www.akkahotels.com — llms.txt & GEO score

67 /100 C · 67 of 100 points

Published once, then left alone

www.akkahotels.com publishes a curated llms.txt — 13 links across 10 sections, 6 KB in all.

Every link carries a description, which is more than most files manage.

The clearest gap is points at clean markdown copies. Right now: 0 of 13 end in .md or .txt (0%, detected by file extension). Closing it is worth 10 points.

Workable, but an assistant is still guessing in places. Scanned 21 September 2026 against 34 checks — 23 passed, 1 partial, 10 missing.

www.akkahotels.com GEO score card: 67 out of 100, with the score broken down across content, structure, discovery, search-engine basics and depth. — www.akkahotels.com scored **67/100** on 21 September 2026. Source file: https://www.akkahotels.com/llms.txt.

67/100geo score

13links

10sections

6 KBsize

What it does well

Every link carries a description 13 of 13 described (100%)
Descriptions add to the title No description merely repeats its title
A workable number of links 13 links (12–50 is the sweet spot)
Grouped into balanced sections 10 H2 sections and 13 sub-headings, largest group holds 4 of 13 links

What is missing

Points at clean markdown copies +10 0 of 13 end in .md or .txt (0%, detected by file extension)
Link titles are descriptive +4 8 weak titles (bare URLs, “here”, one-word labels)
List items are markdown links +4 36 of 49 list items are plain text, not links
Descriptions say something concrete +3 Average 37 characters across 13 described links

Among the 22 sites measured here so far, www.akkahotels.com ranks 15th, against a median of 71. That comparison moves as new sites are scanned — it is a snapshot of this list, not of the web.

What www.akkahotels.com tells an assistant

AKKA Hotels

AKKA Hotels is a premium hotel chain operating in Antalya and Istanbul, offering unforgettable accommodation experiences with family-friendly vacation experiences, luxury comfort and superior service quality. | AKKA Hotels, Antalya ve İstanbul'da faaliyet gösteren premium otel zinciridir. | AKKA Hotels ist eine Premium-Hotelkette in Antalya und Istanbul. | AKKA Hotels - премиум сеть отелей в Анталии и Стамбуле.

Content & links

Can a model pick the right page, first time?

28/52

6 of 11 checks pass. What is left: descriptions say something concrete, points at clean markdown copies, link titles are descriptive, skippable links marked Optional and list items are markdown links.

Every link carries a description 13 of 13 described (100%)
10/10
Descriptions say something concrete Average 37 characters across 13 described links
4/7
Descriptions add to the title No description merely repeats its title
4/4
Points at clean markdown copies 0 of 13 end in .md or .txt (0%, detected by file extension)
0/10
Link titles are descriptive 8 weak titles (bare URLs, “here”, one-word labels)
0/4
A workable number of links 13 links (12–50 is the sweet spot)
4/4
Skippable links marked Optional Nothing is marked as skippable
0/3
No duplicate links All 13 URLs are distinct
2/2
List items are markdown links 36 of 49 list items are plain text, not links
0/4
Enough written detail per link 60 words per link across 780 words
3/3
Links are absolute URLs All 13 links are absolute URLs
1/1

Structure

Does it follow the llms.txt shape?

20/20

All 7 checks pass in this group.

Exactly one H1 project title “AKKA Hotels”
3/3
Summary directly under the title Present as a blockquote
3/3
Summary is a usable length 414 characters — too long
3/3
Concrete language, not marketing filler No marketing filler detected
3/3
Grouped into balanced sections 10 H2 sections and 13 sub-headings, largest group holds 4 of 13 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 All 10 headings are descriptive
2/2

Discovery & access

Can an assistant reach it, and is it allowed to?

11/11

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 122 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

Search-engine basics

What a crawler reads from your homepage today

5/8

3 of 6 checks pass. What is left: title is not padded or repetitive, language declared and social card image.

Homepage title is the right length 55 characters, from title
2/2
Title is not padded or repetitive “hotels” appears twice — brand padding that spends visible characters
0/1
Homepage has a meta description 161 characters, from meta description — Google will truncate it
2/2
Canonical URL declared https://www.akkahotels.com/en
1/1
Language declared No lang attribute on <html>
0/1
Social card image No og:image — shares render as a bare link
0/1

Depth & upkeep

Is there more than the index, and is it current?

3/9

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 6 KB
2/2
Server reports when it last changed Server sends Last-Modified
1/1
The index is kept current 445 days old
0/2

What www.akkahotels.com should fix next

Ordered by what each one is worth. Open a row for the steps.

+33 pts

Right now: 0 of 13 end in .md or .txt (0%, detected by file extension)

Publish a .md version of each page and link to that. The single biggest win here: the model reads your content instead of your navigation and footer.

Where: Your CMS or docs build — this is the biggest single win here

Publish a .md version of each page you link to, at a predictable URL (page.md next to page).
Point the llms.txt links at the .md copies, not at the HTML pages.
Strip navigation, cookie banners and footers from the markdown — that is the whole point: the model reads your content instead of your chrome.
Declare the pair in your HTML with a link relation so clients can find it without guessing.

In your file

line 10

- [Turkish](https://www.akkahotels.com/tr) | [English](https://www.akkahotels.com/en) | [German](https://www.akkahotels.com/de) | [Russian](https://www.akkahotels.com/ru)

- [Turkish](https://www.akkahotels.com/tr.md) | [English](https://www.akkahotels.com/en.md) | [German](https://www.akkahotels.com/de.md) | [Russian](https://www.akkahotels.com/ru.md)

line 15

- [Turkish](https://www.akkahotels.com/antedon/tr) | [English](https://www.akkahotels.com/antedon/en) | [German](https://www.akkahotels.com/antedon/de) | [Russian](https://www.akkahotels.com/antedon/ru)

- [Turkish](https://www.akkahotels.com/antedon/tr.md) | [English](https://www.akkahotels.com/antedon/en.md) | [German](https://www.akkahotels.com/antedon/de.md) | [Russian](https://www.akkahotels.com/antedon/ru.md)

line 19

- [Turkish](https://www.akkahotels.com/alinda/tr) | [English](https://www.akkahotels.com/alinda/en) | [German](https://www.akkahotels.com/alinda/de) | [Russian](https://www.akkahotels.com/alinda/ru)

- [Turkish](https://www.akkahotels.com/alinda/tr.md) | [English](https://www.akkahotels.com/alinda/en.md) | [German](https://www.akkahotels.com/alinda/de.md) | [Russian](https://www.akkahotels.com/alinda/ru.md)

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

Right now: 8 weak titles (bare URLs, “here”, one-word labels)

Replace bare URLs and “click here” with the page’s real name — the title is half the signal.

Where: The "[Title]" part of each link

Replace bare URLs, "here", "click here" and one-word labels with the page’s real name.
The title is half the signal — a model reads it before it reads your description.

In your file

line 10

- [Turkish](https://www.akkahotels.com/tr) | [English](https://www.akkahotels.com/en) | [German](https://www.akkahotels.com/de) | [Russian](https://www.akkahotels.com/ru)

- [{the page’s real name}](https://www.akkahotels.com/tr) | [English](https://www.akkahotels.com/en) | [German](https://www.akkahotels.com/de) | [Russian](https://www.akkahotels.com/ru)

line 15

- [Turkish](https://www.akkahotels.com/antedon/tr) | [English](https://www.akkahotels.com/antedon/en) | [German](https://www.akkahotels.com/antedon/de) | [Russian](https://www.akkahotels.com/antedon/ru)

- [{the page’s real name}](https://www.akkahotels.com/antedon/tr) | [English](https://www.akkahotels.com/antedon/en) | [German](https://www.akkahotels.com/antedon/de) | [Russian](https://www.akkahotels.com/antedon/ru)

line 19

- [Turkish](https://www.akkahotels.com/alinda/tr) | [English](https://www.akkahotels.com/alinda/en) | [German](https://www.akkahotels.com/alinda/de) | [Russian](https://www.akkahotels.com/alinda/ru)

- [{the page’s real name}](https://www.akkahotels.com/alinda/tr) | [English](https://www.akkahotels.com/alinda/en) | [German](https://www.akkahotels.com/alinda/de) | [Russian](https://www.akkahotels.com/alinda/ru)

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

Right now: 36 of 49 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 16
- 5-star family hotel with panoramic sea view in Kemer

- [5-star family hotel with panoramic sea view in Kemer]({https://your-site/path}.md): {what this page covers}

line 20
- 5-star holiday resort by the sea, close to ancient cities

- [5-star holiday resort by the sea, close to ancient cities]({https://your-site/path}.md): {what this page covers}

line 24
- 4-star hotel designed for families with children in nature

- [4-star hotel designed for families with children in nature]({https://your-site/path}.md): {what this page covers}

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

Right now: Average 37 characters across 13 described links

Write 60+ characters that add information the title does not: numbers, limits, formats, names.

Where: The text after ": " on each link

Write 60 characters or more, and make them add information the title does not.
Cover every link: this is measured per LINK, not per description, so an undescribed line counts as zero.
Name the concrete things on the page: numbers, limits, formats, model names.
If the description could be pasted under any other link, it is not a description yet.

In your file

line 10

- [Turkish](https://www.akkahotels.com/tr) | [English](https://www.akkahotels.com/en) | [German](https://www.akkahotels.com/de) | [Russian](https://www.akkahotels.com/ru)

- [Turkish](https: {what is on the page — numbers, limits, formats}

line 15

- [Turkish](https://www.akkahotels.com/antedon/tr) | [English](https://www.akkahotels.com/antedon/en) | [German](https://www.akkahotels.com/antedon/de) | [Russian](https://www.akkahotels.com/antedon/ru)

- [Turkish](https: {what is on the page — numbers, limits, formats}

line 19

- [Turkish](https://www.akkahotels.com/alinda/tr) | [English](https://www.akkahotels.com/alinda/en) | [German](https://www.akkahotels.com/alinda/de) | [Russian](https://www.akkahotels.com/alinda/ru)

- [Turkish](https: {what is on the page — numbers, limits, formats}

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

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.
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
Right now: 445 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.
Right now: No lang attribute on <html>

Set <html lang="…">. It tells screen readers how to pronounce the page and models which language to expect.

Where: The <html> tag
1. Set lang to the page’s actual language: <html lang="tr"> or <html lang="en">.
2. It tells screen readers how to pronounce the page and models which language to expect.
Instead of
<html>

Do this
<html lang="tr">
Right now: No og:image — shares render as a bare link

Add an og:image. One tag, and it is the difference between a link and a card wherever you are shared.

Where: The <head> of your homepage
1. Add an og:image pointing at a 1200×630 PNG or JPG, with an absolute URL.
2. Add og:title and og:description alongside it so the card is not assembled from guesses.
3. Without it, every share of your link renders as bare text.
Do this
<meta property="og:image" content="https://acme.example/og.png"> <meta property="og:image:width" content="1200"> <meta property="og:image:height" content="630">
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
Right now: “hotels” 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.