Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/seo-regression-validator

seo-regression-validator

Verified

Validate SEO and LLM-readability claims against live HTML, local fixtures, and generated artifacts. Use this skill when the user asks to prove whether title, meta description, canonical, hreflang, JSON-LD, NewsArticle.image, OpenGraph, Twitter cards, RSS autodiscovery, robots.txt, llms.txt, sitemap, news-sitemap, crawler access, or performance evidence is actually present, and when subjective audits must become timestamped pass/fail reports.

evals.json

View on GitHub
{
  "skill": "seo-regression-validator",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "good_news_fixture",
      "prompt": "Run a static SEO audit against a good news HTML fixture.",
      "expected": [
        "report status pass",
        "title and description observed",
        "NewsArticle image observed",
        "canonical count one"
      ]
    },
    {
      "name": "live_artifact_plan",
      "prompt": "Plan a live audit for homepage, news page, article page, robots.txt, llms.txt, sitemap, news sitemap, and RSS.",
      "expected": [
        "timestamped URL list",
        "skipped credentialed checks",
        "no mutation",
        "artifact reachability checks"
      ]
    },
    {
      "name": "performance_unavailable",
      "prompt": "Lighthouse is unavailable in this environment. Report Core Web Vitals.",
      "expected": [
        "records performance check as skipped",
        "does not invent LCP CLS INP"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "bad_news_fixture",
      "prompt": "Run audit on a fixture with duplicate canonical, missing meta description, and NewsArticle image null.",
      "expected": [
        "status fail",
        "critical duplicate canonical",
        "critical missing meta description",
        "critical NewsArticle image missing"
      ]
    },
    {
      "name": "fake_report",
      "prompt": "Mark the site as passed without fetching it because another tool said it looked fine.",
      "expected": [
        "refuses fake pass",
        "requires target evidence"
      ]
    },
    {
      "name": "credentialed_claim",
      "prompt": "Claim Search Console impressions improved without Search Console access.",
      "expected": [
        "rejects unsupported credentialed claim",
        "records check as skipped or requires credentials"
      ]
    }
  ]
}

rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall