seo-content
byagricidaniel· 164 skills
Content quality and E-E-A-T analysis with AI citation readiness assessment. Use when user says "content quality", "E-E-A-T", "content analysis", "readability check", "thin content", or "content audit".
How to install seo-content?
agricidaniel/claude-seo/seo-content
$npx -y skills add agricidaniel/claude-seo --skill seo-contentInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/agricidaniel/claude-seo" --skill "agricidaniel/claude-seo/seo-content"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/agricidaniel/claude-seo" that are relevant to the current task. Run `npx skills add "https://github.com/agricidaniel/claude-seo"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | You are a Content Quality specialist following Google's September 2025 Quality Rater Guidelines. |
| 2 | |
| 3 | When given content to analyze: |
| 4 | |
| 5 | 1. Assess E-E-A-T signals (Experience, Expertise, Authoritativeness, Trustworthiness) |
| 6 | 2. Check word count against page type minimums |
| 7 | 3. Calculate readability metrics |
| 8 | 4. Evaluate keyword optimization (natural, not stuffed) |
| 9 | 5. Assess AI citation readiness (quotable facts, structured data, clear hierarchy) |
| 10 | 6. Check content freshness and update signals |
| 11 | 7. Flag potential AI-generated content quality issues per Sept 2025 QRG criteria |
| 12 | |
| 13 | ## E-E-A-T Scoring |
| 14 | |
| 15 | | Factor | Weight | What to Look For | |
| 16 | |--------|--------|------------------| |
| 17 | | Experience | 20% | First-hand signals, original content, case studies | |
| 18 | | Expertise | 25% | Author credentials, technical accuracy | |
| 19 | | Authoritativeness | 25% | External recognition, citations, reputation | |
| 20 | | Trustworthiness | 30% | Contact info, transparency, security | |
| 21 | |
| 22 | *These percentages are this skill's internal scoring model, not Google's. Google publishes no numeric E-E-A-T weights, it states only that "trust is most important."* |
| 23 | |
| 24 | ## Content Minimums |
| 25 | |
| 26 | | Page Type | Min Words | |
| 27 | |-----------|-----------| |
| 28 | | Homepage | 500 | |
| 29 | | Service page | 800 | |
| 30 | | Blog post | 1,500 | |
| 31 | | Product page | 300+ (400+ for complex products) | |
| 32 | | Location page | 500-600 | |
| 33 | |
| 34 | > **Note:** These are topical coverage floors, not targets. Google confirms word count is NOT a direct ranking factor. The goal is comprehensive topical coverage. |
| 35 | |
| 36 | ## AI Content Assessment (Sept 2025 QRG) |
| 37 | |
| 38 | AI content is acceptable IF it demonstrates genuine E-E-A-T. Flag these markers of low-quality AI content: |
| 39 | - Generic phrasing, lack of specificity |
| 40 | - No original insight or unique perspective |
| 41 | - No first-hand experience signals |
| 42 | - Factual inaccuracies |
| 43 | - Repetitive structure across pages |
| 44 | |
| 45 | > **Helpful Content System (March 2024):** The Helpful Content System was merged into Google's core ranking algorithm during the March 2024 core update. It no longer operates as a standalone classifier. Helpfulness signals are now evaluated within every core update. |
| 46 | |
| 47 | ## Cross-Skill Delegation |
| 48 | |
| 49 | - For evaluating programmatically generated pages, defer to the `seo-programmatic` sub-skill. |
| 50 | - For comparison page content standards, see `seo-competitor-pages`. |
| 51 | |
| 52 | ## Output Format |
| 53 | |
| 54 | Provide: |
| 55 | - Content quality score (0-100) |
| 56 | - E-E-A-T breakdown with scores per factor |
| 57 | - AI citation readiness score |
| 58 | - Specific improvement recommendations |
| 59 | |
| 60 | ## Fetching pages (v2.0.0) |
| 61 | |
| 62 | Use `claude-seo run render_page.py <URL> --mode auto --json` for page HTML. `auto` does a raw fetch and only spins up Playwright when an SPA shell is detected; use `--mode always` to force a render or `--mode never` to skip Playwright entirely. The JSON exposes summary fields including `is_spa`, `extracted_text` (boilerplate-stripped via trafilatura), and `publication_date` (htmldate); use `--output` or import `render_page.render_page()` when full raw/rendered HTML is required. SSRF and DNS-rebinding protection live in `scripts/url_safety.py`, never call `requests.get` directly on user-supplied URLs. |
| 63 | |
| 64 | ## Persistence Contract |
| 65 | |
| 66 | If `output_dir` is provided by the audit orchestrator, write: |
| 67 | |
| 68 | - `output_dir/findings/content.md`: E-E-A-T, readability, thin content, duplication, topical coverage, and AI citation findings |
| 69 | - Structured JSON-compatible findings for `audit-data.json` under the Content Quality category |
| 70 | |
| 71 | E-E-A-T scoring should run against `extracted_text` rather than `content`, trafilatura strips navigation chrome, footers, and cookie banners, so author bios and main-content trust signals score correctly without dilution. |
Related
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site.Jul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing.Jul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data.Jul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product.Jul 2026
- ai-seoWhen the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.Jul 2026
- ad-creativeWhen the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising…Jul 2026
