- Home
- Skills
- Agents & Orchestration
- agent-ready-cli
More screenshots
Works with the AI Agents you already use
Agent Ready Cli
Audit any website for AI agent-readability and protocol compliance using the Agent Ready CLI.
Free
agent-ready-cli
Example session with this skill installed
Run a scan on https://example.com/docs and show me why it's failing the llms.txt checks.
- Read your context and instructions
- Compiled the agent-ready-cli
Scan V1StGXR8_Z complete.
Score: 64/100 (Fair)
llms.txt: 2/10 (Missing)
Failing Checks
- L1 (Missing llms.txt): No llms.txt file found at root.
- S4 (High Latency): Resource took >2s to respond.
How to fix: Host a markdown summary at /llms.txt to improve discovery.
Connects securely to your tools. The creator never sees your data.
About this skill
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.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
- Requires Node.js 20.10 or higher.
- Requires a Pro API key for scanning.
- Only audits public URLs: cannot reach localhost or private networks.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
8 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 months ago
- Free with an Agensi account
- Software
- Agent Ready MCPagent-ready-scanner
Node.js