geo-llmstxt covers the llms.txt convention that gives AI systems a short, structured summary of a website. In analysis mode it fetches llms.txt and llms-full.txt, validates the format element by element, scores completeness, accuracy and usefulness, and lists important pages that are missing.
In generation mode it discovers pages from the homepage and sitemap.xml, picks 10 to 30 of the most important ones, writes a factual description for each and assembles a file ready to upload to the site root.
What You Get
- A ready-to-deploy llms.txt for the site root
- GEO-LLMSTXT-ANALYSIS.md with a score and a pass or fail table for each format element
- GEO-LLMSTXT-GENERATION.md explaining which pages were chosen and why
- A list of important pages missing from an existing file
- Suggested update frequency for the file
Common Use Cases
- Create a first llms.txt for a SaaS, publisher or local business site
- Audit an llms.txt that has broken or stale links
- Write the longer llms-full.txt for deep AI analysis
- Align llms.txt entries with what robots.txt lets AI crawlers read
What Makes It Unique
It carries concrete rules for good entries: 10 to 30 words each, absolute URLs, factual wording with no marketing terms, and examples of good and bad descriptions. The analysis score is weighted 40% completeness, 35% accuracy and 25% usefulness.
Under The Hood
A prose recipe with no scripts. The agent fetches the llms.txt file, the llms-full.txt file, the homepage, sitemap.xml and each selected page with WebFetch, checks that listed URLs respond with a success status, and writes the analysis or generation report plus the llms.txt text. It declares Read, Grep, Glob, Bash, WebFetch and Write tools. It does not upload the file anywhere; the owner deploys it.