---
title: "llms.txt generator | SEO Skill"
description: "Generate an llms.txt draft from useful crawled pages, then review the selected links and wording against the saved crawl before publishing the file."
canonical: "https://seoskill.dev/docs/reports/generate-llms-txt"
language: "en"
---

# llms.txt generator

Create a reviewable llms.txt draft from a saved crawl and an explicit page selection. You still decide what belongs in the file (the generator does not know your publishing priorities).

## Install and generate the file

Install the CLI once, then run `seo start` to connect your site and Google data. After setup you can run this generator yourself or ask your agent to run it.

Install the SEO CLI globally.

```
npm i -g seo
```

Run setup after installation.

```
seo start
```

Create an optional llms.txt draft from a saved crawl.

```
seo llms generate --project example
```

## What the generator creates

Generate an llms.txt draft from useful crawled pages, then review the selected links and wording against the saved crawl before publishing the file.

Best for

The optional format is a deliberate publishing choice.

Needs

Saved or fresh crawl report

You get

Generate an llms.txt draft from useful crawled pages, then review the selected links and wording against the saved crawl before publishing the file.

Use next

Audit an llms.txt file

Every report follows the same rules for missing data and outside estimates.[See how report data works](https://seoskill.dev/docs/reports#how-report-data-works).

## What you need before you run it

The report uses the information below. Optional sources are only used when you ask for them.

### Saved or fresh crawl report

Supplies page URLs, titles, descriptions, and crawl exclusions.

### Selection limits and exclusions

Control the maximum URLs, token budget, and paths that should stay out of the draft.

## Use a different report for these jobs

These jobs need a different report or a manual review.

[

### You want to draft a small file from links you choose yourself.

Use the browser generator to create, copy, or download a small draft without installing anything. It does not crawl the pages or choose links for you.

Free llms.txt generator

](https://seoskill.dev/tools/llms-txt-generator)[

### You need to check a published llms.txt file and the pages it links to.

Run the llms.txt audit after publishing. It fetches the live file, parses its entries, checks linked destinations, and compares them with limited crawl candidates.

llms.txt audit

](https://seoskill.dev/docs/reports/llms-txt-audit)

### You need to decide whether the site should publish llms.txt at all.

No automated report can make that product decision because the format is optional and does not guarantee crawling, citations, or rankings. Review who will maintain the file and whether the intended agent audience benefits from a curated page list; this generator can show the likely draft before you commit.

Needs more evidence

## Use the generator with an agent or in code

The command above is enough for most work. These options let an agent, script or application run the same generator with explicit input and structured output.

### CLI

Use the report catalog when an agent, script or CI job needs predictable JSON instead of the normal terminal output. Check the current input first, then run the generator with the validated parameters.

Check the current input before the agent or script runs the generator.

```
seo reports describe generate-llms-txt --json
```

Once the input is valid, run the generator through the report catalog.

```
seo reports run generate-llms-txt --params '{"reportId":"crawl_example_20260710","maxUrls":50,"tokenBudget":4000,"exclude":["/account/*","/search"]}' --json
```

### MCP

An MCP agent follows the same two-step flow. It inspects the current schema, fills the required fields and only then runs the generator.

Ask the MCP server for the current generator input.

```
{
  "id": "generate-llms-txt"
}
```

Run the generator after the agent has checked and filled the input.

```
{
  "id": "generate-llms-txt",
  "params": {
    "reportId": "crawl_example_20260710",
    "maxUrls": 50,
    "tokenBudget": 4000,
    "exclude": [
      "/account/*",
      "/search"
    ]
  }
}
```

### TypeScript

Install the package in a Node 22 project when your application needs to run the generator directly. The result includes the same evidence, warnings and limits returned through the CLI and MCP server.

Add the SEO package to your project.

```
npm install seo
```

Run the generator from your TypeScript application.

```
import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'generate-llms-txt',
  {
  "reportId": "crawl_example_20260710",
  "maxUrls": 50,
  "tokenBudget": 4000,
  "exclude": [
    "/account/*",
    "/search"
  ]
},
)

console.log(result)
```

## What to do next

Review every selected URL and description before publishing the draft. Keep only stable pages you are comfortable recommending, then audit the live file after it is available.

1.  01Validate the draft against the live site.
2.  02Re-audit after publishing or changing important URLs.

## Related reports

[

Check whether llms.txt can be fetched and parsed, whether its links work and how well it covers useful pages before you publish or update it.

llms.txt audit

](https://seoskill.dev/docs/reports/llms-txt-audit)[

Check whether crawlers can access and use important pages in AI search. Find technical blockers without inventing a visibility or citation score.

AI search readiness audit

](https://seoskill.dev/docs/reports/ai-readiness)

## Sources used by this generator

These primary sources define the provider data or search controls used by the result.

-   [Google guidance for AI features and websites](https://developers.google.com/search/docs/appearance/ai-features)