GEOKit

llms.txt Validator

Paste your llms.txt content to check if it follows the spec — H1 title, valid markdown, link format, and more.

🔍 llms.txt Syntax & Validation FAQ

Ensure your AI roadmap file is perfectly structured for LLM parsers and crawler ingestion.

1. What are the key rules for a valid llms.txt?

A valid llms.txt file must begin with exactly one H1 header (e.g., # Project Name), followed immediately by a blockquote summary (e.g., > A brief description). All subheadings must use H2 (##) format, and links should follow the standard list link pattern.

2. Why are HTML tags and code blocks discouraged in llms.txt?

The llms.txt file is designed to be a high-density, low-token directory index. Adding complex HTML tags, inline scripts, or markdown code blocks adds unnecessary token overhead and parsing noise for LLM crawlers. Keep it to pure, clean markdown.

3. Why is there a 50KB size warning?

AI agents ingest this file into their active context window to map out your site's resources. If the index exceeds 50KB, it consumes valuable tokens that the model could use for processing actual page content. If you have extensive links, split them into multiple sub-sections or use a full-text llms-full.txt.

4. How often should I re-validate?

You should validate your file whenever you update your website architecture, add new API documentation, or change key landing page URLs. Validating ensures no broken absolute URLs or malformed markdown syntax slips into your live configuration.

Share this tool

Found this tool useful? Help others by linking to it from your blog or resources page.