tool returns plan_required, say that this data needs a paid Frontmost AI plan, and stop.
  • If the Frontmost AI tools are not available, use the mention-check skill. It needs no account, and it counts a small set of answers by hand. To read recorded answers for each question, the person connects Frontmost AI: https://frontmost.ai/connect
  • Never invent the data, and never fill a gap with a guess.

Terms

  • A question is lost in an answer when the answer mentions at least one rival and does not mention the business.
  • The size of a loss is the number of lost answers for that question in the scan. More AI apps and more lost answers mean a larger loss.

Steps

  1. Call get_questions for the project and the scan in the request.
  2. For each question, read each AI app's result: whether the answer mentioned the business, its position, and the business that the answer mentioned first.
  3. Keep the questions with at least one lost answer. Rank them by lost answers, then by the number of AI apps that lost.
  4. For the top 5, call get_questions again with question_id. Read each AI app's answer, the businesses in it, and the sites that it cites.
  5. Give each loss one reason from this list. Use the first one that the answers support:
    • Access: get_readiness shows that an AI app cannot use the website. Report this first. It blocks the other fixes.
    • Outside pages: the answers cite lists, reviews, or directories that mention rivals and not the business.
    • Topic: the business is missing from a whole topic, across AI apps.
    • Format: the cited pages share a format that the business does not have, such as a comparison, a list, or a guide.
    • Wrong description: the answer mentions the business and describes it incorrectly. This is not a lost answer. List it apart.
  6. If no reason fits, say "the answers do not show why".

Rules

  • Report each number with its counts, for example "0 of 3 AI apps".
  • Quote an answer only from get_answers or the question page. Use one short quote for each question.
  • A question that no AI app answered is not a loss. Leave it out and say how many you left out.
  • Link the url of the Questions tab and of each question that you describe.

Output

A ranked list of up to 5 questions. For each one: the question, the lost answers with counts, the rivals mentioned, the reason, and one first action. Then one line that says how many more questions have a lost answer.

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.