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

answerfirst

Skill432 starsChanged 10 days agoMITView on GitHub

Puts a direct answer under each H2 and an AI Overview summary on top.

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

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When a live page is named, get_site_audit_summary and list_site_audit_issues for its latest audit: the direct-answer and …

    line 23
  2. Distinctive:

    If the person pasted the text, work from it and read nothing else unless needed.

    line 25
  3. Distinctive:

    Write a summary for the top of the page: two or three sentences that answer the page's main question, the way an AI Overview would.

    line 29
  4. Distinctive:

    Keep every fact, figure and claim exactly as the source has it, and the brand's voice: change the order, not the personality.

    line 33
  5. Distinctive:

    Don't add facts, figures or promises that weren't in the text.

    line 41
  6. Distinctive:

    Don't shorten an answer until it is no longer true.

    line 42
  7. Distinctive:

    Don't touch locked passages without saying so.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Answer-first rewrite

Turn sections that warm up slowly into ones that answer first, so an AI engine can lift them as they are.

When to use

  • "Make this page answer-first", "Rewrite our intro so AI quotes it", "Why doesn't AI quote this page?"
  • For a whole page, work section by section, the summary first.

What to read

  1. get_draft when the person names a draft: its passages, and which ones AI quotes now (locked).
  2. list_prompts or get_fanouts for the page's topic: the questions each section should answer.
  3. When a live page is named, get_site_audit_summary and list_site_audit_issues for its latest audit: the direct-answer and bottom-line-up-front checks.

If the person pasted the text, work from it and read nothing else unless needed.

Steps

  1. Write a summary for the top of the page: two or three sentences that answer the page's main question, the way an AI Overview would.
  2. Under each H2, put a direct answer first: one or two sentences, 50 words or fewer, that answer the heading on their own. Detail, reasons and caveats come after.
  3. One question per section; its heading says the question or its answer.
  4. Define a term where it is first used, in the same sentence. Steps as a numbered list, options as a table.
  5. Keep every fact, figure and claim exactly as the source has it, and the brand's voice: change the order, not the personality. A passage AI quotes now stays word for word.

Output

For each section: Before, After, and one line on what changed. Then the full rewritten text in one block, ready to paste. When the person wants it kept, save it as a new draft 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.

Don't

  • Don't add facts, figures or promises that weren't in the text.
  • Don't shorten an answer until it is no longer true.
  • Don't touch locked passages without saying so.

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.