geo-llmstxt

llms.txt Standard Analysis and Generation Skill

Purpose

This skill handles everything related to the llms.txt standard — an emerging convention (proposed by Jeremy Howard in September 2024) that lets a website give AI systems structured guidance about its content, structure, and key information. It is analogous to robots.txt (which tells crawlers what NOT to access) but instead tells AI systems what IS most useful to understand about the site.

The full format spec, the llms-full.txt variant, a fill-in template, and best practices live in references/spec.md — read it before validating or generating a file.

Why llms.txt Matters

AI models must work out which pages matter, what a site is about, and how content is organized — usually by crawling many pages and inferring structure. llms.txt solves this with an explicit, machine- and human-readable summary.

1. Faster AI comprehension: understand the site's purpose and structure from one file rather than dozens of pages.
2. Controlled narrative: you choose which pages and facts AI systems see first, shaping how they represent your brand.
3. Higher citation accuracy: AI systems that consult llms.txt cite the correct, authoritative page for each topic.
4. Reduced misrepresentation: key facts (pricing, features, locations) are stated explicitly, reducing hallucination.
5. Early-adopter advantage: only a small minority of sites have an llms.txt today, so it remains a differentiator.

---

Analysis Mode

When checking an existing llms.txt file.

Step 1: Fetch the File

1. Use WebFetch to retrieve [domain]/llms.txt. Also check [domain]/llms-full.txt.
2. Record HTTP status: 200 → validate; 404 → recommend generation; 403 → file blocked, flag as misconfiguration; 301/302 → follow and note the redirect.

Step 2: Validate Format

Check each structural element against the format rules in references/spec.md:

Element	Check	Severity if Missing
H1 Title	Present, matches business name	Critical
Blockquote description	Present, under 200 chars, factual	High
At least one H2 section	Present	Critical
Page entries with URLs	At least 5 entries present	High
URLs are absolute	All URLs use full https:// paths	High
URLs are valid	All URLs return 200 status	Medium
Descriptions present	Every entry has a description after the colon	Medium
Key Facts section	Present with business information	Medium
Contact section	Present with at least email	Low
Reasonable length	30-200 lines	Low
No broken Markdown	Proper formatting throughout	Medium