What does this skill do, and when should you use it?
This is one sub-skill of the geo-seo-claude repository (a 16-skill collection), located at skills/geo-content/SKILL.md, focused on content quality and E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness) evaluation. It builds on the premise that Google's December 2025 Quality Rater Guidelines update extends E-E-A-T to all competitive queries, and assesses whether content deserves to be cited by AI search platforms. The skill defines a 100-point scoring system (25 points per dimension) plus a -5 to +10 topical authority modifier, and checks word-count floors, readability (Flesch 60-70), paragraph/heading structure, internal linking, freshness, and low-quality AI content patterns. Output is a GEO-CONTENT-ANALYSIS.md report with per-dimension scores, page-level metrics, most-citable passages, and prioritized recommendations.
Fetches target pages (homepage, blog posts, service/product pages); evaluates E-E-A-T signals per dimension at 25 points each (first-person accounts, original data, author credentials, external citations, contact info, HTTPS, disclosures); assesses content quality metrics (minimum word counts per page type, sentence/paragraph length, passive voice, heading hierarchy); flags low-quality AI content patterns (generic phrasing, no original insight, filler); scores freshness by update recency (excellent within 3 months, critical at 24+ months); assesses topical authority (page count and clustering, -5 to +10 modifier); and generates GEO-CONTENT-ANALYSIS.md containing a 0-100 overall score, per-page citability ratings, most/least citable passages, and categorized recommendations (quick wins, content gaps, E-E-A-T improvements).
- A content marketer checking a blog post for E-E-A-T gaps (missing author bio, no original data) before publishing, to improve odds of AI citation
- An SEO consultant delivering an AI-search visibility audit to a client, using per-page citability ratings and passage analysis as deliverables
- A site owner identifying trust-signal gaps (no privacy policy, no contact info, undisclosed affiliate links) and fixing them via the quick-wins list
- A content team evaluating topical authority to find uncovered subtopics and plan a topic-cluster structure
- An editorial team auditing content freshness and prioritizing updates to high-value pages untouched for 12+ months
How do you install this skill?
- Many E-E-A-T signals (backlinks, Wikipedia presence, HTTPS validity, review authenticity) cannot be verified via static reads, so scores may be shallow and partially irreproducible.
- Cited Google guideline updates and market statistics lack sources; verify independently before relying on them.
- allowed-tools include Bash and Write; monitor execution scope and file writes in practice.
- No Chinese-language support or guidance for non-English sites; effectiveness for Chinese users is unknown.
- Publisher is unverified, with no changelog or maintenance commitment; long-term availability is uncertain.
- Shell / CLI
- Network access
- Local filesystem
WebFetch-capable client for fetching target pages
This skill ships inside the zubair-trabzada/geo-seo-claude collection. Recommended one-command install: curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/geo-seo-claude/main/install.sh | bash (use install-win.sh from Git Bash on Windows). Requires Python 3.8+, Claude Code CLI, and Git; dependencies go into an isolated venv at ~/.claude/skills/geo/.venv/. Alternatively, git clone the repo and run ./install.sh. Standalone manual installation of just this sub-skill is not documented; cloning the repo and referencing the skills/geo-content/ directory is the direct route.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/zubair-trabzada/geo-seo-claude.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/geo-content" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
After installation, run /geo content <url> in Claude Code to assess a site. Flow: fetch homepage and key pages → score four E-E-A-T dimensions (25 points each) → check content quality and AI content signals → assess topical authority → generate GEO-CONTENT-ANALYSIS.md. Score interpretation: 85-100 exceptional AI citation candidate; 55-69 average with multiple gaps; 0-39 needs a fundamental content strategy overhaul.
What are this skill's strengths and limitations?
- Fully transparent scoring: every E-E-A-T signal has explicit point values and scoring rules, making results reproducible and explainable
- Structured Markdown output with per-page word count, readability, heading structure, and citability ratings — suitable to hand directly to clients
- Aligned with the December 2025 Quality Rater Guidelines change extending E-E-A-T to all competitive queries; targets AI citation rather than traditional rankings
- Distinguishes low-quality AI content patterns from high-quality signals, consistent with Google's March 2024 stance on AI-generated content
- MIT licensed, free, and part of a 16-skill collection usable alongside /geo audit and other commands
- Many signals (inbound citations, media mentions, Wikipedia presence) require live web verification; scoring quality depends on the executing model's judgment with no automated test suite guaranteeing consistency
- Word-count and readability benchmarks are heuristic floors; the skill itself notes they are not direct ranking factors and efficacy is unverified by third parties
- Topical authority scoring relies on estimating whole-site coverage from fetched pages, which can under- or over-count
- The skill only analyzes and reports; it does not rewrite content — fixes require separate execution
- README marketing metrics ($850M market, +527% AI traffic growth, etc.) are cited without sources
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| GEO Content Quality & E-E-A-T Assessment this page | 47 · Use with care | ★ 11k | 20d ago | MIT |
| GEO Citability Scoring Skill | 48 · Use with care | ★ 11k | 20d ago | MIT |
| GEO Crawlers Access Analysis Skill | 51 · Use with care | ★ 11k | 20d ago | MIT |
| GEO Full-Site Audit | 48 · Use with care | ★ 11k | 20d ago | MIT |
| llms.txt Analysis & Generation Skill | 46 · Use with care | ★ 11k | 20d ago | MIT |
The source names no specific competitor products, so no comparison can be made. Its differentiation from generic SEO tooling — focus on AI citability over keyword rankings — is positional, not a named comparison.
How did FollowSkills review this skill?
Read-mostly assessment skill (Read/Grep/Glob/WebFetch/Write) with no destructive defaults, credential handling, or covert exfiltration; no red-line risk found. However allowed-tools include Bash and Write without least-privilege scoping, user confirmation, rollback guidance, or full data-flow disclosure; 13 deducted.
Scoring method (E-E-A-T 25 points each, tabulated signals) is internally consistent and the output template is explicit; but no test coverage for this skill's key paths (repo tests only cover fetch_page.py), no abnormal-input handling, and several required signals (inbound citations, Wikipedia presence) are not obtainable via Read/Grep, leaving executability questionable; 11 deducted.
Scenario and I/O are clear (content quality and AI citability), with concrete word-count and structure benchmarks; but no declared non-fit boundaries (private pages, non-HTML), no Chinese-language support, and no statement of assessment accuracy limits; 7 deducted.
Well-structured SKILL.md with version, frontmatter, tags, and progressive disclosure; MIT license is explicit; but no changelog, no known-limitations disclosure, and unclear maintenance responsibility or update path; 6 deducted.
The methodology is more structured than manual review and the output template is directly usable; but many signals (authoritative backlinks, media citations, HTTPS validity, verified reviews) exceed what static reads can verify, so scores risk being shallow heuristics with unproven marginal value over alternatives; 9 deducted.
Key factual claims (e.g., the December 2025 Google QRG update applying to all competitive queries) carry no citations, market statistics are unsourced, and there is no test or third-party execution evidence for this skill path — only author-authored methodology; 7 deducted.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →