/llms.txt is present and structured
One of 40 checks the scanner runs. This one is worth 4 points inside the AI Context Files dimension, which carries 5% of the total score.
What does this check look at?
/llms.txt returns more than 20 bytes and contains an H1, a > summary line and at least 3 markdown links. Missing any of those is a partial pass.
How do I fix it?
- Partial pass: Follow the convention: one H1, a > summary line, then H2 sections of annotated links.
- Optional, and weighted low here for that reason - but cheap to add. See the llms.txt guide.
Why is it worth 4 points?
Points are relative weights inside a dimension, and a dimension's weight decides how much of the total it can move. The reasoning for this dimension's weight is published rather than asserted:
| Dimension | AI Context Files — 5% of the total score |
| Points for this check | 4 of 6 in this dimension |
| Worth at most | 3.3 of the 100 points |
Deliberately low. Most tools in this category weight llms.txt heavily and imply it is a ranking factor; the evidence does not support that, so neither does this score.
What else is measured in this dimension?
- A crawler policy is published — 1 point
- A markdown alternate is declared — 1 point
How do I see my own result?
Run a scan on your own domain. The report lists every failed check with the evidence that produced it, so you can tell a real failure from a check that does not apply.
Run a free GEO audit on your own site →
The full method, including the dimensions that are deliberately weighted low and the parts of the picture a single-URL scan cannot see, is on the methodology page.