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

rival-gaps

Skill1 starsChanged 3 days agoMITView on GitHub

Explain why AI apps mention one rival more than the business, and what the business can truthfully match. Use for "why does ChatGPT recommend this rival and not me". Needs a Frontmost AI project.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this guidance to explain why AI apps mention a rival, and to find what the business can match.

    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 for a count of the rivals in a small set of answers.

    line 16
  5. Distinctive:

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

    line 17
  6. Very specific:

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

    line 21
  7. Distinctive:

    Read the rival's page: the business and the rival on AI Visibility, Win Rate, Position, and Sentiment, with the gap, for each AI app and …

    line 23
  8. Distinctive:

    Read Head to head. It holds what AI apps say when a buyer compares the two, with quotes.

    line 24
  9. Very specific:

    Read the answers that mention the rival.

    line 25
  10. Distinctive:

    Ask the person to confirm each fact about their business before you put it in the first group.

    line 34
  11. Distinctive:

    Never suggest contact with the rival, and never suggest a claim about the rival that the answers do not support.

    line 37
  12. Distinctive:

    Do not promise a result. Each step is a bet that the data supports.

    line 39

≈ “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

Rival gaps

Use this guidance to explain why AI apps mention a rival, and to find what the business can match.

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 for a count of the rivals in a small set of answers. It needs no account. To read recorded answers, the person connects Frontmost AI: https://frontmost.ai/connect
  • Never invent the data, and never fill a gap with a guess.

Steps

  1. Call get_rivals for the project and the scan in the request. The default order puts the most mentioned rival first.
  2. Pick the first rival unless the person names one. Call get_rivals again with its rival_id.
  3. Read the rival's page: the business and the rival on AI Visibility, Win Rate, Position, and Sentiment, with the gap, for each AI app and each topic.
  4. Read Head to head. It holds what AI apps say when a buyer compares the two, with quotes.
  5. Read the answers that mention the rival. Copy the answers_filter into get_answers. Read at least 10 answers, or all of them when there are fewer.
  6. Count the points that the answers repeat about the rival. A point counts once for each answer. Report "in 7 of 12 answers read", not "often".
  7. Sort each repeated point into one of three groups:
    • You can match it now: the same thing is true for the business, and the answers do not say it. The fix is to state the fact clearly on the business's own site and on the outside pages that AI apps cite.
    • You can match it with work: it is not true today. Say what must change. Do not write copy that claims it.
    • Do not chase it: it does not fit the business, or it is the rival's main strength.

Rules

  • Ask the person to confirm each fact about their business before you put it in the first group.
  • Find where the rival's mentions come from. Call get_sources and look for cited pages that list the rival and not the business. Those pages are the outreach targets.
  • The rival's own website is not a target. Read it only to learn the format and topics that work.
  • Never suggest contact with the rival, and never suggest a claim about the rival that the answers do not support.
  • Report each number with its counts. Link the url of the rival's page.
  • Do not promise a result. Each step is a bet that the data supports.

Output

Three parts: Where the gap is (the AI apps and topics with the largest gap, with counts), What AI repeats about the rival (up to 5 points, each with its count and one short quote), and What you can match (the three groups above, with one first action).

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.