🦞 MoltProbe

Methodology

Every check is scored pass, warn or fail. Pass earns full weight, warn earns half, fail earns zero. The weighted total is normalized to a 0 to 100 score, then graded: A is 90 and up, B is 75, C is 60, D is 40, F below that. Here is every check and what it is worth.

Agent files

llms.txt present and valid12The file agents read first: a markdown map of your key content.
Agent skill file (skill.md)8Tells an agent what your site does and how to use it.
MCP manifest6Lets agents call your service as a tool.
llms-full.txt present5The full-text version of your key content for LLMs.
ai.txt / ai-plugin2Optional, legacy AI usage manifest.

Crawler access

AI crawlers allowed14Whether robots.txt lets GPTBot, ClaudeBot, PerplexityBot and OAI-SearchBot in. The heaviest single check: if they are blocked, nothing else matters.

Structured data

Structured data (JSON-LD)10schema.org data that tells a machine what a page is about.
Meta description5A short summary of the page.
OpenGraph tags4So shares unfurl and some agents parse the page.
Page title4A clear, descriptive title.

Content & discovery

Content in initial HTML10Real text present before JavaScript runs, since many agents do not run it.
XML sitemap6A sitemap at the root or declared in robots.txt.
Machine-readable feed3Optional RSS or Atom feed.
AboutHow it worksProbe a site