LLMs.txt

View source

Movk Nuxt Docs uses the built-in nuxt-llms module to automatically generate /llms.txt and /llms-full.txt files, providing structured documentation content for AI tools such as Cursor, Windsurf, Claude, and ChatGPT, with support for custom domains, titles, and descriptions, and no manual maintenance required.

What is LLMs.txt?

nuxt-llms is integrated by default to preprocess documentation content for large language models. The system automatically generates and prerenders the /llms.txt and /llms-full.txt files.

See the /llms.txt file generated for the Movk Nuxt Docs documentation itself.

/llms.txt - a structured overview of all content with links to the documentation (about 5K tokens)
/llms-full.txt - the complete documentation, including implementation details, examples, type definitions, and best practices (100K+ tokens)

Default endpoints

The following are the default values used when generating the /llms.txt file:

domain: computed based on your deployment platform (or via the NUXT_SITE_URL environment variable)
title: extracted from your package.json file
description: extracted from your package.json file
full.title: extracted from your package.json file
full.description: extracted from your package.json file

Customizing LLMs.txt generation

You can customize how the LLMs.txt files are generated by configuring the llms option in nuxt.config.ts:

nuxt.config.ts

export default defineNuxtConfig({
  llms: {
    domain: 'https://your-site.com',
    title: 'Your Site Name',
    description: 'A brief description of your site',
    full: {
      title: 'Your Site Name',
      description: 'A brief description of your site',
    },
  },
})

Choosing the right file

Most users should start with /llms.txt - it contains all the essential information and works within standard LLM context windows. Only use /llms-full.txt when you need complete implementation examples and your AI tool supports large contexts (200K+ tokens).

Important usage notes

The @ symbol must be typed manually - when using tools such as Cursor or Windsurf, you must type the @ symbol manually in the chat interface. Copy-pasting breaks the tool's ability to recognize it as a context reference.

How to use it with AI tools

Cursor

You can reference LLMs.txt files in Cursor for better AI assistance.

How to use it

Direct reference: mention the LLMs.txt URL when asking a question
Use @docs to add these specific URLs to your project context

Learn more about Cursor web and documentation search

Windsurf

Windsurf can directly access LLMs.txt files to understand function usage and best practices.

Using LLMs.txt in Windsurf

Use @docs to reference specific LLMs.txt URLs
Create persistent rules in your workspace that reference these URLs

Learn more about Windsurf web and documentation search

Other AI tools

Any AI tool that supports LLMs.txt can use these endpoints to better understand your documentation.

Example for ChatGPT, Claude, or other LLMs

"Use the documentation at https://docs.mhaibaraai.cn/llms.txt"
"Follow the complete guide at https://docs.mhaibaraai.cn/llms-full.txt"

Agent Skills

Publish Agent Skills from your Movk Nuxt Docs site, following the Cloudflare Agent Skills Discovery RFC and deployed automatically via the /.well-known/skills/ endpoint. Users can install your skills into AI assistants such as Claude Code and Cursor with a single command.

Markdown Syntax

Master standard Markdown syntax for text formatting in Movk Nuxt Docs, including heading levels, bold/italic, ordered and unordered lists, inline code, hyperlinks, and images, to build clear, well-structured technical documentation.