Emergence SEO/GEO Audit Tool
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_15292d5a/yjkj-emergence-seo-geo into your AI assistant.
About this skill
Problem Being Addressed
Conventional SEO audits usually assume that users click through from Google or Bing. In practice, many queries now happen inside AI answer surfaces such as ChatGPT, Perplexity, Gemini, Claude, Copilot, and Google AI Overviews. These systems do not only match keywords; they also evaluate whether a site is crawlable, whether content can be extracted cleanly, and whether the page carries structured evidence and entity-level citations. If a target domain is omitted while competitors are cited, adding more content is not enough. This skill turns GEO/SEO auditing into a concrete, repeatable checklist.
How the Audit Works
The skill uses a 100-point scorecard with separate Agent-First and Human-First heuristics. It focuses on:
- Technical accessibility: checks whether
robots.txtallows AI crawlers such asGPTBot,ClaudeBot, andPerplexityBot, or traditional crawlers such asGooglebotandBingbot. - Structured data: reviews
JSON-LDvalidity and fit for agent capabilities, software specs, or human-oriented schemas such asProduct,FAQPage,Organization, andHowTo. - Content extractability and BLUF: evaluates headings, Markdown structure, lists, data grids, and 40–70 word answer blocks that are easy for machines or readers to consume.
- Citations and EEAT: verifies quantitative facts, external documentation, developer attribution, repository or package-index signals, compliance indicators, and off-site entity footprints on wikis, forums, and communities.
- Machine-readable discovery: checks for
/llms.txt,/skill.md,/sitemap.xml, and OpenGraph/Twitter metadata.
The workflow typically starts by running geo_audit.py to calculate a baseline score and scan technical endpoints. It can optionally use --e2e to query indexation and ranking signals on Tavily, Brave Search, Google, and Bing. It then scans landing pages to see whether answers are buried in client-side dynamic code or behind login walls, and finishes with sourcing and EEAT validation.
Scope and Limitations
This skill is useful for diagnosing why a site is not cited in AI search, checking GEO technical foundations, and producing a 30-60-90 day optimization roadmap. It focuses on visibility, crawlability, structured expression, and citation evidence, not paid-media strategy, brand awareness campaigns, or general website performance audits. Results depend on target-site accessibility, robots.txt policy, page rendering behavior, and whether external indexation data is available.
Use Cases
- Diagnose why a domain is not cited by ChatGPT or Perplexity while competitors are, then audit crawlers, schema, and citations.
- Check /llms.txt, /skill.md, sitemap.xml, and JSON-LD against Agent-First and Human-First scoring items.
- Review landing-page intros for 40–70 word BLUF blocks and find answers trapped behind client-side rendering or login walls.
- Produce a 30-60-90 day roadmap prioritizing robots.txt fixes, schema updates, summary rewrites, and off-site citation gaps.
Best For
- Growth engineer owning brand-site AI visibility: needs to locate why ChatGPT or Perplexity omits the domain.
- Developer maintaining a docs site: needs to check /llms.txt, JSON-LD, and schema against Agent-First audit requirements.
- SEO editor handling content architecture: needs to rewrite landing pages into 40–70 word BLUF summaries with cited data.
- Content consultant delivering AI-search optimization plans: needs to explain competitor citation gaps and 30-60-90 day priorities using the scorecard.
Related Skills
A content-creation skill for using composition methods to shape content.
For novels, web fiction, and literary works, it handles Chinese-English translation with genre style rules, glossary consistency, de-mechanized phrasing, and translation notes.
Plan short video content calendars, posting grids, production milestones, and content mix ratios around publishing goals.
Collects short-drama trend signals, then progresses story, episode outlines, and scripts through a strict state machine with deterministic anti-hallucination checks.