docs.stripe.com — llms.txt & GEO score

Stripe Documentation

10 of 11 checks pass. What is left: no duplicate links.

• Enough links carry a description 417 of 453 described (92%) — for a map-shaped file the bar is 60%, not every line
  10/10
• Descriptions say something concrete Average 71 characters across 417 described links
  7/7
• Descriptions add to the title No description merely repeats its title
  4/4
• Points at clean markdown copies 452 of 453 end in .md or .txt (100%, detected by file extension)
  10/10
• Link titles are descriptive 7 weak titles (bare URLs, “here”, one-word labels)
  4/4
• A workable number of links 453 links, nearly all pointing at machine-readable copies — an exhaustive map rather than a short guide, which is a legitimate shape for a documentation site
  4/4
• Skippable links marked Optional An ## Optional section is present
  3/3
• No duplicate links 5 duplicate URLs — wasted context
  1/2
• List items are markdown links 5 of 458 list items are plain text, not links
  4/4
• Grouped so the map stays navigable Median heading group holds 7 links across 38 groups (15 sub-headings)
  3/3
• Links are absolute URLs All 453 links are absolute URLs
  1/1

5 of 7 checks pass. What is left: summary directly under the title and summary is a usable length.

• Exactly one H1 project title “Stripe Documentation”
  3/3
• Summary directly under the title An opening paragraph is there, but not as a "> " blockquote — clients that look for the quoted summary will miss it
  2/3
• Summary is a usable length 410 characters (from the opening paragraph) — too long
  2/3
• Concrete language, not marketing filler No marketing filler detected
  3/3
• Grouped into balanced sections 26 H2 sections and 15 sub-headings, largest group holds 40 of 453 links
  4/4
• Conforms to the published grammar Markdown only, headings used as the spec defines them
  2/2
• Section names say what is inside 1 of 26 headings are generic
  2/2

All 5 checks pass in this group.

• At the root of the domain you typed Found at the standard /llms.txt path
  2/2
• Sent as plain text Content-Type: text/markdown; charset=utf-8
  1/1
• robots.txt exists 174 B of crawler rules
  1/1
• AI crawlers are not blocked No AI user-agent is disallowed at the root
  6/6
• robots.txt points at a sitemap A Sitemap: line is declared
  1/1

The homepage did not answer our request, so these checks were not scored — a failed measurement is not a failing site.

1 of 5 checks pass. What is left: publishes llms-full.txt, the index points at the full file, server reports when it last changed and the index is kept current.

• Publishes llms-full.txt No llms-full.txt alongside the index
  0/3
• The index points at the full file No llms-full.txt exists to link to
  0/1
• Index is a sensible size 90 KB
  2/2
• Server reports when it last changed No Last-Modified header — clients cannot tell when this changed
  0/1
• The index is kept current Cannot be confirmed — the server sends no Last-Modified header
  0/2

• Publishes llms-full.txt Depth & upkeep +3

  Right now: No llms-full.txt alongside the index

  Generate an llms-full.txt that inlines every linked page. Community convention rather than spec, but assistants with a large context window take the whole thing in one request.

  Where: Your docs build, output at /llms-full.txt

  1. Concatenate the markdown of every page listed in llms.txt into one file.
  2. Keep the heading structure: a client uses those headings to navigate a multi-megabyte file.
  3. Regenerate it in the same build step that publishes the docs, so it cannot drift.
  4. Note that llms-full.txt is a community convention, not part of the proposal — useful, but optional.
• The index is kept current Depth & upkeep +2

  Right now: Cannot be confirmed — the server sends no Last-Modified header

  Regenerate llms.txt when the docs change. A year-old index quietly points models at pages that have moved.

  Where: Your build pipeline

  1. Regenerate llms.txt in the same step that publishes content, so it cannot go stale silently.
  2. Treat it as a build artifact, not a hand-edited file — hand-edited indexes drift within a quarter.
  3. An llms.txt with discontinued products is worse than none: a model will repeat the wrong facts confidently.
• No duplicate links Content & links +1

  Right now: 5 duplicate URLs — wasted context

  Remove repeated URLs. Every duplicate costs context the model could have spent elsewhere.

  Where: The link lists in llms.txt

  1. Remove repeated URLs, including the same page listed under two sections.
  2. Every duplicate costs context the model could have spent on a page it has not seen.
• Server reports when it last changed Depth & upkeep +1

  Right now: No Last-Modified header — clients cannot tell when this changed

  Let the server send Last-Modified on llms.txt. Without it a client has to re-download the whole file to notice a change.

  Where: Your web server configuration

  1. Serve llms.txt as a real file on disk so the server can derive Last-Modified from its mtime.
  2. If it is generated by an application route, set the header yourself from the generation time.
  3. Without it a client has to re-download the whole file to notice a change, and cannot answer "is this current?".

  Instead of

  HTTP/1.1 200 OK\nContent-Type: text/plain

  Do this

  HTTP/1.1 200 OK\nContent-Type: text/plain\nLast-Modified: Wed, 10 Sep 2026 08:14:00 GMT

• Summary directly under the title Structure +1

  Right now: An opening paragraph is there, but not as a "> " blockquote — clients that look for the quoted summary will miss it

  Put the opening line in a > blockquote. The spec calls it optional, but it is the first thing a model reads and often the only thing it quotes back.

  Where: The line directly under the H1

  1. Add a single line starting with "> ".
  2. Answer three things in it: what you do, for whom, and what makes it specific.
  3. This is the sentence a model is most likely to quote back, so write it last, after the rest of the file.

  Instead of

  > We are an innovative company delivering world-class solutions.

  Do this

  > Industrial spare parts for food processing lines, shipped across Europe with same-week dispatch.

• Summary is a usable length Structure +1

  Right now: 410 characters (from the opening paragraph) — too long

  Aim for 80–350 characters: one or two sentences that make sense read aloud on their own.

  Where: The "> " line in llms.txt

  1. Aim for 80–350 characters: one or two sentences that stand on their own when read aloud.
  2. Under 80 and it says nothing specific; over 350 and a model summarises your summary.
  3. Cut adjectives first — they are the part that carries no information.
• The index points at the full file Depth & upkeep +1

  Right now: No llms-full.txt exists to link to

  Mention llms-full.txt inside llms.txt. Guessing the filename works often enough to be tempting and not often enough to rely on.

  Where: Inside llms.txt

  1. Mention the full file in llms.txt itself, as a link or a line of context.
  2. Guessing the filename works often enough to be tempting and not often enough to rely on.

  Do this

  Full inlined text: https://acme.example/llms-full.txt

This score is Devsly’s own heuristic, not an official standard — llms.txt has no scoring body. It measures how well a file serves an AI assistant, and it does not predict whether any assistant will cite the site. The reading is a snapshot from 19 September 2026; run it again for the current state, or check a different site.