Skip to content
SkillModel-led2,824 tokens in use

geo-audit

Runs a full Generative Engine Optimization audit of a site with five parallel subagents and a weighted 0-100 GEO Score plus a 30-day action plan.

11,792 stars on the repository MIT Licensezubair-trabzada/geo-seo-claude · skills/geo-audit
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-audit costs

61tokens idle
2,824tokens 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 →
Excellent
  • Frontmatter8/15
  • Structure22/25
  • Examples12/15
  • Output15/15
  • 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-audit orchestrates a complete GEO and SEO audit. It fetches the homepage, classifies the business type, delegates analysis to five subagents (AI visibility, platform optimization, technical infrastructure, content E-E-A-T and schema), and merges their category scores into one GEO Score.

The result is written to GEO-AUDIT-REPORT.md with issues grouped by severity, quick wins for the week and a four-week plan.

What You Get

  • GEO-AUDIT-REPORT.md with an executive summary and a score breakdown across six categories
  • Issues sorted into critical, high, medium and low with suggested time frames
  • A list of quick wins to implement this week
  • A four-week action plan with a theme per week
  • An appendix of the pages analysed and any fetches that failed

Common Use Cases

  • Deliver a first audit to a new GEO client
  • Benchmark your own site before and after a content push
  • Compare how a SaaS site and a local business site need different fixes
  • Find out which of the six categories drags the overall score down

What Makes It Unique

It states its formula: citability 25%, brand authority 20%, content E-E-A-T 20%, technical GEO 15%, schema 10% and platform optimization 10%, with named score bands from Critical to Excellent. It also changes its checks by business type, so a local business is judged on LocalBusiness schema while an e-commerce site is judged on Product schema and reviews.

Under The Hood

This is a prose recipe for the model, with no scripts of its own. It tells the agent to fetch pages with WebFetch, read sitemap.xml and robots.txt, hand work to five subagents defined elsewhere in the repository, and write GEO-AUDIT-REPORT.md to the working directory. It declares Read, Grep, Glob, Bash, WebFetch and Write tools. Its quality gates limit the crawl to 50 pages, 30 seconds per page and one second between requests, skip non-HTML content and respect robots.txt.

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