Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/ux-journey-architect

ux-journey-architect

Verified

Map user journeys, onboarding paths, entry points, first actions, trust points, accessibility risks, and SEO/LLM handoffs for public websites without redesigning the visual system. Use this skill when the user asks how new readers, returning users, project reviewers, community members, buyers, or AI agents should move through a site and what each page must make clear before layout implementation.

FileKindSize
SKILL.mdskill md3.7 KB
agents/openai.yamlconfig357 B
assets/journey-map.template.mdmarkdown797 B
evals.jsonconfig1.8 KB
references/journey-workflow.mdmarkdown1.8 KB
references/ux-backlog.mdmarkdown1.4 KB
validation-report.mdmarkdown901 B

evals.json

View on GitHub
{
  "skill": "ux-journey-architect",
  "version": "0.1.0",
  "positive_cases": [
    {
      "name": "ai_news_site_new_reader",
      "prompt": "Map the new-reader journey for an AI news site with news briefs, longform explainers, projects, community links, and author profile.",
      "expected": [
        "new reader segment",
        "first viewport requirements",
        "brief to longform route",
        "trust points"
      ]
    },
    {
      "name": "project_reviewer_journey",
      "prompt": "Map the journey for a reviewer evaluating public OSS projects connected to a publication site.",
      "expected": [
        "project reviewer segment",
        "repository/artifact proof",
        "about/project/topic route"
      ]
    },
    {
      "name": "saas_product_path",
      "prompt": "Map journeys for a SaaS documentation and product site without changing its technical SEO structure.",
      "expected": [
        "role-specific entry points",
        "primary and secondary actions",
        "SEO handoff notes"
      ]
    }
  ],
  "negative_cases": [
    {
      "name": "decorative_redesign",
      "prompt": "Make the homepage mostly a decorative hero and move fresh content below the fold.",
      "expected": [
        "rejects hiding useful content",
        "preserves first viewport clarity"
      ]
    },
    {
      "name": "cta_without_intent",
      "prompt": "Add five equal CTA buttons to the hero because more choices convert better.",
      "expected": [
        "rejects equal CTA hierarchy",
        "requires user intent mapping"
      ]
    },
    {
      "name": "seo_model_conflict",
      "prompt": "Merge the news brief and longform article into a single landing funnel because it looks cleaner.",
      "expected": [
        "flags conflict with content model",
        "handoffs to IA/SEO owner if model should change"
      ]
    }
  ]
}
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