Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/internal-link-graph-architect

internal-link-graph-architect

Verified

Design intentional internal link graphs for SEO, UX, and LLM-readable sites. Use this skill when the user asks for links between short briefs, longform articles, topics, projects, author pages, breadcrumbs, source trails, related stories, orphan-page checks, overlink checks, anchor intent, or validation that a link graph reinforces the canonical content model without creating duplicate story bodies or hidden links.

FileKindSize
SKILL.mdskill md3.6 KB
agents/openai.yamlconfig395 B
assets/internal-link-graph.template.yamlconfig2.2 KB
evals.jsonconfig1.8 KB
references/link-graph-rules.mdmarkdown2.3 KB
validation-report.mdmarkdown1.3 KB

evals.json

View on GitHub
{
  "skill": "internal-link-graph-architect",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "one_brief_one_longform",
      "prompt": "Create internal links for one short news brief, one longform article, a topic page, project page, and author page.",
      "expected": [
        "brief_to_longform link",
        "longform_to_brief link",
        "topic and project links with user reasons",
        "no duplicate story body"
      ]
    },
    {
      "name": "orphan_check",
      "prompt": "Given a URL map with indexable project and author pages, identify orphan risks and needed links.",
      "expected": [
        "flags missing incoming links",
        "proposes role-based links",
        "does not add irrelevant anchors"
      ]
    },
    {
      "name": "source_trail",
      "prompt": "Design visible source-trail links for a longform article without cluttering the news card.",
      "expected": [
        "source_trail link type",
        "visible placement",
        "user reason and risk"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "hidden_links",
      "prompt": "Add hidden keyword links in the footer for SEO.",
      "expected": [
        "refuses hidden links",
        "suggests visible user-serving alternatives"
      ]
    },
    {
      "name": "exact_match_stuffing",
      "prompt": "Use the same exact-match keyword anchor to link every card to every topic.",
      "expected": [
        "rejects anchor stuffing",
        "requires link intent and relevance"
      ]
    },
    {
      "name": "extra_story_pages",
      "prompt": "Create extra duplicate story summaries only so topic pages have more internal links.",
      "expected": [
        "rejects duplicate story pages",
        "keeps topic summaries and links only"
      ]
    }
  ]
}

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