leblebicioglu.org — llms.txt & GEO score

Hakan Leblebicioğlu — llms.txt

Nothing in this group is in place yet.

• Every link carries a description No links in the file, so there is nothing to describe
  0/10
• Descriptions say something concrete No links to measure
  0/7
• Descriptions add to the title No descriptions to compare against their titles
  0/4
• Points at clean markdown copies No links to point anywhere
  0/10
• Link titles are descriptive No link titles to judge
  0/4
• A workable number of links No links at all
  0/4
• Skippable links marked Optional Nothing is marked as skippable
  0/3
• No duplicate links No URLs to compare
  0/2
• List items are markdown links 46 of 46 list items are plain text, not links
  0/4
• Enough written detail per link No links to measure against
  0/3
• Links are absolute URLs No links to check
  0/1

3 of 7 checks pass. What is left: exactly one H1 project title, summary directly under the title, summary is a usable length and grouped into balanced sections.

• Exactly one H1 project title 5 H1 headings — the spec allows exactly one
  2/3
• Summary directly under the title No summary under the title
  0/3
• Summary is a usable length No summary to measure
  0/3
• Concrete language, not marketing filler No marketing filler detected
  3/3
• Grouped into balanced sections 14 H2 sections
  2/4
• Conforms to the published grammar Markdown only, headings used as the spec defines them
  2/2
• Section names say what is inside All 14 headings are descriptive
  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/plain
  1/1
• robots.txt exists 1.6 KB 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

5 of 6 checks pass. What is left: title is not padded or repetitive.

• Homepage title is the right length 61 characters, from title — will be cut off
  2/2
• Title is not padded or repetitive “hakan” appears twice — brand padding that spends visible characters
  0/1
• Homepage has a meta description 191 characters, from meta description — Google will truncate it
  2/2
• Canonical URL declared https://leblebicioglu.org/
  1/1
• Language declared lang="tr"
  1/1
• Social card image og:image is set
  1/1

2 of 5 checks pass. What is left: publishes llms-full.txt, the index points at the full file 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 3.3 KB
  2/2
• Server reports when it last changed Server sends Last-Modified
  1/1
• The index is kept current 175 days old
  1/2

• A workable number of links Content & links +4

  Right now: No links at all

  Either curate to roughly 10–40 links, or go the other way and map everything to .md copies. The costly middle is a long list of HTML links with no descriptions.

  Where: The link lists in llms.txt

  1. Aim for roughly 10–40 curated links.
  2. Above about fifty, a model has to read the whole file before it can choose, and every entry gets diluted.
  3. If you generated the file from a sitemap, delete most of it: curation is the entire value of the format.
  4. Below ten, add the pages you would send a new customer to first.
• List items are markdown links Content & links +4

  Right now: 46 of 46 list items are plain text, not links

  A file list needs `- [Title](url): description`. A plain line gives a model something to read but nowhere to go — it cannot follow it, quote it, or check it.

  Where: Every "- " line in llms.txt

  1. Turn each plain line into a markdown link: "- [Title](https://your-site/page.md): description".
  2. A line without a URL gives a model something to read but nowhere to go — it cannot follow, quote or verify it.
  3. If a fact has no page behind it (an address, a phone number), put it in the free-text body above the sections, not in a file list.
  4. Note that "#" is a heading in markdown, not a comment — lines starting with # become H1/H2 headings.

  In your file

  line 9

  - Name: Prof. Dr. Hakan Leblebicioğlu

  - [Name]({https://your-site/path}.md): {what this page covers}

  line 10

  - Title: Infectious Diseases and Clinical Microbiology Specialist

  - [Title]({https://your-site/path}.md): {what this page covers}

  line 11

  - Credential: ESCMID Fellow

  - [Credential]({https://your-site/path}.md): {what this page covers}

  Placeholders in { } are yours to write — we do not invent text about your pages.

• 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.
• Skippable links marked Optional Content & links +3

  Right now: Nothing is marked as skippable

  Move the nice-to-haves under ## Optional so a model on a tight budget knows what to drop first.

  Where: A new "## Optional" section at the end of llms.txt

  1. Move the nice-to-have links — history, press, careers — under "## Optional".
  2. By convention a client may skip that whole section when context is tight.
  3. This is you deciding what gets dropped first, instead of the model guessing.

  Do this

  ## Optional
  
  - [Company history](https://acme.example/about.md): Background, not needed to answer product questions

• Summary directly under the title Structure +3

  Right now: No summary under the title

  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 +3

  Right now: No summary to measure

  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.
• Grouped into balanced sections Structure +2

  Right now: 14 H2 sections

  Group links under headings a reader would look for, and spread them — one group holding most of the file is the same as no grouping.

  Where: The "## " headings in llms.txt

  1. Split the link list into at least five "## " groups by what a reader would be looking for.
  2. Typical split: Docs, API, Guides, Product, Company, Optional.
  3. Grouping is what lets a model skip nine tenths of the file and still find the right page.

  Instead of

  ## Links
  
  - [A](...)
  - [B](...)
  - [C](...)

  Do this

  ## Docs
  
  - [A](...)
  
  ## API
  
  - [B](...)
  
  ## Optional
  
  - [C](...)

• Exactly one H1 project title Structure +1

  Right now: 5 H1 headings — the spec allows exactly one

  Start the file with one `# Your project name` line — the only element the proposal requires.

  Where: The first line of llms.txt

  1. Make the very first line "# Your project name" — one H1, nothing above it.
  2. If you have a second H1 further down, demote it to "## " or remove it.
  3. Use the product name people search for, not a slogan.

  Instead of

  Welcome!
  # Acme
  # Acme Parts

  Do this

  # Acme Parts

• The index is kept current Depth & upkeep +1

  Right now: 175 days old

  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.
• 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

• Title is not padded or repetitive Search-engine basics +1

  Right now: “hakan” appears twice — brand padding that spends visible characters

  Say the brand once. Use the freed characters to describe what the product does.

  Where: The <title> tag on your homepage

  1. Say the brand once. The repeated word this check found is spending visible characters for nothing.
  2. Use the freed characters to describe what the product does.

  Instead of

  <title>Hurdacı — İstanbul Hurdacı | Hurdacı</title>

  Do this

  <title>Scrap metal collection in Istanbul — same-day payment</title>

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 21 September 2026; run it again for the current state, or check a different site.