- Home
- Skills
- Agents & Orchestration
- agent-ready-api
More screenshots
Works with the AI Agents you already use
Agent Ready Api
Score and optimize any website for AI agent-readability using the Agent Ready REST API.
Free
agent-ready-api
Example session with this skill installed
Run an Agent Ready scan on https://docs.example.com to see if it follows the llms.txt standard and Vercel spec.
- Read your context and instructions
- Compiled the agent-ready-api
Scan complete for docs.example.com.
Score: 82/100 (Rating: Good)
- llms.txt: Found, but missing 'optional' section (Check L4 failed).
- Vercel Spec: Pass (95/100).
- Issue: Missing agent-permissions.json (Check C2).
Full Report: https://agent-ready.dev/share/scan_01HXYZ...
Connects securely to your tools. The creator never sees your data.
About this skill
Optimize Your Site for AI Agents
The Agent Ready skill allows developers to programmatically audit any public URL for "AI readiness." As the web shifts from human-centric to agent-centric browsing, this skill ensures your documentation and site structure are easily parsable by LLMs and autonomous agents.
What it does
- Comprehensive Auditing: Scans sites against 60+ benchmarks, including the Vercel Agent Readability Spec and llmstxt.org standards.
- Protocol Validation: Checks for modern agent manifests like MCP server cards, agents.json, A2A, and NLWeb.
- Technical Scoring: Provides automated scores (0-100) and categorical ratings (Excellent to Needs Improvement).
- Remediation Guidance: Returns specific failure reasons and "how-to-fix" instructions for every failing check.
Why use this skill?
Prompting an AI to "look at my site" often results in surface-level feedback based on visual layout. This skill uses a specialized REST API to perform a deep structural crawl, looking for the specific invisible files and metadata that actual production agents (like Claude Code or GPT-4o) depend on. It provides a repeatable, data-driven score that you can track over time or integrate into CI/CD pipelines.
The Output
You receive a structured summary featuring an overall score, sub-scores for specific specifications (like llms.txt), a list of the highest-impact failing checks, and a shareable URL for a detailed visual dashboard.
- Requires a paid Pro account for most scans
- Scan time usually takes 15 to 60 seconds
- Limited to public URLs only
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 any payment.
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
5 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 5 months ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts