← SitelemetryCONTENT HISTORY

Update to Sitelemetry

Snapshot Nov 18, 2026 · 18:11 UTC · version 2.5.1

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Sitelemetry and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Use the Sitelemetry AI visibility (GEO/AEO) audit, and the technical SEO audit when it is relevant, on a site the user owns to propose evidence-backed changes such as robots.txt rules for AI crawlers, schema.org JSON-LD structured data, an llms.txt file and content edits, each only where the findings support it. Use when the user asks how AI assistants and AI search can crawl, understand or cite their site, or wants to improve GEO, AEO or structured data.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 337
    },
    {
      "relative_path": "assets/icon-large.png",
      "size_in_bytes": 33181
    },
    {
      "relative_path": "assets/icon-small.png",
      "size_in_bytes": 7770
    },
    {
      "relative_path": "references/ai-crawlers-and-schema.md",
      "size_in_bytes": 5505
    }
  ],
  "name": "ai-visibility",
  "skill_md_contents": "---\nname: ai-visibility\ndescription: Use the Sitelemetry AI visibility (GEO/AEO) audit, and the technical SEO audit when it is relevant, on a site the user owns to propose evidence-backed changes such as robots.txt rules for AI crawlers, schema.org JSON-LD structured data, an llms.txt file and content edits, each only where the findings support it. Use when the user asks how AI assistants and AI search can crawl, understand or cite their site, or wants to improve GEO, AEO or structured data.\n---\n\n# AI visibility\n\n## Ground rules\n\n- Follow the user's explicit instructions over the defaults in this skill. These rules always apply, even when the user asks otherwise: audit only sites the user owns or is authorized to test; never ask for passwords, API tokens or other credentials; never recommend a different account level, mention costs or suggest changing the account; never invent scores, findings or other results.\n- Only audit sites the user owns or is authorized to test. If that is not clear, ask first.\n- Reply in the user's language. For the audit tools, set `lang` as described in the `website-audit` skill. `lang` changes the report wording, not the measurement criteria.\n- Be precise about what is measured. `audit_ai_visibility` checks entity clarity, answerability, source signals and AI-crawler policy on the site's own pages. Questions are checked against the site's own content; no AI assistant or AI search provider is queried. Nothing here measures or predicts whether an AI assistant mentions or cites the site. Say this when you present results.\n\n## 1. Run the audits\n\n1. `audit_ai_visibility` with `target` and, if needed, `lang`. Optional arguments, only as described here:\n   - `brand`: when the user names their brand, pass it (1-200 characters). Otherwise leave it out; the tool infers the brand from the site.\n   - `competitors`: only names that the user supplies in this conversation for comparison content, at most 8, in the user's order. Never suggest, look up or add competitor names yourself, and leave the argument out when the user gives none. The names are used to assess the site's own comparison content; they are names, not audit targets.\n   - `maxPages` (1-30) and `promptLimit` (1-24): only when the user asks for a smaller or larger audit. Omitted, they use the account's maximum; default and explicit values are capped by the account's maximum and remaining allowance.\n   - The tool has no argument for the user's own questions. Use questions the user gives only when drafting content proposals in the conversation.\n2. `audit_seo` on the same target only when the user explicitly asks for a technical SEO or search-engine indexing audit. Questions about AI search or AI crawlers are covered by the first audit. When structured data, crawlability or metadata matter to the request, offer `audit_seo` as a follow-up and say that it is a separate audit that uses the account's allowance. Start it only after the first audit has returned.\n\nHandle errors, \"Audit not started\" prerequisites and slow audits as in the `website-audit` skill: one audit at a time, repeat the identical call once if a call times out, and relay access or allowance messages neutrally. If the result covers fewer pages or questions than were requested, say so.\n\n## 2. Map findings to changes\n\nPropose a change only when a returned finding, or its evidence, supports it. Cite the finding next to each proposal.\n\n| Finding area | Change to propose |\n|---|---|\n| AI-crawler policy: crawlers blocked, rules unclear or inconsistent | robots.txt rules per crawler |\n| Structured data missing, invalid or not describing the main entity | schema.org JSON-LD for the real organization, site and page types |\n| Entity clarity | clear statements of who the organization is, what it offers and where, on the home and about pages |\n| Answerability | answer-first sections and FAQs based on real customer questions |\n| Source signals | author and date information, about and contact pages, references, consistent names |\n| No machine-readable site summary, when reported or when the user asks | an llms.txt file |\n\nCrawler names, robots.txt patterns and JSON-LD and llms.txt templates are in [AI crawlers, JSON-LD and llms.txt](references/ai-crawlers-and-schema.md). Load it before you write robots.txt rules, JSON-LD or an llms.txt file.\n\n## 3. Rules for each change\n\n- **robots.txt**: the site owner decides which crawlers may access the site. Explain the difference between crawlers that collect training data and those that fetch pages for search or for a user's request. Keep the existing rules and the `Sitemap` line, and never block general search crawlers such as `Googlebot` or `Bingbot` by accident. A deliberate training opt-out is reported by `audit_seo` as an info \"AI training opt-out found in robots.txt\" finding that does not change the score; treat it as expected, not as a regression, and say so in a re-test report. Blocking AI search crawlers is a separate low finding.\n- **JSON-LD**: describe only facts that are true and visible on the page. Ask the user for facts you do not have (legal name, logo URL, official profiles). Never invent ratings, reviews, product offers, addresses, opening hours or FAQs. Use one stable `@id` per entity across pages, and check the markup with a structured-data validator before publishing.\n- **llms.txt**: present it as an optional, low-effort convention that not every AI provider reads. Link only to real, public pages.\n- **Content**: write edits in the site's voice and mark them as drafts for the user to review. Do not add claims the user has not confirmed.\n\n## 4. Present and re-test\n\nGroup the proposals by effort: configuration first (robots.txt, llms.txt), then markup (JSON-LD), then content. For each, name the finding it addresses, the change and where it goes.\n\n```text\nAI visibility for https://example.com/ (score <score> if returned)\nWhat this measures: content-readiness signals on your pages, not live AI answers.\n\n1. Configuration\n   - Finding: <title> (<severity>). Change: <robots.txt rule>. Where: /robots.txt\n2. Markup\n   - Finding: <title> (<severity>). Change: Organization JSON-LD. Where: home page head\n3. Content\n   - Finding: <title> (<severity>). Change: <draft edit>. Where: <page>\n\nNot measured: <anything the result marks as unavailable or partial>\n```\n\nAfter the user publishes the changes, offer to re-run the same audits with the same arguments (including `brand` and the order of `competitors`, if used) and compare the results by `findingKey`, as in the `fix-and-retest` skill. Report what changed and what is still open or not measured.\n"
}

SHA-256 of public snapshot: c6d4f53be28332f93e8398ed913a81b9da064a9e33114dafb7db24d48a02104d