Question 1

What is llms.txt?

Accepted Answer

A proposed standard: a Markdown file at /llms.txt that gives AI engines a curated map of your site — one H1 title, a blockquote summary, then H2 sections listing your key URLs with short descriptions. This validator checks that structure: exactly one H1 first, a "> summary" after it, well-formed "- [name](url)" entries with absolute http(s) links.

Question 2

Do AI engines actually fetch llms.txt today?

Accepted Answer

Honestly: adoption is early and entirely voluntary. Some AI dev tools and crawlers read it, but the major engines have not committed to it, and Google has said it does not use the file. Treat a clean llms.txt as cheap, zero-risk hygiene — a clear signal of your canonical pages — not as something that will move citations by itself.

Question 3

What does the "## Optional" section mean?

Accepted Answer

Per the spec, links under an "## Optional" heading may be skipped by a model working under a tight context budget. That contract only works if the section comes last — which is why this validator warns when something follows it.

Question 4

What is the difference between llms.txt and llms-full.txt?

Accepted Answer

llms.txt is the short index: title, summary, and links. llms-full.txt is the optional companion with the full text of your key pages inlined, for tools that want the content without crawling. Validate the index here; keep the depth in the -full file.

Question 5

How is the grade calculated?

Accepted Answer

Errors dominate: 1–2 errors is a D, 3 or more is an F, because a structurally broken file can be misread by parsers. With zero errors, warnings erode the grade — one warning is a B, two or three a C, four or more a D. A clean file is an A. Info findings never affect the grade.

Validate your
llms.txt

Your llms.txt

Report

What the linter checks

llms.txt validation questions.

A valid file is the floor