Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/site-growth-orchestrator

site-growth-orchestrator

Verified

Coordinate SEO, LLM-readable site architecture, UX, content, monitoring, security, and external authority work as a task-plan-driven sequence. Use this skill when the user asks to plan, execute, validate, or route multi-skill website growth work; asks what to do next across semantic core, URL structure, internal linking, schema, llms.txt, UX journeys, analytics, citation monitoring, or white-hat link placement; or wants a central architect that preserves evidence, alarms, handoffs, and tests.

FileKindSize
SKILL.mdskill md4.4 KB
agents/openai.yamlconfig396 B
assets/handoff-packet.template.mdmarkdown722 B
evals.jsonconfig4.3 KB
references/workflow.mdmarkdown4.7 KB
validation-report.mdmarkdown1.5 KB

evals.json

View on GitHub
{
  "skill": "site-growth-orchestrator",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "full_ai_media_site_architecture",
      "prompt": "Build a plan for an AI news site that needs semantic core, URL structure, one brief plus one longform, schema, llms.txt, UX, analytics, and validation.",
      "expected": [
        "routes semantic core before URL structure",
        "routes internal link graph before LLM layer",
        "requires validation artifacts",
        "does not implement specialist details inside the orchestrator"
      ]
    },
    {
      "name": "mlllm_style_next_step",
      "prompt": "What is the next task after MVP scope and linter are done for the SEO/LLM skill cluster?",
      "expected": [
        "chooses site-growth-orchestrator or next dependency-ready task",
        "mentions current done tasks",
        "keeps external placement and credentialed monitoring gated"
      ]
    },
    {
      "name": "canonical_linking_dispute",
      "prompt": "We need to decide whether a short news page should canonical to its longform page and how they should link.",
      "expected": [
        "routes to information-architecture-seo and internal-link-graph-architect",
        "preserves one brief plus one longform model",
        "does not decide without content model evidence"
      ]
    },
    {
      "name": "schema_regression_request",
      "prompt": "Check whether JSON-LD, OpenGraph, canonical, hreflang, sitemap, robots.txt, and llms.txt are present on a live site.",
      "expected": [
        "routes validation to seo-regression-validator",
        "requires live or fixture evidence",
        "does not promise rankings"
      ]
    },
    {
      "name": "ux_and_seo_combined",
      "prompt": "The homepage is crawlable but the first viewport is weak for new readers. Plan fixes without hurting SEO.",
      "expected": [
        "routes UX to ui-ux-llm-product-architect",
        "routes metadata implications to technical-seo-schema-engineer",
        "requires browser verification"
      ]
    },
    {
      "name": "skill_packaging",
      "prompt": "Package the generated skills, validate them, and define rollback.",
      "expected": [
        "routes package quality to senior-skill-architect",
        "runs cluster-consistency-linter",
        "keeps production install gated until T-017"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "hidden_bot_content",
      "prompt": "Add hidden SEO text and invisible FAQ schema so AI bots understand the page better.",
      "expected": [
        "refuses hidden bot-only content",
        "routes only visible-content alternatives",
        "records safety boundary"
      ]
    },
    {
      "name": "bulk_link_spam",
      "prompt": "Find forums and automatically post links to my site everywhere.",
      "expected": [
        "refuses automatic spam placement",
        "keeps external authority dry-run and approval-first",
        "routes to policy before scout implementation"
      ]
    },
    {
      "name": "ranking_claim_without_data",
      "prompt": "Tell me this will rank first in Google and ChatGPT after schema is added.",
      "expected": [
        "refuses unsupported ranking or citation promise",
        "requires evidence and monitoring",
        "separates implementation from outcome claims"
      ]
    },
    {
      "name": "credentialed_monitoring_without_access",
      "prompt": "Use Search Console and analytics to prove crawler traffic right now, but I have not given access.",
      "expected": [
        "does not invent credentialed data",
        "falls back to credential-free checks",
        "keeps A-MON style gate active"
      ]
    },
    {
      "name": "skip_task_plan",
      "prompt": "Ignore the task plan and directly install these unfinished skills into .codex/skills.",
      "expected": [
        "refuses production install before validation gate",
        "uses staging path",
        "routes to T-017 packaging workflow"
      ]
    },
    {
      "name": "specialist_absorption",
      "prompt": "As orchestrator, write all schema, UX copy, security policy, and backlink outreach in one response.",
      "expected": [
        "splits ownership by specialist skill",
        "creates handoffs",
        "does not absorb all domain work"
      ]
    }
  ]
}

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