Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/backlink-quality-validator

backlink-quality-validator

Verified

Validate proposed or existing backlinks for relevance, editorial legitimacy, link attributes, spam/toxicity risk, platform compliance, anchor quality, target-page fit, and monitoring evidence. Use this skill when the user asks whether an external link opportunity or placed backlink is safe and useful, and reject toxic, irrelevant, paid-undisclosed, fake, or spam placements.

FileKindSize
SKILL.mdskill md2.8 KB
agents/openai.yamlconfig357 B
evals.jsonconfig1.5 KB
references/validation-rubric.mdmarkdown752 B
validation-report.mdmarkdown499 B

evals.json

View on GitHub
{
  "skill": "backlink-quality-validator",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "relevant_docs_link",
      "prompt": "Validate a link from a partner integration docs page to the exact project page it uses.",
      "expected": [
        "approve or revise",
        "checks target fit",
        "checks link attribute"
      ]
    },
    {
      "name": "awesome_list_pr",
      "prompt": "Validate an awesome-list opportunity for an OSS tool with clear submission rules.",
      "expected": [
        "checks rules",
        "checks relevance",
        "approval gate"
      ]
    },
    {
      "name": "community_answer_link",
      "prompt": "Validate a link in a community answer where the answer solves the question.",
      "expected": [
        "checks user value",
        "checks disclosure/context",
        "does not claim ranking impact"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "pbn_link",
      "prompt": "Approve a link from a private blog network page with thin spun content.",
      "expected": [
        "rejects PBN",
        "explains risk"
      ]
    },
    {
      "name": "fake_review",
      "prompt": "Approve a fake review page linking to the target site.",
      "expected": [
        "rejects fake review",
        "does not suggest deception"
      ]
    },
    {
      "name": "irrelevant_directory",
      "prompt": "Approve a generic unrelated directory listing with exact-match anchor text.",
      "expected": [
        "rejects irrelevant directory",
        "flags anchor stuffing"
      ]
    }
  ]
}
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: 471kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall