Skip to content
SkillModel-led8,296 tokens in use

ai-seo

Gets a site cited and recommended in ChatGPT, Perplexity and Google AI Overviews, with an audit of bot access, citations and content structure.

61,709 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/ai-seo
npx skills add coreyhaines31/marketingskills --skill ai-seo
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ai-seo costs

86tokens idle
8,296tokens in use
37,801tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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

shelldetected

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
  • Output15/15
  • Size11/15
  • Resources15/15

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 →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

ai-seo covers answer engine optimization, generative engine optimization and agent-readable sites. It audits how AI answers your key queries, which competitors get cited, whether content is extractable and whether AI bots can reach the site.

The optimization strategy rests on three pillars: structure, authority and presence. It also covers machine-readable files, schema for AI, monitoring tools and a do-it-yourself monitoring routine.

What You Get

  • An AI visibility audit of key queries and citation patterns
  • A content extractability check and an AI bot access check
  • Guidance on robots rules that allow agents, with named exceptions for opt-outs
  • Content patterns and types that get cited most
  • A monitoring plan with tracked metrics and tool options

Common Use Cases

  • Finding out why an AI answer cites a competitor
  • Checking whether robots rules and HTML block AI agents
  • Restructuring pages so answers can be extracted and quoted
  • Deciding whether llms.txt or a page format is worth the effort

What Makes It Unique

It separates citations from recommendations and gives platform-specific ranking factors, plus references on LinkedIn and YouTube citations, multilingual and commerce cases and answer accuracy. It discloses its own ties: monitoring tools built by the repository’s maintainer or partners are labeled as such.

Under The Hood

The SKILL.md loads first and pulls in reference files by task. The skill ships no scripts. It names a command-line scoring tool launched with npx for checking agent readiness, plus free web checkers and a monitoring tool table; running any of them is up to you, and tool integrations need your own accounts.

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