[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P45B1R3H9XENBPVNG8RYRZ":3,"skill-same:01M6P45B1R3H9XENBPVNG8RYRZ":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":38,"commitSha":67,"skillDirectory":68,"forksCount":13,"repositoryHtmlUrl":69,"repositoryHomepageUrl":6,"ownerHtmlUrl":70,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":71,"install":72,"resources":85},"01M6P45B1R3H9XENBPVNG8RYRZ","geo-content",null,"Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fgeo-content\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"content","geo content","geo","authority","PDF","expertise","headless","eeat","scripts","structure","main","community","reports","only","write","read","access","Bash","assessment","safe","2026-11-10 10:12:30",false,"---\nname: geo-content\ndescription: Content quality and E-E-A-T assessment for AI citability — evaluate experience,\n  expertise, authoritativeness, trustworthiness, and content structure\ncategory: seo\nrisk: safe\nsource: https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude\nsource_repo: zubair-trabzada\u002Fgeo-seo-claude\nsource_type: community\ndate_added: '2026-09-20'\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude\u002Fblob\u002Fmain\u002FLICENSE\ncompatibility: Docs-only; upstream helper scripts and templates are not bundled. Site\n  audits need network access to the target site; PDF reports need pandoc and headless\n  Chrome.\nversion: 1.0.0\nauthor: geo-seo-claude\ntags:\n- geo\n- content-quality\n- eeat\n- citability\n- ai-content\n- topical-authority\nallowed-tools: Read, Grep, Glob, Bash, WebFetch, Write\n---\n\n# GEO Content Quality & E-E-A-T Assessment\n\n## Purpose\n\nAI search platforms do not just find content — they evaluate whether content deserves to be cited. The primary framework for this evaluation is **E-E-A-T** (Experience, Expertise, Authoritativeness, Trustworthiness), which per Google's December 2025 Quality Rater Guidelines update now applies to **ALL competitive queries**, not just YMYL (Your Money Your Life) topics. Content that scores high on E-E-A-T is dramatically more likely to be cited by AI platforms.\n\nThis skill evaluates content through two lenses:\n1. **E-E-A-T signals** — does the content demonstrate real expertise and trust?\n2. **AI citability** — is the content structured so AI platforms can extract and cite specific claims?\n\n## How to Use This Skill\n\n1. Fetch the target page(s) — homepage, key blog posts, service\u002Fproduct pages\n2. Evaluate E-E-A-T across the 4 dimensions (25% each)\n3. Assess content quality metrics (structure, readability, depth)\n4. Check for AI content quality signals\n5. Evaluate topical authority across the site\n6. Score and generate GEO-CONTENT-ANALYSIS.md\n\n---\n\n## E-E-A-T Framework (100 points total)\n\n### Experience — 25 points\nFirst-hand knowledge and direct involvement with the topic. AI platforms increasingly distinguish between content that reports on a topic and content from someone who has DONE it.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| First-person accounts (\"I tested...\", \"We implemented...\") | 5 | 5 if present and specific, 3 if generic, 0 if absent |\n| Original research or data not available elsewhere | 5 | 5 if original data, 3 if references original work, 0 if none |\n| Case studies with specific results | 4 | 4 if detailed with numbers, 2 if general, 0 if none |\n| Screenshots, photos, or evidence of direct use | 3 | 3 if authentic evidence, 1 if stock\u002Fgeneric, 0 if none |\n| Specific examples from personal experience | 4 | 4 if specific and unique, 2 if somewhat specific, 0 if generic |\n| Demonstrations of process (not just outcome) | 4 | 4 if step-by-step from experience, 2 if partial, 0 if none |\n\n**What to flag as weak Experience:**\n- Content that only summarizes what other sources say without adding new perspective\n- Generic advice that could apply to any situation (\"It depends on your needs\")\n- No mention of actual usage, testing, or direct involvement\n- Hedging language that suggests lack of direct knowledge (\"reportedly\", \"supposedly\", \"some say\")\n\n### Expertise — 25 points\nDemonstrated knowledge depth and professional competence in the subject matter.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Author credentials visible (bio, degrees, certifications) | 5 | 5 if full credentials, 3 if basic bio, 0 if no author |\n| Technical depth appropriate to topic | 5 | 5 if thorough technical treatment, 3 if adequate, 0 if superficial |\n| Methodology explanation (how conclusions were reached) | 4 | 4 if clear methodology, 2 if some explanation, 0 if none |\n| Data-backed claims (statistics, research citations) | 4 | 4 if well-sourced, 2 if some data, 0 if unsupported claims |\n| Industry-specific terminology used correctly | 3 | 3 if accurate specialized language, 1 if basic, 0 if errors |\n| Author page with detailed professional background | 4 | 4 if dedicated author page, 2 if brief bio, 0 if none |\n\n**What to flag as weak Expertise:**\n- Claims without supporting evidence or sources\n- Surface-level coverage of complex topics\n- Misuse of technical terminology\n- No visible author or author without relevant credentials\n- Content that is broad and generic rather than deep and specific\n\n### Authoritativeness — 25 points\nRecognition by others as a credible source on the topic.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Inbound citations from authoritative sources | 5 | 5 if cited by major sources, 3 if some citations, 0 if none |\n| Author quoted or cited in press\u002Fmedia | 4 | 4 if media mentions, 2 if industry mentions, 0 if none |\n| Industry awards or recognition mentioned | 3 | 3 if relevant awards, 1 if tangential, 0 if none |\n| Speaker credentials (conferences, events) | 3 | 3 if listed, 0 if none |\n| Published in peer-reviewed or respected outlets | 4 | 4 if tier-1 publications, 2 if industry outlets, 0 if none |\n| Comprehensive topic coverage (topical authority) | 3 | 3 if site covers topic thoroughly, 1 if some coverage, 0 if isolated |\n| Brand mentioned on Wikipedia or authoritative references | 3 | 3 if Wikipedia, 2 if other encyclopedic refs, 0 if none |\n\n**What to flag as weak Authoritativeness:**\n- Single-topic site with no depth of coverage\n- No external validation of expertise claims\n- No backlinks from authoritative sources\n- Claims of authority without evidence (self-proclaimed \"expert\")\n\n### Trustworthiness — 25 points\nSignals that the content and its publisher are reliable and transparent.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Contact information visible (address, phone, email) | 4 | 4 if full contact info, 2 if email only, 0 if none |\n| Privacy policy present and linked | 2 | 2 if present, 0 if absent |\n| Terms of service present | 1 | 1 if present, 0 if absent |\n| HTTPS with valid certificate | 2 | 2 if valid HTTPS, 0 if not |\n| Editorial standards or corrections policy | 3 | 3 if documented, 1 if implicit, 0 if none |\n| Transparent about business model and conflicts | 3 | 3 if clear disclosures, 1 if some, 0 if none |\n| Reviews and testimonials from real customers | 3 | 3 if verified reviews, 1 if testimonials, 0 if none |\n| Accurate claims (no misinformation detected) | 4 | 4 if all claims accurate, 2 if mostly accurate, 0 if errors found |\n| Clear affiliate\u002Fsponsorship disclosures | 3 | 3 if properly disclosed, 0 if undisclosed or absent |\n\n**What to flag as weak Trustworthiness:**\n- No contact information or physical address\n- Missing privacy policy or terms\n- Undisclosed affiliate links or sponsored content\n- Claims that are verifiably false or misleading\n- No way to contact the publisher for corrections\n\n---\n\n## Content Quality Metrics\n\n### Word Count Benchmarks\nThese are **floors, not targets**. More words does not mean better content. The benchmark is the minimum length to adequately cover a topic for AI citability.\n\n| Page Type | Minimum Words | Ideal Range | Notes |\n|---|---|---|---|\n| Homepage | 500 | 500-1,500 | Clear value proposition, not a wall of text |\n| Blog post | 1,500 | 1,500-3,000 | Thorough but focused |\n| Pillar content \u002F Ultimate guide | 2,000 | 2,500-5,000 | Comprehensive topic coverage |\n| Product page | 300 | 500-1,500 | Descriptions, specs, use cases |\n| Service page | 500 | 800-2,000 | What, how, why, for whom |\n| About page | 300 | 500-1,000 | Company\u002Fperson story and credentials |\n| FAQ page | 500 | 1,000-2,500 | Thorough answers, not one-liners |\n\n### Readability Assessment\n- **Target Flesch Reading Ease**: 60-70 (8th-9th grade level)\n- This is NOT a direct ranking factor but affects citability — AI platforms prefer content that is clear and unambiguous\n- Overly academic writing (score \u003C 30) reduces citability for general queries\n- Overly simple writing (score > 80) may lack the depth needed for expertise signals\n\n**How to estimate without a tool:**\n- Average sentence length: 15-20 words is ideal\n- Average paragraph length: 2-4 sentences\n- Presence of jargon: should be defined when first used\n- Passive voice: \u003C 15% of sentences\n\n### Paragraph Structure for AI Parsing\nAI platforms extract content at the paragraph level. Each paragraph should be a self-contained unit of meaning.\n\n**Optimal paragraph structure:**\n- **2-4 sentences** per paragraph (1-sentence paragraphs are weak; 5+ sentences are hard to extract)\n- **One idea per paragraph** — do not mix topics within a paragraph\n- **Lead with the key claim** — first sentence should contain the main point\n- **Support with evidence** — remaining sentences provide data, examples, or context\n- **Quotable standalone** — each paragraph should make sense if extracted in isolation\n\n### Heading Structure\n- **One H1 per page** — the primary topic\u002Ftitle\n- **H2 for major sections** — should represent distinct subtopics\n- **H3 for subsections** — nested under relevant H2\n- **No skipped levels** — do not go from H1 to H3 without an H2\n- **Descriptive headings** — \"How to Optimize for AI Search\" not \"Section 2\"\n- **Question-based headings** where appropriate — these map directly to AI queries\n\n### Internal Linking\n- Every content page should link to 3-5 related pages on the same site\n- Links should use descriptive anchor text (not \"click here\")\n- Create a topic cluster structure: pillar page linked to\u002Ffrom all related subtopic pages\n- Orphan pages (no internal links pointing to them) are rarely cited by AI\n\n---\n\n## AI Content Assessment\n\n### AI-Generated Content Policy\nAI-generated content is **acceptable** per Google's guidance (March 2024 clarification) as long as it demonstrates genuine E-E-A-T signals and has human oversight. The concern is not HOW content is created but WHETHER it provides value.\n\n### Signs of Low-Quality AI Content (flag these)\n\n| Signal | Description |\n|---|---|\n| Generic phrasing | \"In today's fast-paced world...\", \"It's important to note that...\", \"At the end of the day...\" |\n| No original insight | Content that only rephrases widely available information |\n| Lack of first-hand experience | No personal anecdotes, case studies, or specific examples |\n| Perfect but empty structure | Well-formatted headings with shallow content beneath them |\n| No specific examples | Uses abstract explanations without concrete instances |\n| Repetitive conclusions | Each section ends with a variation of the same point |\n| Hedging overload | \"Generally speaking\", \"In most cases\", \"It depends on various factors\" without specifying which factors |\n| Missing human voice | No opinions, preferences, or professional judgment expressed |\n| Filler content | Paragraphs that could be deleted without losing information |\n| No data or sources | Claims presented as facts without attribution or evidence |\n\n### High-Quality Content Signals (regardless of production method)\n\n| Signal | Description |\n|---|---|\n| Original data | Surveys, experiments, benchmarks, proprietary analysis |\n| Specific examples | Named products, companies, dates, numbers |\n| Contrarian or nuanced views | Disagreement with conventional wisdom, backed by reasoning |\n| First-person experience | \"When I tested this...\" or \"Our team found...\" |\n| Updated information | References to recent events, current data |\n| Expert opinion | Clear professional judgment, not just facts |\n| Practical recommendations | Specific, actionable advice, not vague guidance |\n| Trade-offs acknowledged | \"This approach works well for X but not for Y because...\" |\n\n---\n\n## Content Freshness Assessment\n\n### Publication Dates\n- Check for visible `datePublished` and `dateModified` in both the content and structured data\n- Content without dates is treated as less trustworthy by AI platforms\n- Dates should be specific (January 15, 2026) not vague (\"recently\")\n\n### Freshness Scoring\n\n| Criterion | Score |\n|---|---|\n| Updated within 3 months | Excellent — current and relevant |\n| Updated within 6 months | Good — still reasonably current |\n| Updated within 12 months | Acceptable — may need refresh |\n| Updated 12-24 months ago | Warning — review for accuracy |\n| No date or 24+ months old | Critical — AI platforms may deprioritize |\n\n### Evergreen Indicators\nSome content remains relevant regardless of age. Flag content as evergreen if:\n- It covers fundamental concepts that do not change (physics, basic math, legal definitions)\n- It is clearly labeled as a reference\u002Fguide for lasting concepts\n- It does not contain time-dependent claims (\"the latest\", \"currently\", \"in 2024\")\n\n---\n\n## Topical Authority Assessment\n\n### What It Is\nTopical authority measures whether a site comprehensively covers a topic rather than touching on it superficially. AI platforms prefer citing sites that are recognized authorities on their topics.\n\n### How to Assess\n1. **Content breadth**: Does the site have multiple pages covering different aspects of its core topic?\n2. **Content depth**: Do individual pages go deep into subtopics?\n3. **Topic clustering**: Are pages organized into logical groups with internal linking?\n4. **Content gaps**: Are there obvious subtopics that the site should cover but does not?\n5. **Competitor comparison**: Do competitors cover subtopics that this site misses?\n\n### Scoring\n\n| Level | Description | Score Impact |\n|---|---|---|\n| Authority | 20+ pages covering topic comprehensively, strong clustering | +10 bonus |\n| Developing | 10-20 pages with some clustering | +5 bonus |\n| Emerging | 5-10 pages on topic, limited clustering | +0 |\n| Thin | \u003C 5 pages, no clustering | -5 penalty |\n\n---\n\n## Overall Scoring (0-100)\n\n### Score Composition\n| Component | Weight | Max Points |\n|---|---|---|\n| Experience | 25% | 25 |\n| Expertise | 25% | 25 |\n| Authoritativeness | 25% | 25 |\n| Trustworthiness | 25% | 25 |\n| **Subtotal** | | **100** |\n| Topical Authority Modifier | | +10 to -5 |\n| **Final Score** | | **Capped at 100** |\n\n### Score Interpretation\n- **85-100**: Exceptional — strong AI citation candidate across platforms\n- **70-84**: Good — solid foundation, specific improvements will increase citability\n- **55-69**: Average — multiple E-E-A-T gaps reducing AI visibility\n- **40-54**: Below Average — significant content quality and trust issues\n- **0-39**: Poor — fundamental content strategy overhaul needed\n\n---\n\n## Output Format\n\nGenerate **GEO-CONTENT-ANALYSIS.md** with:\n\n```markdown\n# GEO Content Quality & E-E-A-T Analysis — [Domain]\nDate: [Date]\n\n## Content Score: XX\u002F100\n\n## E-E-A-T Breakdown\n| Dimension | Score | Key Finding |\n|---|---|---|\n| Experience | XX\u002F25 | [One-line summary] |\n| Expertise | XX\u002F25 | [One-line summary] |\n| Authoritativeness | XX\u002F25 | [One-line summary] |\n| Trustworthiness | XX\u002F25 | [One-line summary] |\n\n## Topical Authority Modifier: [+10 to -5]\n\n## Pages Analyzed\n| Page | Word Count | Readability | Heading Structure | Citability Rating |\n|---|---|---|---|---|\n| [URL] | [Count] | [Score] | [Pass\u002FWarn\u002FFail] | [High\u002FMedium\u002FLow] |\n\n## E-E-A-T Detailed Findings\n\n### Experience\n[Specific passages and pages with strong\u002Fweak experience signals]\n\n### Expertise\n[Author credentials found, technical depth assessment, specific gaps]\n\n### Authoritativeness\n[External validation found, topical authority assessment, gaps]\n\n### Trustworthiness\n[Trust signals present\u002Fmissing, accuracy concerns if any]\n\n## Content Quality Issues\n[Specific passages flagged with reasons and rewrite suggestions]\n\n## AI Content Concerns\n[Any low-quality AI content patterns detected, with specific examples]\n\n## Freshness Assessment\n| Page | Published | Last Updated | Status |\n|---|---|---|---|\n| [URL] | [Date] | [Date] | [Current\u002FStale\u002FNo Date] |\n\n## Citability Assessment\n### Most Citable Passages\n[Top 5 passages that AI platforms are most likely to cite, with reasons]\n\n### Least Citable Pages\n[Pages with lowest citability, with specific improvement recommendations]\n\n## Improvement Recommendations\n### Quick Wins\n[Specific content changes that can be made immediately]\n\n### Content Gaps\n[Topics the site should cover to strengthen topical authority]\n\n### Author\u002FE-E-A-T Improvements\n[Specific steps to strengthen E-E-A-T signals]\n```\n\n## When to Use\n\n- You need a Generative Engine Optimization task for a website: audit, citability, crawlers, schema, llms.txt, content, platform tuning, or client reporting.\n- Run read-only analysis first; propose site changes before making any.\n\n## Limitations\n\n- Audits are read-only analysis; never publish, deploy, or modify the target site without explicit approval.\n- Scores and citation likelihoods are heuristics, not guarantees from AI search platforms.\n- Docs-only import: upstream scripts, agents, hooks, and schema templates are not bundled.\n\n### Example\n\n```bash\ncurl -s https:\u002F\u002Fexample.com\u002Frobots.txt\ncurl -s https:\u002F\u002Fexample.com\u002Fllms.txt\n```\n\n> Adapted from [zubair-trabzada\u002Fgeo-seo-claude](https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude) (MIT); frontmatter, When to Use\u002FLimitations, and safety boundaries added for upstream compliance. Docs-only import: upstream runtime helpers not bundled.\n","# GEO Content Quality & E-E-A-T Assessment\n\n## Purpose\n\nAI search platforms do not just find content — they evaluate whether content deserves to be cited. The primary framework for this evaluation is **E-E-A-T** (Experience, Expertise, Authoritativeness, Trustworthiness), which per Google's December 2025 Quality Rater Guidelines update now applies to **ALL competitive queries**, not just YMYL (Your Money Your Life) topics. Content that scores high on E-E-A-T is dramatically more likely to be cited by AI platforms.\n\nThis skill evaluates content through two lenses:\n1. **E-E-A-T signals** — does the content demonstrate real expertise and trust?\n2. **AI citability** — is the content structured so AI platforms can extract and cite specific claims?\n\n## How to Use This Skill\n\n1. Fetch the target page(s) — homepage, key blog posts, service\u002Fproduct pages\n2. Evaluate E-E-A-T across the 4 dimensions (25% each)\n3. Assess content quality metrics (structure, readability, depth)\n4. Check for AI content quality signals\n5. Evaluate topical authority across the site\n6. Score and generate GEO-CONTENT-ANALYSIS.md\n\n---\n\n## E-E-A-T Framework (100 points total)\n\n### Experience — 25 points\nFirst-hand knowledge and direct involvement with the topic. AI platforms increasingly distinguish between content that reports on a topic and content from someone who has DONE it.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| First-person accounts (\"I tested...\", \"We implemented...\") | 5 | 5 if present and specific, 3 if generic, 0 if absent |\n| Original research or data not available elsewhere | 5 | 5 if original data, 3 if references original work, 0 if none |\n| Case studies with specific results | 4 | 4 if detailed with numbers, 2 if general, 0 if none |\n| Screenshots, photos, or evidence of direct use | 3 | 3 if authentic evidence, 1 if stock\u002Fgeneric, 0 if none |\n| Specific examples from personal experience | 4 | 4 if specific and unique, 2 if somewhat specific, 0 if generic |\n| Demonstrations of process (not just outcome) | 4 | 4 if step-by-step from experience, 2 if partial, 0 if none |\n\n**What to flag as weak Experience:**\n- Content that only summarizes what other sources say without adding new perspective\n- Generic advice that could apply to any situation (\"It depends on your needs\")\n- No mention of actual usage, testing, or direct involvement\n- Hedging language that suggests lack of direct knowledge (\"reportedly\", \"supposedly\", \"some say\")\n\n### Expertise — 25 points\nDemonstrated knowledge depth and professional competence in the subject matter.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Author credentials visible (bio, degrees, certifications) | 5 | 5 if full credentials, 3 if basic bio, 0 if no author |\n| Technical depth appropriate to topic | 5 | 5 if thorough technical treatment, 3 if adequate, 0 if superficial |\n| Methodology explanation (how conclusions were reached) | 4 | 4 if clear methodology, 2 if some explanation, 0 if none |\n| Data-backed claims (statistics, research citations) | 4 | 4 if well-sourced, 2 if some data, 0 if unsupported claims |\n| Industry-specific terminology used correctly | 3 | 3 if accurate specialized language, 1 if basic, 0 if errors |\n| Author page with detailed professional background | 4 | 4 if dedicated author page, 2 if brief bio, 0 if none |\n\n**What to flag as weak Expertise:**\n- Claims without supporting evidence or sources\n- Surface-level coverage of complex topics\n- Misuse of technical terminology\n- No visible author or author without relevant credentials\n- Content that is broad and generic rather than deep and specific\n\n### Authoritativeness — 25 points\nRecognition by others as a credible source on the topic.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Inbound citations from authoritative sources | 5 | 5 if cited by major sources, 3 if some citations, 0 if none |\n| Author quoted or cited in press\u002Fmedia | 4 | 4 if media mentions, 2 if industry mentions, 0 if none |\n| Industry awards or recognition mentioned | 3 | 3 if relevant awards, 1 if tangential, 0 if none |\n| Speaker credentials (conferences, events) | 3 | 3 if listed, 0 if none |\n| Published in peer-reviewed or respected outlets | 4 | 4 if tier-1 publications, 2 if industry outlets, 0 if none |\n| Comprehensive topic coverage (topical authority) | 3 | 3 if site covers topic thoroughly, 1 if some coverage, 0 if isolated |\n| Brand mentioned on Wikipedia or authoritative references | 3 | 3 if Wikipedia, 2 if other encyclopedic refs, 0 if none |\n\n**What to flag as weak Authoritativeness:**\n- Single-topic site with no depth of coverage\n- No external validation of expertise claims\n- No backlinks from authoritative sources\n- Claims of authority without evidence (self-proclaimed \"expert\")\n\n### Trustworthiness — 25 points\nSignals that the content and its publisher are reliable and transparent.\n\n**Signals to evaluate:**\n\n| Signal | Points | How to Score |\n|---|---|---|\n| Contact information visible (address, phone, email) | 4 | 4 if full contact info, 2 if email only, 0 if none |\n| Privacy policy present and linked | 2 | 2 if present, 0 if absent |\n| Terms of service present | 1 | 1 if present, 0 if absent |\n| HTTPS with valid certificate | 2 | 2 if valid HTTPS, 0 if not |\n| Editorial standards or corrections policy | 3 | 3 if documented, 1 if implicit, 0 if none |\n| Transparent about business model and conflicts | 3 | 3 if clear disclosures, 1 if some, 0 if none |\n| Reviews and testimonials from real customers | 3 | 3 if verified reviews, 1 if testimonials, 0 if none |\n| Accurate claims (no misinformation detected) | 4 | 4 if all claims accurate, 2 if mostly accurate, 0 if errors found |\n| Clear affiliate\u002Fsponsorship disclosures | 3 | 3 if properly disclosed, 0 if undisclosed or absent |\n\n**What to flag as weak Trustworthiness:**\n- No contact information or physical address\n- Missing privacy policy or terms\n- Undisclosed affiliate links or sponsored content\n- Claims that are verifiably false or misleading\n- No way to contact the publisher for corrections\n\n---\n\n## Content Quality Metrics\n\n### Word Count Benchmarks\nThese are **floors, not targets**. More words does not mean better content. The benchmark is the minimum length to adequately cover a topic for AI citability.\n\n| Page Type | Minimum Words | Ideal Range | Notes |\n|---|---|---|---|\n| Homepage | 500 | 500-1,500 | Clear value proposition, not a wall of text |\n| Blog post | 1,500 | 1,500-3,000 | Thorough but focused |\n| Pillar content \u002F Ultimate guide | 2,000 | 2,500-5,000 | Comprehensive topic coverage |\n| Product page | 300 | 500-1,500 | Descriptions, specs, use cases |\n| Service page | 500 | 800-2,000 | What, how, why, for whom |\n| About page | 300 | 500-1,000 | Company\u002Fperson story and credentials |\n| FAQ page | 500 | 1,000-2,500 | Thorough answers, not one-liners |\n\n### Readability Assessment\n- **Target Flesch Reading Ease**: 60-70 (8th-9th grade level)\n- This is NOT a direct ranking factor but affects citability — AI platforms prefer content that is clear and unambiguous\n- Overly academic writing (score \u003C 30) reduces citability for general queries\n- Overly simple writing (score > 80) may lack the depth needed for expertise signals\n\n**How to estimate without a tool:**\n- Average sentence length: 15-20 words is ideal\n- Average paragraph length: 2-4 sentences\n- Presence of jargon: should be defined when first used\n- Passive voice: \u003C 15% of sentences\n\n### Paragraph Structure for AI Parsing\nAI platforms extract content at the paragraph level. Each paragraph should be a self-contained unit of meaning.\n\n**Optimal paragraph structure:**\n- **2-4 sentences** per paragraph (1-sentence paragraphs are weak; 5+ sentences are hard to extract)\n- **One idea per paragraph** — do not mix topics within a paragraph\n- **Lead with the key claim** — first sentence should contain the main point\n- **Support with evidence** — remaining sentences provide data, examples, or context\n- **Quotable standalone** — each paragraph should make sense if extracted in isolation\n\n### Heading Structure\n- **One H1 per page** — the primary topic\u002Ftitle\n- **H2 for major sections** — should represent distinct subtopics\n- **H3 for subsections** — nested under relevant H2\n- **No skipped levels** — do not go from H1 to H3 without an H2\n- **Descriptive headings** — \"How to Optimize for AI Search\" not \"Section 2\"\n- **Question-based headings** where appropriate — these map directly to AI queries\n\n### Internal Linking\n- Every content page should link to 3-5 related pages on the same site\n- Links should use descriptive anchor text (not \"click here\")\n- Create a topic cluster structure: pillar page linked to\u002Ffrom all related subtopic pages\n- Orphan pages (no internal links pointing to them) are rarely cited by AI\n\n---\n\n## AI Content Assessment\n\n### AI-Generated Content Policy\nAI-generated content is **acceptable** per Google's guidance (March 2024 clarification) as long as it demonstrates genuine E-E-A-T signals and has human oversight. The concern is not HOW content is created but WHETHER it provides value.\n\n### Signs of Low-Quality AI Content (flag these)\n\n| Signal | Description |\n|---|---|\n| Generic phrasing | \"In today's fast-paced world...\", \"It's important to note that...\", \"At the end of the day...\" |\n| No original insight | Content that only rephrases widely available information |\n| Lack of first-hand experience | No personal anecdotes, case studies, or specific examples |\n| Perfect but empty structure | Well-formatted headings with shallow content beneath them |\n| No specific examples | Uses abstract explanations without concrete instances |\n| Repetitive conclusions | Each section ends with a variation of the same point |\n| Hedging overload | \"Generally speaking\", \"In most cases\", \"It depends on various factors\" without specifying which factors |\n| Missing human voice | No opinions, preferences, or professional judgment expressed |\n| Filler content | Paragraphs that could be deleted without losing information |\n| No data or sources | Claims presented as facts without attribution or evidence |\n\n### High-Quality Content Signals (regardless of production method)\n\n| Signal | Description |\n|---|---|\n| Original data | Surveys, experiments, benchmarks, proprietary analysis |\n| Specific examples | Named products, companies, dates, numbers |\n| Contrarian or nuanced views | Disagreement with conventional wisdom, backed by reasoning |\n| First-person experience | \"When I tested this...\" or \"Our team found...\" |\n| Updated information | References to recent events, current data |\n| Expert opinion | Clear professional judgment, not just facts |\n| Practical recommendations | Specific, actionable advice, not vague guidance |\n| Trade-offs acknowledged | \"This approach works well for X but not for Y because...\" |\n\n---\n\n## Content Freshness Assessment\n\n### Publication Dates\n- Check for visible `datePublished` and `dateModified` in both the content and structured data\n- Content without dates is treated as less trustworthy by AI platforms\n- Dates should be specific (January 15, 2026) not vague (\"recently\")\n\n### Freshness Scoring\n\n| Criterion | Score |\n|---|---|\n| Updated within 3 months | Excellent — current and relevant |\n| Updated within 6 months | Good — still reasonably current |\n| Updated within 12 months | Acceptable — may need refresh |\n| Updated 12-24 months ago | Warning — review for accuracy |\n| No date or 24+ months old | Critical — AI platforms may deprioritize |\n\n### Evergreen Indicators\nSome content remains relevant regardless of age. Flag content as evergreen if:\n- It covers fundamental concepts that do not change (physics, basic math, legal definitions)\n- It is clearly labeled as a reference\u002Fguide for lasting concepts\n- It does not contain time-dependent claims (\"the latest\", \"currently\", \"in 2024\")\n\n---\n\n## Topical Authority Assessment\n\n### What It Is\nTopical authority measures whether a site comprehensively covers a topic rather than touching on it superficially. AI platforms prefer citing sites that are recognized authorities on their topics.\n\n### How to Assess\n1. **Content breadth**: Does the site have multiple pages covering different aspects of its core topic?\n2. **Content depth**: Do individual pages go deep into subtopics?\n3. **Topic clustering**: Are pages organized into logical groups with internal linking?\n4. **Content gaps**: Are there obvious subtopics that the site should cover but does not?\n5. **Competitor comparison**: Do competitors cover subtopics that this site misses?\n\n### Scoring\n\n| Level | Description | Score Impact |\n|---|---|---|\n| Authority | 20+ pages covering topic comprehensively, strong clustering | +10 bonus |\n| Developing | 10-20 pages with some clustering | +5 bonus |\n| Emerging | 5-10 pages on topic, limited clustering | +0 |\n| Thin | \u003C 5 pages, no clustering | -5 penalty |\n\n---\n\n## Overall Scoring (0-100)\n\n### Score Composition\n| Component | Weight | Max Points |\n|---|---|---|\n| Experience | 25% | 25 |\n| Expertise | 25% | 25 |\n| Authoritativeness | 25% | 25 |\n| Trustworthiness | 25% | 25 |\n| **Subtotal** | | **100** |\n| Topical Authority Modifier | | +10 to -5 |\n| **Final Score** | | **Capped at 100** |\n\n### Score Interpretation\n- **85-100**: Exceptional — strong AI citation candidate across platforms\n- **70-84**: Good — solid foundation, specific improvements will increase citability\n- **55-69**: Average — multiple E-E-A-T gaps reducing AI visibility\n- **40-54**: Below Average — significant content quality and trust issues\n- **0-39**: Poor — fundamental content strategy overhaul needed\n\n---\n\n## Output Format\n\nGenerate **GEO-CONTENT-ANALYSIS.md** with:\n\n```markdown\n# GEO Content Quality & E-E-A-T Analysis — [Domain]\nDate: [Date]\n\n## Content Score: XX\u002F100\n\n## E-E-A-T Breakdown\n| Dimension | Score | Key Finding |\n|---|---|---|\n| Experience | XX\u002F25 | [One-line summary] |\n| Expertise | XX\u002F25 | [One-line summary] |\n| Authoritativeness | XX\u002F25 | [One-line summary] |\n| Trustworthiness | XX\u002F25 | [One-line summary] |\n\n## Topical Authority Modifier: [+10 to -5]\n\n## Pages Analyzed\n| Page | Word Count | Readability | Heading Structure | Citability Rating |\n|---|---|---|---|---|\n| [URL] | [Count] | [Score] | [Pass\u002FWarn\u002FFail] | [High\u002FMedium\u002FLow] |\n\n## E-E-A-T Detailed Findings\n\n### Experience\n[Specific passages and pages with strong\u002Fweak experience signals]\n\n### Expertise\n[Author credentials found, technical depth assessment, specific gaps]\n\n### Authoritativeness\n[External validation found, topical authority assessment, gaps]\n\n### Trustworthiness\n[Trust signals present\u002Fmissing, accuracy concerns if any]\n\n## Content Quality Issues\n[Specific passages flagged with reasons and rewrite suggestions]\n\n## AI Content Concerns\n[Any low-quality AI content patterns detected, with specific examples]\n\n## Freshness Assessment\n| Page | Published | Last Updated | Status |\n|---|---|---|---|\n| [URL] | [Date] | [Date] | [Current\u002FStale\u002FNo Date] |\n\n## Citability Assessment\n### Most Citable Passages\n[Top 5 passages that AI platforms are most likely to cite, with reasons]\n\n### Least Citable Pages\n[Pages with lowest citability, with specific improvement recommendations]\n\n## Improvement Recommendations\n### Quick Wins\n[Specific content changes that can be made immediately]\n\n### Content Gaps\n[Topics the site should cover to strengthen topical authority]\n\n### Author\u002FE-E-A-T Improvements\n[Specific steps to strengthen E-E-A-T signals]\n```\n\n## When to Use\n\n- You need a Generative Engine Optimization task for a website: audit, citability, crawlers, schema, llms.txt, content, platform tuning, or client reporting.\n- Run read-only analysis first; propose site changes before making any.\n\n## Limitations\n\n- Audits are read-only analysis; never publish, deploy, or modify the target site without explicit approval.\n- Scores and citation likelihoods are heuristics, not guarantees from AI search platforms.\n- Docs-only import: upstream scripts, agents, hooks, and schema templates are not bundled.\n\n### Example\n\n```bash\ncurl -s https:\u002F\u002Fexample.com\u002Frobots.txt\ncurl -s https:\u002F\u002Fexample.com\u002Fllms.txt\n```\n\n> Adapted from [zubair-trabzada\u002Fgeo-seo-claude](https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude) (MIT); frontmatter, When to Use\u002FLimitations, and safety boundaries added for upstream compliance. Docs-only import: upstream runtime helpers not bundled.\n",{"name":5,"risk":47,"tags":53,"author":58,"source":59,"license":14,"version":60,"category":61,"date_added":62,"description":7,"source_repo":63,"source_type":39,"allowed-tools":64,"compatibility":65,"license_source":66},[30,54,35,55,56,57],"content-quality","citability","ai-content","topical-authority","geo-seo-claude","https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude","1.0.0","seo","2026-09-20","zubair-trabzada\u002Fgeo-seo-claude","Read, Grep, Glob, Bash, WebFetch, Write","Docs-only; upstream helper scripts and templates are not bundled. Site audits need network access to the target site; PDF reports need pandoc and headless Chrome.","https:\u002F\u002Fgithub.com\u002Fzubair-trabzada\u002Fgeo-seo-claude\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fgeo-content","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill geo-content",{"tool":78,"command":79},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill geo-content",{"tool":81,"command":82},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill geo-content","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fgeo-content\u002FSKILL.md",true,[],[87,110,132,156,182,206],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":96,"publishedAt":48},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[97,98,99,100,46,101,89,102,103,44,104,41,39,38,105,106,107,36,108,109],"ZeRO","trust","zero trust","architecture","verification","segmentation","devops-security","configure","active","critical","scope","relevant","implementing",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":48},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[117,118,119,120,121,122,123,124,45,125,126,43,127,41,128,39,129,130,106,131],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","model","node","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":48},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[139,140,141,47,142,143,144,145,146,147,148,149,150,39,38,151,152,153,154,155],"transcript","youtube transcript","youtube","github","codex","research","license","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":171,"publishedAt":48},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[162,165,168],{"categoryNo":163,"categoryName":164,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":166,"categoryName":167,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":169,"categoryName":170,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000030","开发工程师",[139,140,141,172,47,173,142,143,145,174,175,176,177,148,178,39,38,179,180,181],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":192,"publishedAt":48},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[188,191],{"categoryNo":189,"categoryName":190,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":166,"categoryName":167,"taxonomyType":20,"taxonomyTypeDesc":21},[141,193,194,121,47,195,196,197,198,145,176,199,200,201,202,38,203,151,204,205],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":48},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[212],{"categoryNo":163,"categoryName":164,"taxonomyType":20,"taxonomyTypeDesc":21},[214,141,215,216,47,173,174,217,218,175,176,177,148,219,178,39,38,179,220,154],"youtube full","full","google","server","dlp","credits","automatic"]