squirrelscan Skills

Install

npx skills add squirrelscan/skills

This is third-party code. Review the repository files before installing.

What it does

The repository gives the agent two skills for the squirrel CLI. The first covers installing and configuring the tool, running audits, publishing reports and connecting MCP. The second drives a fix loop: the agent audits the site with LLM-friendly output, presents the score and top issues, finds the templates and components behind them, fixes them in batches after your approval and re-audits until the target is met. Checks cover SEO, performance, security, accessibility, content and API keys leaked into page code.

Who it is for. For web developers and SEO specialists who want the agent to find and fix site issues on its own.

Example request

Run an audit on example.com and show me the top 5 critical issues

Limitations

The skills require the squirrel CLI to be installed. Report publishing, the hosted MCP and some features need a squirrelscan account and use credits. Sites behind Cloudflare or Shopify may block the crawler without special headers.

How to disable. Uninstall the squirrelscan plugin via /plugin or delete the squirrelscan and audit-website folders from your agent's skills directory.

Security check

• Runs an external CLI that crawls the site over the network
• Edits project files based on audit findings

README in short

The README explains that squirrelscan crawls a site and checks pages against a large rule set across about twenty categories, returning a score and fixable issues. The repo has two skills plus a Claude Code plugin and marketplace and a Cursor plugin with a hosted MCP server. It covers installing via npx skills, /plugin, squirrel skills install or manually, and the MCP endpoint with OAuth or API key auth. MIT licensed.

SKILL.md

---
name: audit-website
description: Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, and re-auditing until the site scores well. Use to discover and assess website or webapp issues and drive them to fixed.
license: See LICENSE file in repository root
compatibility: Requires squirrel CLI installed and accessible in PATH
metadata:
  author: squirrelscan
  version: "2.1"
allowed-tools: Bash(squirrel:*) Read Edit Grep Glob
---

# Audit a Website and Fix It

Run a squirrelscan audit against a website, read the LLM report, map each issue to the code or content that causes it, fix in batches, and re-audit until the score target is met.

Requires the `squirrel` CLI ([squirrelscan.com/download](https://squirrelscan.com/download); verify with `squirrel --version`). For CLI setup, login, publishing, MCP, and general CLI usage, use the companion `squirrelscan` skill.

## Rule docs

Look up any rule at `https://docs.squirrelscan.com/rules/{rule_category}/{rule_id}`, for example:

https://docs.squirrelscan.com/rules/links/external-links

## Running the audit

```bash
squirrel audit https://example.com --format llm
```

- Use `--format llm`: it is compact, exhaustive, and made for agents.
- If the user doesn't provide a URL, ask which site to audit.
- Prefer auditing the live site: only there do you see true rendering, performance, and redirect behavior. If both a local dev server and a live site exist, suggest the live one; apply the fixes to the local code either way.
- Audits are cached locally. Re-render later without recrawling: `squirrel report <audit-id> --format llm`.

Related