Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/llm-friendly-site-architect

llm-friendly-site-architect

Verified

Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, visible TLDR or direct-answer blocks, source trails, entity pages, markdown alternates, AI crawler policy, topic-to-URL maps, assistant-readable public content, or LLM-friendly architecture that must preserve canonical SEO strategy without hidden bot-only facts or duplicate story bodies.

evals.json

View on GitHub
{
  "skill": "llm-friendly-site-architect",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "ai_news_site",
      "prompt": "Design LLM-friendly architecture for an AI news site with short briefs, longform explainers, topics, projects, author page, RSS, sitemap, robots, and llms.txt.",
      "expected": [
        "llms.txt section plan",
        "visible source trail policy",
        "brief plus longform preserved",
        "crawler verification needs"
      ]
    },
    {
      "name": "docs_site_markdown_alternates",
      "prompt": "Plan markdown alternates for a documentation-heavy site while keeping HTML canonical.",
      "expected": [
        "rel alternate policy",
        "no hidden facts",
        "sitemap/noindex decision"
      ]
    },
    {
      "name": "project_portfolio_entities",
      "prompt": "Make a project portfolio easier for AI agents to understand and cite.",
      "expected": [
        "entity pages",
        "project evidence",
        "author context",
        "no invented relationships"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "tldr_every_brief",
      "prompt": "Add TLDR blocks to every short news page even though each brief is already the short version.",
      "expected": [
        "does not add TLDR by default",
        "preserves page role",
        "suggests longform or topic summaries where appropriate"
      ]
    },
    {
      "name": "hidden_bot_facts",
      "prompt": "Put extra facts in llms.txt that are not visible on the site so agents understand us better.",
      "expected": [
        "refuses hidden bot-only facts",
        "requires visible public page updates first"
      ]
    },
    {
      "name": "duplicate_story_variants",
      "prompt": "Create three extra AI-readable story pages for every news item.",
      "expected": [
        "rejects duplicate public story variants",
        "uses canonical brief, longform, topic, and markdown policy instead"
      ]
    }
  ]
}

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