Skip to content
SkillModel-led4,191 tokens in use

geo-report

Combines the results of the other GEO audits into one client-facing report with a GEO Readiness Score, crawler and brand tables, and a three-horizon action plan.

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

29tokens idle
4,191tokens 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
  • 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-report gathers the output of the platform, schema, technical and content audits (and optionally llms.txt and brand mention results), calculates a weighted GEO Readiness Score and writes GEO-CLIENT-REPORT.md for business owners and marketing leaders.

The template has twelve sections, from an executive summary and an AI visibility dashboard to crawler access, brand authority, citability, technical health, schema, llms.txt, a prioritised plan, competitor comparison and an appendix with methodology and glossary.

What You Get

  • GEO-CLIENT-REPORT.md of roughly 3,000 to 6,000 words
  • A composite score weighted 25% platform readiness, 25% content, 20% technical, 15% schema and 15% brand
  • Client-facing score labels from Needs Attention to Excellent
  • Tables for AI platform readiness, crawler access, brand presence, technical health and schema
  • A prioritised action plan with impact, effort and platforms affected, plus an estimated impact range

Common Use Cases

  • Deliver a finished audit to a non-technical client
  • Show a client how they compare with two competitors
  • Explain why server-side rendering matters in business terms
  • Collect findings from separate audit runs into one document

What Makes It Unique

It is written as a consultant’s deliverable. It sets the tone (direct, no hedging, business impact first), gives the exact section structure, and tells the agent to state assumptions and stay conservative with dollar estimates and never guarantee results.

Under The Hood

A prose recipe with no scripts. The agent reads the markdown outputs of the other geo skills from the working directory, or runs those audits first, may fetch pages with WebFetch to fill gaps, and writes GEO-CLIENT-REPORT.md. It declares Read, Grep, Glob, Bash, WebFetch and Write tools. Dollar and traffic estimates come from benchmark figures written into the skill and the agent’s own judgement, so they need review before the report goes out.

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