Skip to content
SkillModel-led3,630 tokens in use

geo-llmstxt

Validates an existing llms.txt against the standard or generates a new one by crawling the site, with page descriptions, key facts and a contact section.

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

47tokens idle
3,630tokens 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
  • Examples12/15
  • Output15/15
  • 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-llmstxt covers the llms.txt convention that gives AI systems a short, structured summary of a website. In analysis mode it fetches llms.txt and llms-full.txt, validates the format element by element, scores completeness, accuracy and usefulness, and lists important pages that are missing.

In generation mode it discovers pages from the homepage and sitemap.xml, picks 10 to 30 of the most important ones, writes a factual description for each and assembles a file ready to upload to the site root.

What You Get

  • A ready-to-deploy llms.txt for the site root
  • GEO-LLMSTXT-ANALYSIS.md with a score and a pass or fail table for each format element
  • GEO-LLMSTXT-GENERATION.md explaining which pages were chosen and why
  • A list of important pages missing from an existing file
  • Suggested update frequency for the file

Common Use Cases

  • Create a first llms.txt for a SaaS, publisher or local business site
  • Audit an llms.txt that has broken or stale links
  • Write the longer llms-full.txt for deep AI analysis
  • Align llms.txt entries with what robots.txt lets AI crawlers read

What Makes It Unique

It carries concrete rules for good entries: 10 to 30 words each, absolute URLs, factual wording with no marketing terms, and examples of good and bad descriptions. The analysis score is weighted 40% completeness, 35% accuracy and 25% usefulness.

Under The Hood

A prose recipe with no scripts. The agent fetches the llms.txt file, the llms-full.txt file, the homepage, sitemap.xml and each selected page with WebFetch, checks that listed URLs respond with a success status, and writes the analysis or generation report plus the llms.txt text. It declares Read, Grep, Glob, Bash, WebFetch and Write tools. It does not upload the file anywhere; the owner deploys it.

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