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

rivals

Skill432 starsChanged 12 days agoMITView on GitHub

A one-page brief on one competitor across all AI platforms.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every number with the period it covers.

    line 39
  2. Distinctive:

    Don't disparage the competitor, and claim nothing about them a read page or answer doesn't say.

    line 43
  3. Distinctive:

    Don't copy their text: say what their pages answer.

    line 44
  4. Distinctive:

    Never promise the moves will win.

    line 45

≈ “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 brief

A one-page brief on one competitor in AI answers: where they lead, the prompts they win, the pages AI cites for them, how AI describes them, and what the brand can do.

When to use

  • "Tell me about Northwind in AI search", "Why does AI recommend them over us?", "Competitor moves."
  • To work on one prompt they win, the Beat a competitor skill fits better.

What to read

  1. list_competitors: the tracked competitors. When the person names none, ask, with these as the options.
  2. get_competitor_comparison for the period: where they lead, per platform.
  3. get_visibility_trend: how their visibility and the brand's moved.
  4. get_prompt_performance and list_ai_answers: the prompts they win, and the answers that recommend them.
  5. list_citations with the competitor filter: the pages AI cites for them.
  6. get_mention_competitors and list_mentions: how AI describes them beside the brand.

Steps

  1. Summarise where they stand against the brand in three lines.
  2. By platform: who leads, and by how much.
  3. The prompts they win that the brand doesn't, with the pages AI cites for them there.
  4. How AI describes them, quoted, and what it credits them with.
  5. Three moves for the brand, each tied to a prompt or a page.

Output

  1. One page: Summary, By platform, Prompts they win, Pages AI cites for them, How AI describes them, What to do next.
  2. Every number with the period it covers.

Don't

  • Don't disparage the competitor, and claim nothing about them a read page or answer doesn't say.
  • Don't copy their text: say what their pages answer.
  • Never promise the moves will win.

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.