GEO SKILL · geo-page-technical
yao-geo-page-audit
输入网址后诊断首页、代表性一级页和二级页的可抓取性、结构规范性、内容信号和 AI 可抽取性，输出权威证据台账、代码层/内容层修复清单、Schema/HTML 建议和 Word/PDF/固定目录 HTML/Markdown 四件套。
执行说明
--- name: yao-geo-page-audit description: Diagnose a website page or small page set for GEO readiness with authoritative public evidence, systematic page analysis, code/content/schema fixes, and four-format Chinese report delivery. metadata: owner: Yao Team family: geo-page-technical maturity: beta requires_web: true default_outputs: Word, PDF, HTML, Markdown --- <!-- Copyright © 2026 姚金刚. All rights reserved. Project: yao-geo-page-audit Created by: 姚金刚 Date: 2026-05-16 X: https://x.com/yaojingang --> # yao-geo-page-audit Use this skill when the user wants a GEO Page Audit, website/page GEO diagnosis, page technical audit, AI extractability audit, schema/HTML module advice, or code/content repair list for a URL. ## Job Given a target URL or website, diagnose the homepage, a representative first-level page, and a representative second-level page when possible. Output development-ready and content-ready recommendations that improve how public pages can be discovered, parsed, cited, and summarized by search-driven AI systems. By default, analyze public page readiness and public evidence coverage only; do not estimate AI-platform recall, rankings, citation share, or internal platform behavior unless the user provides platform sampling data. ## Workflow 1. Read `references/research-foundation.md`, `references/authority-reference-model.md`, and `references/report-module-taxonomy.md`. Frame the audit as a five-stage chain: discovery, retrieval candidate, main-content extraction, evidence quality, generated citation. 2. Identify page type and sample scope. If the input is a homepage, select homepage, one representative first-level page, and one representative second-level page. State the selection basis and unresolved input gaps. 3. Build an evidence ledger. Prefer official pages, official docs, schema/source code, standards, and peer-reviewed or arXiv research before third-party commentary. Mark each finding as observed, official, standard, research, inferred, or input gap. 4. Check crawlability and renderability: status code, robots, sitemap, canonical, meta robots, mobile-first parity, JavaScript dependency, and whether primary content appears in initial HTML. 5. Check structural quality: H1-H3, `main`/`article`, summary, table of contents, FAQ, tables, lists, breadcrumbs, internal links, anchor text, accessibility headings, and schema. 6. Check content evidence: conclusions first, full entity names, data, citations, cases, dates, author/source, freshness, objectivity, price, service boundaries, regional constraints, and source accountability. 7. Check AI extractability and public-answer material coverage: key-value facts, atomic facts, comparison tables, steps, Q&A, context-independent summary, paragraph independence, entity graph, sameAs links, and chunk-level citation readiness. Convert domestic platform concerns into high-intent question material gaps, not platform recall claims. 8. Produce code-layer fixes, content-layer fixes, page-module suggestions, schema/HTML snippets, priority, owner, acceptance test, risk, and estimated cost. 9. Deliver Word, PDF, sticky-menu HTML, and Markdown from one Markdown content source. Use the `kami` editorial report style in `references/report-formatting-spec.md` and `references/output-layout-policy.md`. 10. After DOCX generation, run `scripts/polish_docx.py` to apply Kami-style Word typography, margins, and table formatting. 11. Run `scripts/review_report_layout.py` and `references/quality-gates.md` before claiming completion. ## Boundaries - Without crawl/log access, only report front-end observable evidence. Do not infer log-level crawl frequency. - Without AI-platform sampling data, do not analyze platform recall, ranking, answer frequency, citation share, or platform-internal weighting. Replace that section with public material coverage and high-intent question readiness. - Distinguish user-visible content, crawler-readable content, and AI-extractable content. - Schema must match page body facts. Do not use schema to invent facts absent from the page. - Cite or name the evidence source for important claims. If the source is not available, label the recommendation as a hypothesis or input gap. - Domestic answer-material adaptation should consider search results, public webpages, news pages, encyclopedia pages, WeChat public articles, documentation, and help-center pages as possible public material. Treat actual platform answer performance as optional user-supplied evidence. ## Outputs - Page GEO diagnosis report. - Code-layer repair checklist. - Content-structure remodeling advice. - Schema and HTML module suggestions. - Evidence ledger and report completeness self-check. - Default four-piece deliverable: Word, PDF, HTML package, Markdown. - `quality-report.json` with artifact existence, byte size, and layout checks.
使用指南
<!-- Copyright © 2026 姚金刚. All rights reserved. Project: yao-geo-page-audit Created by: 姚金刚 Date: 2026-05-16 X: https://x.com/yaojingang --> # yao-geo-page-audit `yao-geo-page-audit` 是页面技术类 GEO skill，用于输入网址后诊断首页、代表性一级页和二级页，输出代码层与内容层优化建议，并默认支持 Word、PDF、固定目录 HTML、Markdown 四件套交付。 ## 使用场景 - 诊断官网首页、栏目页、产品页、文章页、帮助中心和文档页的 GEO 准备度。 - 检查页面是否可抓取、正文是否可读、结构是否清晰、事实是否可切片引用。 - 建立权威证据台账，区分页面观察、官方材料、标准依据、研究依据、推断和输入缺口。 - 输出开发可执行的 HTML、schema、渲染、移动端和 CMS 字段建议。 - 生成中文答案场景下的公开素材覆盖诊断报告；没有平台采样时不分析 AI 平台召回、排名或答案频次。 ## 示例报告 合成示例： - [Markdown](../../skills/yao-geo-page-audit/examples/example-site-demo/example-site-geo-page-audit.md) - [HTML](../../skills/yao-geo-page-audit/examples/example-site-demo/example-site-geo-page-audit.html) - [Word](../../skills/yao-geo-page-audit/examples/example-site-demo/example-site-geo-page-audit.docx) - [PDF](../../skills/yao-geo-page-audit/examples/example-site-demo/example-site-geo-page-audit.pdf) HubSpot 公开答案素材测试示例： - [Markdown](../../skills/yao-geo-page-audit/examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.md) - [HTML](../../skills/yao-geo-page-audit/examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.html) - [Word](../../skills/yao-geo-page-audit/examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.docx) - [PDF](../../skills/yao-geo-page-audit/examples/hubspot-domestic-ai-demo/hubspot-geo-page-audit.pdf) ## 质量门 - 必须覆盖可抓取性、渲染、结构规范性、内容信号、AI 可抽取性、schema 一致性、移动/性能和证据质量。 - 必须包含公开答案素材问题集、权威证据台账、优先级路线图和完整性自检。 - 没有用户提供的平台采样时，不输出平台召回、排名、答案频次或引用份额结论。 - 必须区分用户可见内容、爬虫可读内容和 AI 可抽取内容。 - 代码层建议必须给字段、代码片段或复测命令。 - schema 必须与页面正文事实一致。 - Word 表格最多 5 列；长 URL 和长命令必须拆分，防止向右溢出。 - HTML 报告必须包含固定跟随目录菜单栏，便于长报告阅读和定位。 - PDF 交付前必须渲染检查右边缘安全带。
来源：yaojingang/yao-geo-skills，MIT License。工作流输出仍需人工核验，不应把未证实的品牌主张直接发布。