Nik Cubrilovic
8721d5eea3
The skill could run an audit that reports a schema/entity-* finding and had nothing to say about it. Adds the three things an agent needs: - A Structured data section: what the entity map is, where it appears in each report format, `squirrel entities` with its filters and formats, and how to read `--diff` to tell a landed fix from a re-audit that missed the pages. - The five entity MCP tools, with the fix-and-verify loop and the four fields that say what you are NOT being told: truncation, warnings, analyzed and generatedIds. An agent that reads an empty result as good news is the failure these exist to prevent. - references/entity-map-fixes.md, loaded when a finding appears: the shape that works, a row per finding, and the exact change for Yoast, Rank Math, WordLift, Next.js, Astro and tangly. The skill description now names the entity map, so a question about structured data identity selects it. Canonical source: https://docs.squirrelscan.com/entity-map Claude-Session: https://claude.ai/code/session_01T8w822GqnrviVMytnAsKFP Signed-off-by: Nik Cubrilovic <git@nikcub.me>
squirrelscan Skills & Plugins
Website audits for AI agents: skills, plugins, and MCP in one repo
What is squirrelscan?
squirrelscan is a website audit tool built for AI agents. It crawls a site, analyzes every page against 260+ rules across SEO, performance, security, accessibility, content, and more, and returns a health score plus concrete, fixable issues.
Features:
- 260+ audit rules across 21 categories
- Leaked secrets detection (96 patterns: OpenAI, Anthropic, AWS, Stripe, and more)
- Multiple output formats: console, text, json, markdown, llm, html
- Diff reports for regressions between audits
- LLM-native output for AI-assisted debugging and optimization
- Optimized for CI/CD pipelines and automation
What's in this repo
| Skill | What it does |
|---|---|
squirrelscan |
Operate the CLI: install, login, run audits, publish reports, credits, API keys, MCP setup, config, troubleshooting |
audit-website |
The fix loop: audit a site, map findings to code, fix in batches, re-audit until it scores well |
The repo is also a Claude Code plugin + marketplace and a Cursor plugin, bundling both skills and the hosted squirrelscan MCP server.
Prerequisites
All skills drive the squirrel CLI, which must be installed and in PATH.
Install: squirrelscan.com/download
Verify:
squirrel --version
Installing
Pick the path for your tool:
| Tool | Install |
|---|---|
| Any agent (Agent Skills standard) | npx skills add squirrelscan/skills |
| Claude Code | /plugin marketplace add squirrelscan/skills then /plugin install squirrelscan@squirrelscan |
| Cursor | npx skills add squirrelscan/skills, or the plugin / MCP deeplink below |
| OpenAI Codex | npx skills add squirrelscan/skills (lands in .agents/skills/) |
| squirrel CLI | squirrel skills install |
| Manual | clone + symlink skills/* into your agent's skills dir |
Agent Skills via npx (works everywhere)
npx skills add squirrelscan/skills
Installs both skills (squirrelscan and audit-website) for whichever agents you select: Claude Code, Codex, Cursor, Gemini CLI, Amp, and more. Skills follow the Agent Skills standard, so the same SKILL.md works across tools. To install just one skill:
npx skills add squirrelscan/skills --skill audit-website
Claude Code plugin (recommended for Claude Code)
/plugin marketplace add squirrelscan/skills
/plugin install squirrelscan@squirrelscan
One step installs both skills and connects the hosted squirrelscan MCP server. Updates ship automatically with new commits to this repo.
Cursor
Three options, lightest to fullest:
- Skills:
npx skills add squirrelscan/skills. Cursor reads Agent Skills from.cursor/skills/,.agents/skills/, and their~/equivalents (it also picks up~/.claude/skills/). - MCP only, one click: Add squirrelscan MCP to Cursor
- Plugin: this repo is also a Cursor plugin (
.cursor-plugin/) bundling both skills and the MCP server, for install via the Cursor Marketplace.
OpenAI Codex
Codex reads skills from .agents/skills/ (project) or ~/.agents/skills/ (global). npx skills add squirrelscan/skills installs there, or clone and symlink the skills/* directories.
From the squirrel CLI
squirrel skills install
squirrel skills update
Manual
git clone https://github.com/squirrelscan/skills.git
Then copy or symlink skills/squirrelscan and skills/audit-website into your agent's skills directory (make link does this for Claude Code and .agents/skills consumers).
MCP server
The hosted MCP server lives at https://mcp.squirrelscan.com/mcp (streamable-http; OAuth or Authorization: Bearer sq_... API key). A local stdio server is available via squirrel mcp. Docs: docs.squirrelscan.com/developers/mcp
Example prompts
Audit this website and fix all errors and warnings
Run an audit on example.com and show me the top 5 critical issues
Check my site for broken links and leaked secrets
Re-audit after the deploy and diff against the last report
Contributing
Contributions are welcome! To suggest new skills or improvements:
- Open an issue to discuss your idea
- Fork this repository
- Create a feature branch
- Submit a pull request
All skills follow the Agent Skills Standard.
License
MIT License — See LICENSE file for details.
Learn more: docs.squirrelscan.com | squirrelscan.com