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

beat

Skill432 starsChanged 12 days agoMITView on GitHub

Compares your cited pages with theirs and drafts the changes.

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:

    Write a gap table, then draft the changes to the brand's page: new or rewritten passages, each tied to a gap.

    line 32
  2. Distinctive:

    Don't copy the competitor's text or structure: say what it answers, and answer it in the brand's own way.

    line 42
  3. Distinctive:

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

    line 43
  4. Distinctive:

    No tracking numbers on the page, and never claim the changes will win the prompt.

    line 44

≈ “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

Beat a competitor

On one prompt where a competitor wins, compare the pages AI engines cite for them with the brand's own, and draft the changes that close the gap.

When to use

  • "Help us beat Northwind on 'ai visibility tool'", "Why does ChatGPT pick them over us for this prompt?"
  • For a new side-by-side page instead, the Comparison page skill fits better.

What to read

  1. list_competitors, and get_competitor_comparison for the period: where the competitor leads, per platform.
  2. get_prompt_performance for the brand's prompts: the prompt where the gap is widest, if the person names none.
  3. list_ai_answers for that prompt: which pages each engine cites, theirs and the brand's.
  4. list_citations with the competitor and owned filters: the competitor's cited pages, and the brand's best page for the topic.
  5. get_fanouts for the prompt: the questions behind it that the cited pages answer.
  6. get_draft when the brand's page is a draft in the Content Library.

Steps

  1. Pick the prompt and the competitor. If either is unclear, ask, with the tracked competitors as the options.
  2. Compare the cited pages: what the competitor's page answers that the brand's doesn't, how directly it answers, its tables, FAQs, dates and sources.
  3. Write a gap table, then draft the changes to the brand's page: new or rewritten passages, each tied to a gap.
  4. Save the changed page as a new version with create_draft, method optimize, with the live page's address as its source; the app asks the person first when it should.

Output

  1. A gap table: What the cited page does, The competitor, The brand, Change.
  2. The drafted passages, ready to paste, with [placeholders] for facts only the brand can give.

Don't

  • Don't copy the competitor's text or structure: say what it answers, and answer it in the brand's own way.
  • Don't disparage the competitor, and claim nothing about them a read page doesn't say.
  • No tracking numbers on the page, and never claim the changes will win the prompt.

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.