---
name: agentready-audit
description: Audit a public website for AI-agent discovery, readability, operability, and safety using AgentReady.
---

# AgentReady Audit

Use this skill when a user asks whether a public website is ready for browser agents, coding agents, or agent-driven search.

## Workflow

1. Confirm the exact public URL with the user or infer it from the current task.
2. Send `POST https://www.agentready.me/api/scan` with `Content-Type: application/json` and `{ "url": "https://example.com", "includePlaywright": true }`.
3. Report the overall score and each phase score separately.
4. Prioritize concrete fixes that improve both human accessibility and agent reliability.
5. Treat the scan as best-effort diagnostics, not certification or a security guarantee.

## Safety

- Scan only public URLs unless the user explicitly authorizes private access.
- Do not sign in, connect a repository, submit a form, or start payment without explicit user authorization.
- Never expose tokens, credentials, private repository content, or personal information.

## Canonical references

- Methodology: https://www.agentready.me/methodology
- OpenAPI: https://www.agentready.me/openapi.json
- Agent instructions: https://www.agentready.me/agents.md