Skip to content
SkillModel-led2,668 tokens in use

geo-compare

Compares a baseline GEO audit with the latest one and writes a monthly progress report with score deltas, crawler changes and action item status.

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

89tokens idle
2,668tokens 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

shelldeclaredwrites 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
  • Structure25/25
  • Examples15/15
  • 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-compare turns two saved GEO audits into a client-facing progress report. Give it a domain and it finds the oldest and newest audit files, extracts the overall score, six category scores, five platform scores and the status of 14 AI crawlers, and calculates the change in each.

The report shows green, red or neutral trend markers, progress on quick-win, medium-term and strategic actions, this month’s wins, new issues and next month’s focus.

What You Get

  • A monthly report file named by domain and month
  • Before and after tables for the overall score, categories and platforms
  • AI crawler access changes between the two audits
  • Action plan progress grouped by quick wins, medium-term and strategic items
  • A six-month trajectory and a next-month priority list

Common Use Cases

  • Send a client a monthly proof-of-progress report
  • Check whether a robots.txt change opened the AI crawlers
  • Compare two specific audit files by path
  • Prepare a quarterly review from saved audits

What Makes It Unique

It is built around the retention loop of a GEO agency: baseline, work, re-audit, delta. It accepts a domain, two explicit file paths or a month name, and falls back to a fresh quick audit when only one saved audit exists.

Under The Hood

A prose recipe with no scripts. The agent lists audit files under the ~/.geo-prospects/audits folder in the home directory, sorts them by date, reads the oldest and newest, pulls out score lines such as GEO Score and per-crawler Allowed or Blocked markers, and writes the report to ~/.geo-prospects/reports. When exact scores are missing it is told to estimate them from the written findings. It declares Read, Write, Bash and Glob tools and makes no web requests itself.

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