Skip to content
SkillModel-led58 tokens in use

geo-optimizer

Audits, rewrites and measures how a site appears in AI answers from ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews, without fabricated citations.

4,282 stars on the repository MIT Licensenowork-studio/notfair-plugin · skills/geo-optimizer
/plugin marketplace add nowork-studio/notfair-plugin /plugin install notfair@nowork-studio
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing geo-optimizer costs

85tokens idle
58tokens 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

Nothing detected: no shell, network, file writes, git or credentials in its files.

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 →
Needs attention
  • Frontmatter8/15
  • Structure7/25
  • Examples0/15
  • Output0/15
  • Size13/15
  • 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 activity96
  • Maintenance52
  • Community64
  • Maturity28
  • Momentum40

geo-optimizer is a generative engine optimization workflow for AI agents with four modes: audit a page, optimize its content, build a 30, 60 and 90 day strategy, or measure AI visibility against a baseline of buyer questions.

An audit scores four pillars: evidence density, structure and position, authority signals, and AI crawlability. Veto checks cap the score, and fabricated citations, statistics or expert names block delivery entirely. Measurement is read-only and every count must trace to a sampled answer or a named report.

What You Get

  • A GEO audit with pillar breakdown, ranked fixes and any vetoes triggered
  • A rewritten page with front-loaded answers, extraction-friendly structure and JSON-LD
  • A 30, 60 and 90 day playbook with engine-specific moves
  • A reusable buyer-question set and run log for measuring AI visibility
  • A pre-publish checklist for sources, author identity and crawler access

Common Use Cases

  • Checking whether AI search crawlers can reach a page
  • Rewriting a page so an answer appears in the first 150 words
  • Comparing what AI engines say about a brand with first-party facts
  • Analyzing supplied Bing AI Performance or Search Console Generative AI reports

What Makes It Unique

Its central rule is no fabrication: every statistic needs a verifiable source and every quote a named person, and it declines to predict numerical lift from a rewrite. Audit results can be pass, partial, fail, unverified or not applicable, and the overall score is omitted when required checks are unverified. It separates crawler evidence (raw HTML, robots rules, CDN or WAF) and treats intentional blocks as policy choices.

Under The Hood

The skill is a short wrapper whose SKILL.md tells the agent to read a longer WORKFLOW.md in the seo folder of the same repository and follow it. The workflow is prose and points to a packaged references file; it ships no scripts. It has the agent fetch public pages and check crawler and robots behavior for a live URL, and read supplied reports. Measurement is read-only. It never pushes changes to a site without an explicit yes, hands approved WordPress changes to the WordPress workflow, and treats fetched pages as untrusted data.

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