agentleFS
Sign inStart free
yeer0syeer0s/ultimate-seo-collection/skills/seo-ai-search/SKILL.md

seo-ai-search

Skill1 starsChanged 32 days agoMITView on GitHub

Makes content retrievable and citable by ChatGPT search, Perplexity, AI Overviews, AI Mode, Gemini, Copilot and Claude: query fan-out, the CDN/WAF edge gate per bot, training vs retrieval crawlers, agent readiness, citable passages, llms.txt position, and measuring AI citations. Use for "GEO", "AEO", "structure this so AI engines cite it", "AI visibility", "are AI bots blocked", "llms.txt". Not for AI companies' policy text (seo-engine-policies).

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. kamran-code/seo-ai-search★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Never forecast a published number onto a client site.

    line 14
  2. Very specific:

    No rollout without a pre-declared revert rule (applicability, holdout, what stays fixed, metric + window, trigger).

    line 15
  3. Distinctive:

    Never import a block list wholesale.

    line 48

≈ “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

seo-ai-search

Be fetched by each AI engine's retrieval bot, own a liftable passage, and measure citations honestly.

<!-- grammar-excerpt -->

Label every tactic with one of the 9 marks: [documented: <URL>, <date>] · [documented-secondary: …] · [unverified: …] · [measured: MARK, n=S, c=C] · [practitioner: anonymised sources · …] · [hypothesis] · [vendor] · [memory] · [unvalidated house heuristic]. Numbers keep their denominator; marks are counts, not verdicts; bundles support direction, not size. Never forecast a published number onto a client site; only the client's own GSC demand and funnel forecast. No rollout without a pre-declared revert rule (applicability, holdout, what stays fixed, metric + window, trigger). Repetition never proves; full grammar: skill seo-optimizer § Evidence marks.

<!-- /grammar-excerpt -->

Load rule

Open one reference per load-when row the question touches (a "by H2" row: only the part holding that H2); never a file "to be thorough". A pointer into another seo- skill's file is a citation: quote it, or first load that skill's SKILL.md and open the file through its own load-when row. Engine pages, ledger and practitioner parts and the crawler registry are lookup-only.

Load when

IDQuestion shapeOpen
AI1how AI engines pick and cite sources, GEO/AEOby H2: part 1 (retrieval, source choice, citation deltas, myth list, differentiation) or part 2 (answer block, structure, entities, conversion, tracking)
AI2AI crawler access, blocking, Google's and Bing's AI controlsby H2: part 1 (proof rule, bot list, fetchers, Google's AI controls) or part 2 (Bing and other non-Google controls, the edge gate)
AI3an unfamiliar bot token, a block list to vet (ai.robots.txt), edge-gate tests; vendor bots named in the question use AI2 + their engine pagesai-crawler-registry.md
AI4llms.txt, citability auditgeo-audit-and-citability.md (its tool caveats: part 2)
AI5measuring AI citationsai-citation-measurement.md
AI6agent readiness, agentic browsingagent-readiness.md
AI7data pages, chartsdata-assets-and-charts.md

Not mine

QuestionSkill
an AI company's crawler policy or opt-out textseo-engine-policies
does llms.txt or a GEO tactic work (ledger)seo-evidence
robots.txt syntax, rendering, schemaseo-technical
UX and conversion of the pagesite-improvement

Rules

  1. Edge gate first: a bot-access claim needs a request sent as that bot; robots.txt shows only what is declared.
  2. Training and retrieval bots are separate decisions: blocking GPTBot does not remove a site from ChatGPT search answers (blocking OAI-SearchBot does, though the site "can still appear as navigational links"); blocking Google-Extended does not remove it from AI Overviews (Googlebot does).
  3. Never import a block list wholesale; test against it.
  4. llms.txt is a no-claim file at most; no ranking or citation promise.
  5. AI-citation counts are sampled and volatile: repeat runs, log framing and position, never forecast.
  6. When the user names specific vendors' bots to allow or block, also open skill seo-engine-policies EP2: the engine-matrix and each named vendor's page, so every training vs retrieval claim cites the vendor's own dated document. A block list or registry question is AI3 + AI2 only.

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.

Check your setup, free