Eeat

Skill josezuma/ai-visibility-geo-toolkit/.claude/skills/eeat

EEAT scoring (Experience, Expertise, Authoritativeness, Trustworthiness) 0-100. Extracts author, credentials, publish date, references, schema from any URL.From its SKILL.md

Install

npx -y skills add josezuma/ai-visibility-geo-toolkit --skill eeat

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.9 KB, 713 tokens by cl100k_base, as published. Nobody here has run it

EEAT Analysis

Scores any URL for Google's EEAT signals (Experience, Expertise, Authoritativeness, Trustworthiness). Critical for understanding why your content may or may not be cited by AI search engines.

Quick Start

# Using the CLI
ai-visibility-geo-toolkit audit-eeat https://example.com

# Using the script directly
python3 scripts/eeat.py https://example.com

# JSON output
python3 scripts/eeat.py https://example.com --json

Agent Instructions (manual mode)

When the installed script isn't available, perform these checks using your own tools:

1. Experience: Named Author (25 pts max)

Fetch the URL
Check for <meta name="author" content="..."> in the HTML head
If no meta tag, check the visible text for "by FirstName LastName" pattern
Score: 25 pts for meta tag, 20 pts for visible byline, 0 if no author

2. Expertise: Author Credentials (20 pts max)

If an author was found: search for their LinkedIn, Twitter/X, GitHub profiles in the page
Check for "bio", "about the author", "credentials" sections
Score: 20 pts if both social profiles AND bio present, 15 pts for social only, 10 pts for bio only

3. Authoritativeness: Publish Date (20 pts max)

Check for "datePublished" in JSON-LD schema blocks
Check for <meta name="date" content="..."> or <meta name="article:published_time">
Check visible text for "Published January 15, 2026" patterns
Score: 20 pts for schema date, 20 pts for meta date, 15 pts for visible date

4. Authoritativeness: External References (20 pts max)

Extract all href links from the page
Filter out same-domain and social/media links
Count unique external domains cited
Score: 20 pts for 10+ references, 15 for 5+, 10 for 3+, 5 for 1-2

5. Trustworthiness: Schema.org (15 pts max)

Extract all application/ld+json blocks
List the @type values found (Article, Organization, Person, FAQPage, etc.)
Score: 15 pts for 3+ types, 8 pts for 1-2 types

Output Format

Return results as a formatted markdown report:

## EEAT Analysis: https://example.com
**Score: 72/100 — Good**

| Signal | Score | Status |
|--------|:-----:|--------|
| Named Author | 25/25 | ✅ Jose Zuma |
| Credentials | 15/20 | ✅ LinkedIn + Twitter |
| Publish Date | 20/20 | ✅ 2026-01-15 |
| External Refs | 12/20 | ⚠️ 4 unique refs |
| Schema.org | 15/15 | ✅ 4 types |

Recommendations

Add author credentials section with bio and expertise description
Add 3+ more external references to authoritative sources
Consider linking to more research papers or industry reports

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.