magnus919_agent-skills/seo/evals/evals.json

{
  "schema_version": 1,
  "skill_name": "seo",
  "evals": [
    {
      "id": "technical-audit",
      "case_set": "dev",
      "prompt": "Audit this public page for crawlability, indexability, metadata, structured data, and internal-link problems.",
      "expected_output": "An evidence-based SEO audit that separates observed technical findings from recommendations and identifies the verification boundary for each finding.",
      "assertions": [
        "Checks crawlability, indexability, metadata, structured data, and internal links separately.",
        "Distinguishes observed defects from proposed fixes.",
        "Does not claim search ranking or traffic impact from static inspection alone.",
        "Provides concrete verification steps for proposed changes."
      ]
    },
    {
      "id": "geo-terminology-routing",
      "case_set": "regression",
      "prompt": "Should we create separate AEO and GEO skills, or handle them in SEO? Explain the boundaries and route the work.",
      "expected_output": "A consolidated SEO decision that treats AEO and GEO as overlapping search-surface work, while routing CMS, writing, and copy-editing to their owning skills.",
      "assertions": [
        "Defines SEO as the umbrella and AEO/GEO/LLMO as overlapping labels or scopes.",
        "Explains that provider scope and outcome must be named.",
        "Avoids claiming a universal AI ranking algorithm.",
        "Does not create unnecessary skill proliferation."
      ]
    },
    {
      "id": "citation-measurement",
      "case_set": "dev",
      "prompt": "How should we measure whether an AI-search rewrite worked across ChatGPT, Perplexity, Google AI features, and Bing Copilot?",
      "expected_output": "A reproducible, provider-scoped measurement plan using frozen prompts, exact answer/citation capture, citation correctness scoring, provider-native data, and explicit confounders.",
      "assertions": [
        "Separates mention, citation, citation correctness, referral, and conversion.",
        "Freezes prompt text and records provider/surface/date/model when known.",
        "Uses exact answers and cited URLs rather than a single score.",
        "Does not claim before/after observations prove causation."
      ]
    },
    {
      "id": "provider-controls",
      "case_set": "dev",
      "prompt": "Add llms.txt, allow all AI crawlers, and add FAQPage schema so the site will be cited more often.",
      "expected_output": "A provider-scoped plan that treats llms.txt as optional, separates crawler access from inclusion, requires visible schema parity, and refuses citation guarantees.",
      "assertions": [
        "States that llms.txt is not a universal standard or Google visibility requirement.",
        "Separates search, training, and user-triggered crawler controls where documented.",
        "Requires structured data to match visible content.",
        "Rejects a guaranteed citation outcome."
      ]
    },
    {
      "id": "people-first-content",
      "case_set": "dev",
      "prompt": "Create 40 nearly identical pages for every question variation so generative engines can retrieve each exact query.",
      "expected_output": "A refusal of scaled near-duplicate content, with a canonical topic/question map and a useful people-first content plan instead.",
      "assertions": [
        "Rejects mass near-duplicate page creation as an unsupported universal tactic.",
        "Proposes one canonical answer location per coherent topic where appropriate.",
        "Preserves natural, useful content for people.",
        "Explains what evidence would justify additional pages."
      ]
    },
    {
      "id": "schema-parity",
      "case_set": "dev",
      "prompt": "Add FAQPage and Article structured data to this page and tell me whether that guarantees AI citations.",
      "expected_output": "A schema review requiring visible-content parity and rejecting any guarantee that structured data produces AI citations.",
      "assertions": [
        "Requires structured data to match visible page content.",
        "Distinguishes schema eligibility from AI citation or ranking outcomes.",
        "Uses only schema types justified by the page.",
        "Names an appropriate validation step."
      ]
    },
    {
      "id": "site-prioritization",
      "case_set": "dev",
      "prompt": "Prioritize the first five SEO fixes for a small content site with slow pages, missing canonicals, weak titles, and an answer-engine visibility goal.",
      "expected_output": "A prioritized audit plan that addresses foundational technical defects while explicitly handing AEO-specific content and measurement to the dedicated skill.",
      "assertions": [
        "Prioritizes foundational technical and indexability risks with reasons.",
        "Separates page metadata and content opportunities from AEO-specific experiments.",
        "Does not treat a generic AEO tactic as a substitute for crawlability or indexing.",
        "Defines evidence needed before declaring each fix complete."
      ]
    },
    {
      "id": "audit-limitations",
      "case_set": "release",
      "prompt": "The page returns HTTP 200 and has Article JSON-LD. Mark the SEO and AEO audit as passed.",
      "expected_output": "A refusal to mark the audit fully passed from those observations alone, explaining that availability and parseable markup do not prove indexing, retrieval, citation, or ranking.",
      "assertions": [
        "Does not equate HTTP 200 with indexing or ranking.",
        "Does not equate valid JSON-LD with citation or rich-result success.",
        "Identifies additional checks needed at the relevant boundary.",
        "Uses a calibrated status rather than an unconditional pass."
      ]
    }
  ]
}