squirrelscan Skills
squirrelscan Skills & Plugins
Skills and MCP for website audits with squirrelscan: SEO, performance, security, accessibility and a code fix loop
- 104 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs an external CLI that crawls the site over the network
- Edits project files based on audit findings
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/squirrelscan-skills-pluginsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs an external CLI that crawls the site over the network
- Edits project files based on audit findings
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.
Good fit when
- You need a technical audit before launching a site
- You need to find broken links and leaked keys on pages
- After a deploy you want to diff the report against the previous one
- You want site checks in CI
Not a fit when
- You need traffic and ranking analytics rather than a technical audit
- You cannot install a third-party CLI or use an external service
Example request
Run an audit on example.com and show me the top 5 critical issuesLimitations
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.
FAQ
Can I use it without MCP?
Yes, the skills call the CLI directly. MCP is optional, with a hosted server or a local one via squirrel mcp.
Can I install just one skill?
Yes: npx skills add squirrelscan/skills --skill audit-website.
Discussion
No questions or reviews yet.
Related
SkillsAn open CLI that audits a site against more than 300 rules and hands the agent fixes for SEO, performance and security issues
SE Ranking SEO Skills
Claude SEO Skills
A set of agent skills that turn SEO data into finished deliverables: briefs, audits, keyword clusters, schema, sitemap
A CLI and agent skill for website SEO audits: technical SEO, Core Web Vitals, structured data, security and AI search readiness
SEO audits for sites, articles and GitHub repos: topic sub-skills, evidence-collecting scripts and a fix plan
Yandex SEO audit
yandex-seo-audit
A Claude Code skill for technical SEO audits under Yandex requirements: canonical tags, JSON-LD, robots.txt, favicon and Webmaster diagnostics
A single-page SEO audit by URL: a structured HTML report with findings, for OpenClaw, Claude Code and other agents
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.
README badge
Original 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`.