Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/semantic-core-architect

semantic-core-architect

Verified

Build evidence-labeled semantic cores for SEO, LLM-readable architecture, and site information design. Use this skill when the user asks for semantic core, query clusters, search intents, audience segments, entity/topic maps, language or locale priorities, competitor/source evidence, pillar-topic planning, or a structured handoff before URL architecture and internal linking. It must mark unknown search volume, difficulty, and ranking data as unknown instead of inventing metrics.

evals.json

View on GitHub
{
  "skill": "semantic-core-architect",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "ai_news_for_builders",
      "prompt": "Create a semantic core for an AI news site for builders with English and Russian sections, short briefs, longform explainers, projects, and author pages.",
      "expected": [
        "clusters by intent",
        "entities for site, author, pipeline, topics, projects",
        "language priorities",
        "unknown metrics instead of invented volume"
      ]
    },
    {
      "name": "saas_site",
      "prompt": "Build a semantic core for a B2B SaaS analytics product with docs, pricing, use cases, comparisons, and support.",
      "expected": [
        "commercial and support intents separated",
        "product and use-case entities",
        "page candidate notes without final URL decisions"
      ]
    },
    {
      "name": "personal_portfolio",
      "prompt": "Create semantic clusters for a personal engineering portfolio with projects, blog posts, talks, and consulting services.",
      "expected": [
        "Person and Project entities",
        "navigational and informational intents",
        "portfolio and service clusters separated"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "invent_volume",
      "prompt": "Make up search volume and difficulty for these keywords so the plan looks complete.",
      "expected": [
        "refuses invented metrics",
        "marks metrics unknown",
        "asks for keyword tool or Search Console evidence"
      ]
    },
    {
      "name": "final_canonical_policy",
      "prompt": "Decide final canonical URLs and write all hreflang for the site from this semantic core.",
      "expected": [
        "does not own final URL/canonical policy",
        "hands off to information-architecture-seo"
      ]
    },
    {
      "name": "ambiguous_audience",
      "prompt": "Build a semantic core for everyone interested in technology.",
      "expected": [
        "flags audience ambiguity",
        "creates assumptions or asks for narrowing",
        "does not overfit broad generic clusters"
      ]
    }
  ]
}

brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall