Skip to content
SkillModel-led3,680 tokens in use

geo-content

Scores a site's content on Experience, Expertise, Authoritativeness and Trustworthiness, plus readability, freshness and topical authority, for AI citation.

11,792 stars on the repository MIT Licensezubair-trabzada/geo-seo-claude · skills/geo-content
curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/geo-seo-claude/main/install.sh | bash
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing geo-content costs

32tokens idle
3,680tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclarednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity32
  • Momentum40

geo-content evaluates whether content deserves to be cited by AI platforms. It scores the four E-E-A-T dimensions at 25 points each, then looks at word count, readability, paragraph and heading structure, internal linking, content freshness and topical authority.

It also flags signs of low-quality AI-generated content and writes GEO-CONTENT-ANALYSIS.md with findings, citable passages, content gaps and author improvements.

What You Get

  • GEO-CONTENT-ANALYSIS.md with a content score out of 100
  • An E-E-A-T breakdown with detailed findings for each of the four dimensions
  • A list of content quality issues and AI content concerns
  • A freshness assessment and the most and least citable pages
  • Quick wins, content gaps and author or E-E-A-T improvements

Common Use Cases

  • Check whether author bios and credentials are strong enough to earn trust
  • Find thin or stale pages that weaken a site
  • Review AI-assisted drafts for the signs of low-quality output
  • Plan topic clusters to build authority

What Makes It Unique

It treats AI-generated content by its quality signals and does not penalise how it was produced, and lists the marks of low quality separately from the marks of strong content. A topical authority modifier from +10 to -5 adjusts the final score for how well a site covers its subject.

Under The Hood

A prose recipe with no scripts. The agent fetches pages with WebFetch, reads them against the rubric for experience, expertise, authority and trust, checks dates, author information and linking, and writes GEO-CONTENT-ANALYSIS.md to the working directory. It declares Read, Grep, Glob, Bash, WebFetch and Write tools.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers