Agent Ready Cli

What it does

The Agent Ready CLI skill gives your AI agent a powerful command-line interface to audit any public website for AI-readability. It scans URLs against the Vercel Agent Readability Spec, llmstxt.org standards, and various agent-protocol manifests like MCP server cards and agents.json. The tool runs ~60 automated checks to determine how well an AI agent can navigate, understand, and interact with a site's content.

Why use this skill

Instead of manually prompting an AI to "look at this site" and hoping for the best, this skill provide a structured, engineering-grade audit. It solves the "black box" problem of AI discovery by providing a concrete score (0-100), rating bands, and high-impact remediation steps. Unlike simple web scraping, it specifically looks for agent-only manifests and protocol files that standard scrapers miss.

Supported tools

• Frameworks: Supports Vercel Agent Spec, llmstxt.org, MCP (Model Context Protocol), and A2A.
• Technical Stack: Zero-dependency wrapper for the Agent Ready REST API; requires Node.js ≥ 20.10.
• Output: Ships with both human-readable terminal summaries and machine-readable JSON for automated piping and scripting.

Output format

The skill produces a detailed summary including an overall score, rating band (Excellent to Needs Improvement), sub-scores for llms.txt compliance, and a prioritized list of failing checks with specific "How to Fix" instructions.