Programmatic SEO

evals/evals.json

{
  "skill_name": "programmatic-seo",
  "evals": [
    {
      "id": 1,
      "prompt": "We want to create programmatic SEO pages for our CRM. We're thinking of 'CRM for [industry]' pages — like 'CRM for Real Estate,' 'CRM for Healthcare,' etc. How should we approach this?",
      "expected_output": "Should check for product-marketing.md first. Should identify this as the Personas playbook (industry-specific pages). Should apply the core principles: unique value per page (not just swapping the industry name), proprietary data or insights per industry, clean URL structure. Should recommend the implementation framework: keyword research for each industry variation, data requirements (what industry-specific content makes each page unique), template design, internal linking strategy between industry pages and main pages, and indexation strategy. Should warn against thin content (just template + keyword swap).",
      "assertions": [
        "Checks for product-marketing.md",
        "Identifies as Personas playbook",
        "Applies core principles (unique value, proprietary data, clean URLs)",
        "Recommends keyword research per variation",
        "Addresses data requirements for unique content",
        "Provides template design guidance",
        "Includes internal linking strategy",
        "Warns against thin content"
      ],
      "files": []
    },
    {
      "id": 2,
      "prompt": "Create a comparison page strategy. We want pages like 'Notion vs Asana', 'Notion vs Monday', etc. for all our competitors. We have 15 competitors.",
      "expected_output": "Should identify this as the Comparisons playbook. Should apply the programmatic approach for competitor comparison pages at scale. Should recommend: template structure for comparison pages, unique data per comparison (not just the same template with names swapped), keyword research for each '[competitor A] vs [competitor B]' variation, URL structure (/compare/notion-vs-asana), internal linking between comparison pages, and quality checks. Should cross-reference the competitors skill for page content structure.",
      "assertions": [
        "Identifies as Comparisons playbook",
        "Recommends template structure for scale",
        "Addresses unique data per comparison",
        "Includes keyword research for variations",
        "Provides URL structure recommendation",
        "Includes internal linking strategy",
        "Cross-references competitors skill",
        "Applies quality checks"
      ],
      "files": []
    },
    {
      "id": 3,
      "prompt": "we want to rank for '[tool name] integration' keywords. we integrate with 50+ tools and want a page for each. like 'Slack integration', 'Salesforce integration' etc.",
      "expected_output": "Should trigger on casual phrasing. Should identify this as the Integrations playbook. Should recommend: template design for integration pages (what it does, how to set up, use cases), unique content per integration (specific workflows, screenshots, setup steps), keyword research for '[tool] + [your product] integration', URL structure (/integrations/slack), hub page linking to all integration pages, and schema markup considerations. Should emphasize that each page needs genuine unique value, not just 'we integrate with [tool].'",
      "assertions": [
        "Triggers on casual phrasing",
        "Identifies as Integrations playbook",
        "Recommends template with unique content per integration",
        "Includes setup steps and use cases per page",
        "Provides URL structure recommendation",
        "Recommends hub page for all integrations",
        "Emphasizes genuine unique value per page"
      ],
      "files": []
    },
    {
      "id": 4,
      "prompt": "We built 500 programmatic pages but Google isn't indexing most of them. Only 80 are in the index. What's going wrong?",
      "expected_output": "Should diagnose the indexation problem. Should apply the quality checks and indexation strategy guidance. Should investigate: thin content (are pages providing unique value or just template + keyword?), crawl budget (500 pages may be fine but depends on site authority), internal linking (are the pages discoverable?), XML sitemap inclusion, duplicate/near-duplicate content issues. Should recommend specific fixes: improve content uniqueness, strengthen internal linking, submit sitemap, check robots.txt, use Search Console for indexation requests. Should warn that Google may choose not to index thin pages regardless.",
      "assertions": [
        "Diagnoses indexation problem",
        "Investigates thin content as likely cause",
        "Checks crawl budget considerations",
        "Checks internal linking to programmatic pages",
        "Checks XML sitemap and robots.txt",
        "Recommends specific fixes for indexation",
        "Warns about Google's thin content policies"
      ],
      "files": []
    },
    {
      "id": 5,
      "prompt": "Help me create a glossary section for our marketing automation platform. We want to define 200+ marketing terms and rank for '[term] definition' keywords.",
      "expected_output": "Should identify this as the Glossary playbook. Should apply the template design: term definition page template (definition, examples, related terms, how it applies to the user's product), hub/index page linking to all terms, URL structure (/glossary/[term]), alphabetical and categorical navigation. Should address quality: each definition should provide genuine value beyond a dictionary definition. Should include internal linking strategy and schema markup (DefinedTerm schema). Should recommend starting with highest-volume terms.",
      "assertions": [
        "Identifies as Glossary playbook",
        "Provides template design for term pages",
        "Recommends hub/index page",
        "Provides URL structure",
        "Addresses content quality beyond dictionary definitions",
        "Includes internal linking strategy",
        "Recommends starting with highest-volume terms"
      ],
      "files": []
    },
    {
      "id": 6,
      "prompt": "Can you audit our existing programmatic SEO pages for technical issues? We have crawl errors and some pages return 404s.",
      "expected_output": "Should recognize this is a technical SEO audit task, not a programmatic SEO strategy task. Should defer to or cross-reference the seo-audit skill, which handles crawlability, indexation, and technical SEO issues. Programmatic-seo focuses on strategy, template design, and content planning for scaled pages.",
      "assertions": [
        "Recognizes this as technical SEO audit task",
        "References or defers to seo-audit skill",
        "Explains that programmatic-seo is for strategy and template design",
        "Does not attempt full technical SEO audit"
      ],
      "files": []
    },
    {
      "id": 7,
      "prompt": "We want to launch 5,000 'integration + use case' pages. We're on Framer now. Where should we build them?",
      "expected_output": "Should check the platform requirements from the implementation-platforms reference: item limits at 5,000+ pages, data refresh, server-rendered HTML, conditional sections, per-page noindex and split sitemaps, and publish times. Should first check whether the current platform (Framer, whose higher plans reach tens of thousands of CMS items) can hold the set, and if not, weigh a reverse-proxied subpath against a subdomain (Google has no ranking preference; it's an effort and structure tradeoff) on a platform that can (e.g., WordPress, a hand-coded static/hybrid build, Webflow within its limits, a headless CMS, or an AI-native platform). Any Verified Partner tool named carries the disclosure plus an alternative. Should recommend proving it on a small batch of the strongest pages before scaling.",
      "assertions": [
        "Checks item limits and the other platform requirements",
        "Considers the current platform first",
        "Treats subpath vs subdomain as a tradeoff, not an SEO rule",
        "Gives several options with tradeoffs and discloses any partner tool",
        "Recommends a small first batch before scaling"
      ],
      "files": []
    }
  ]
}