setup-llms-txt

Setup llms.txt Skill

Create and configure llms.txt and llms-full.txt for any website. These files help LLMs understand your site — think of them as robots.txt for AI models.

What is llms.txt?

llms.txt is a standard file (served at /llms.txt) that tells AI models:

• What your site/product does
• Where to find key resources (docs, API, guides)
• How to interact with your service

llms-full.txt is an expanded version with full content that LLMs can ingest without following links.

Spec: https://llmstxt.org

Workflow

Step 1: Analyze the Project

Examine the project structure to understand:

• What the site/product does
• Key pages and documentation
• API endpoints (if any)
• Framework being used

# Check framework
ls package.json next.config.* astro.config.* gatsby-config.* nuxt.config.* 2>/dev/null

# Find key content
find . -name "*.md" -o -name "*.mdx" | head -20
ls -la public/ static/ 2>/dev/null

# Check for existing llms.txt
curl -s "https://YOUR_SITE/llms.txt" | head -5

Step 2: Generate llms.txt

Create the file following the standard format:

# [Site/Product Name]

> [One-line description of what the site does]

## Docs
- [Getting Started](/docs/getting-started): How to get started with [Product]
- [API Reference](/docs/api): Full API documentation
- [Examples](/docs/examples): Code examples and tutorials

## API
- Base URL: https://api.example.com
- [Authentication](/docs/auth): How to authenticate API requests
- [Rate Limits](/docs/rate-limits): API rate limiting details

## Key Pages
- [Pricing](/pricing): Plans and pricing
- [Blog](/blog): Latest updates and articles
- [Changelog](/changelog): Product updates

## Contact
- Support: [email protected]
- Twitter: @example

Guidelines:

• Use Markdown format
• Start with # heading and > blockquote summary
• Group links by category with ## headings
• Use descriptive link text with brief explanations
• Include all important pages and resources
• Keep it concise — this is a summary, not full docs