What the llms.txt generator checks

Your site, described the way AI reads it.

From sitemap to finished file in one pass, with the format the llms.txt standard expects.

/sitemap.xml1,204 URLs
<urlset>
<loc>
200
<loc>
404
<lastmod>2026-09-01

Sitemap discovery

0 pts

Reads the Sitemap: lines in robots.txt, then standard locations, then sitemap indexes. Falls back to homepage links when a site has no sitemap.

Internal linksdepth ≤ 3
orphan

Smart page selection

0 pts

Picks up to 40 pages: the homepage first, then shallow paths, spread across sections so a blog does not crowd out pricing and docs.

H1
H2
?
H2
?

Titles and descriptions

0 pts

Visits each page and uses its title and meta description, falling back to the first real paragraph when the description is missing.

/llms.txtFound
#
>
##
-[
]
-[
]

Standard format

0 pts

An H1 with the site name, a blockquote summary, and Markdown link lists under H2 sections, exactly as the llms.txt proposal specifies.

output
CopyDownload
# Acme
> Acme makes widgets for teams.
## Docs
- [Getting started](/docs/start): Install in 5 min
- [API](/docs/api): Endpoints and auth

Copy or download

0 pts

Get the file as text to paste, or as a download named llms.txt ready to drop in your site root.

File health1 error
  • Disallow: / under User-agent: *
  • No Sitemap: line
  • Crawl-delay ignored by Googlebot
line 12

Existing file check

0 pts

Tells you if the site already serves an llms.txt so you can compare before replacing it.

Why it matters

One file. Every AI assistant knows what you do.

AI assistants cannot read your whole site every time someone asks about you. llms.txt gives them the short version: what the site is, and which pages answer which questions.

01

It is the robots.txt of the AI era

robots.txt tells crawlers where they may go. llms.txt tells language models what is worth reading and how to describe you. It is a proposed standard already read by a growing list of tools.

Standard format
02

Descriptions do the work

A model uses the description next to each link to decide which page to open. Clear, specific descriptions get your pricing page cited for pricing questions and your docs cited for how-to questions.

Titles and descriptionsSmart page selection
03

It takes five minutes, once

The file is plain text at your domain root. Generate it, publish it, regenerate when your site changes. There is no ongoing cost and no downside.

Copy or downloadExisting file check
How to improve

Publish it. Then make it better.

  1. 1

    Upload the file to your site root

    It must be served at yourdomain.com/llms.txt as plain text. On most hosts that means dropping it into the public folder next to robots.txt.

  2. 2

    Improve the summary

    The blockquote is the first thing a model reads. Make it one or two sentences that say what you do and for whom, in plain words.

  3. 3

    Tighten the descriptions

    Edit any description that is vague. "Pricing for Starter and Growth plans, billed monthly or yearly" beats "Pricing".

  4. 4

    Add pages the sitemap missed

    If a key page was skipped or is not in your sitemap, add a line for it by hand under the right section.

  5. 5

    Consider llms-full.txt

    For documentation-heavy sites, publish a second file with the full text of your key pages so tools can load everything in one request.

Score after fixes
41 → 93
F
D
C
B
A
robots.txt
llms.txt
FAQPage

Keep llms.txt and your content in sync, automatically

SiteLift publishes AI-ready articles with structured data and keeps your llms.txt current as your site grows, then distributes the content so AI assistants find it.

No credit card required

Frequently Asked Questions

Everything you need to know about the llms.txt generator.

llms.txt is a proposed standard for a Markdown file at your domain root that tells large language models what your site is about and links to the pages worth reading, each with a short description. It complements robots.txt and sitemap.xml.