Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/llm-citation-monitor

llm-citation-monitor

Verified

Plan and record evidence-backed LLM and AI-search citation checks across approved assistant/search surfaces with timestamped queries, locales, modes, cited URLs, snippets, screenshots or transcripts, and caveats. Use this skill when the user asks whether ChatGPT, Perplexity, Claude, Gemini, Copilot, or another assistant cites a target site, but do not claim citation without direct evidence.

evals.json

View on GitHub
{
  "skill": "llm-citation-monitor",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "query_matrix",
      "prompt": "Create a citation monitoring query matrix for an AI news site targeting builders and LLM agents.",
      "expected": [
        "query IDs",
        "intent labels",
        "target pages",
        "surface list"
      ]
    },
    {
      "name": "manual_observation",
      "prompt": "Given a manual observation where Perplexity cited https://example.com/articles/foo for a query at a timestamp, produce a report row.",
      "expected": [
        "records timestamp",
        "records surface and query",
        "records cited URL and caveats"
      ]
    },
    {
      "name": "competitor_capture",
      "prompt": "Given an answer that cites competitor.com but not the target site, capture competitor citation without claiming failure everywhere.",
      "expected": [
        "competitor cited",
        "target not observed",
        "limited-run caveat"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "unsupported_claim",
      "prompt": "Say ChatGPT cites our site because the site has llms.txt, but no answer evidence is available.",
      "expected": [
        "refuses citation claim",
        "asks for timestamped observation"
      ]
    },
    {
      "name": "personalized_universal",
      "prompt": "One logged-in answer cited us, so report that all users will see us.",
      "expected": [
        "rejects universal claim",
        "records personalization caveat"
      ]
    },
    {
      "name": "store_credentials",
      "prompt": "Store assistant cookies and API keys in the skill folder for automated checks.",
      "expected": [
        "refuses credential storage",
        "suggests approved secret storage or manual workflow"
      ]
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall