Skip to content
SkillModel-led2,725 tokens in use

geo

The entry point of the GEO-SEO toolkit: one /geo command that routes to audits, citability, crawler, schema, report and client-pipeline sub-skills.

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

139tokens idle
2,725tokens 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

shelldeclared and detectednetworkdeclared and detectedwrites 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
  • Frontmatter12/15
  • Structure23/25
  • Examples15/15
  • Output12/15
  • Size11/15
  • 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
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 203

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 is the orchestrator skill of the GEO-SEO Claude toolkit. It answers /geo commands such as audit, quick, citability, crawlers, llmstxt, brands, platforms, schema, technical, content, report and report-pdf, and sends each one to a specialised sub-skill.

A full audit fetches the homepage, detects the business type (SaaS, local service, e-commerce, publisher, agency), launches five parallel subagents and combines their findings into one GEO Score from 0 to 100 with a prioritised action plan.

What You Get

  • A single /geo command set covering audit, page, quick, citability, crawlers, llmstxt, brands, platforms, schema, technical, content, report and report-pdf
  • A composite GEO Score from 0 to 100 built from six weighted categories
  • One named output file per command, such as GEO-AUDIT-REPORT.md or GEO-CITABILITY-SCORE.md
  • Business-type detection that changes the recommendations for SaaS, local, e-commerce, publisher and agency sites
  • A pandoc and headless Chrome route to a styled GEO-REPORT.pdf

Common Use Cases

  • Run a full AI search audit on a client website and hand over a prioritised action plan
  • Take a 60-second GEO snapshot of a competitor before a pitch
  • Check whether AI crawlers can reach a site and which pages are quotable
  • Turn an audit markdown file into a branded PDF for a client

What Makes It Unique

Most SEO skills cover one task. This one is a router over fourteen sub-skills and five subagents, with fixed scoring weights (citability 25%, brand authority 20%, content 20%, technical 15%, schema 10%, platforms 10%) and quality gates on crawl size, timeouts and request pacing. It also reaches past audits into prospecting, proposals and monthly progress reports for agencies.

Under The Hood

The SKILL.md is a routing table and an orchestration recipe. It tells the agent to fetch pages with curl or WebFetch, read sitemap.xml, check robots.txt, delegate to five subagent files in the repository’s agents folder, and write report files (markdown, llms.txt, PDF) into the current directory. Prospect, proposal and comparison commands write into a ~/.geo-prospects folder in the home directory. The PDF route runs pandoc and a headless Google Chrome from the shell. It declares Read, Grep, Glob, Bash, WebFetch and Write tools. Quality gates cap an audit at 50 pages, 30 seconds per fetch and one second between requests.

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