{
  "markdown": "![squirrelscan](https://mintcdn.com/squirrelscan/CCMTmLbI4xfnpJbQ/logo/light.svg?fit=max&auto=format&n=CCMTmLbI4xfnpJbQ&q=85&s=1303484a4ea3c154c29dd5f6245e55cd)\n\n# squirrelscan Skills & Plugins\n\n**Website audits for AI agents: skills, plugins, and MCP in one repo**\n\n## What is squirrelscan?\n\n[squirrelscan](https://squirrelscan.com) 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.\n\n**Features:**\n\n- 260+ audit rules across 21 categories\n- Leaked secrets detection (96 patterns: OpenAI, Anthropic, AWS, Stripe, and more)\n- Multiple output formats: console, text, json, markdown, llm, html\n- Diff reports for regressions between audits\n- LLM-native output for AI-assisted debugging and optimization\n- Optimized for CI/CD pipelines and automation\n\n## What's in this repo\n\n| Skill | What it does |\n|-------|--------------|\n| [`squirrelscan`](skills/squirrelscan/SKILL.md) | Operate the CLI: install, login, run audits, publish reports, credits, API keys, MCP setup, config, troubleshooting |\n| [`audit-website`](skills/audit-website/SKILL.md) | The fix loop: audit a site, map findings to code, fix in batches, re-audit until it scores well |\n\nThe repo is also a **Claude Code plugin + marketplace** and a **Cursor plugin**, bundling both skills and the hosted squirrelscan MCP server.\n\n## Prerequisites\n\nAll skills drive the **squirrel CLI**, which must be installed and in PATH.\n\n**Install:** [squirrelscan.com/download](https://squirrelscan.com/download)\n\n**Verify:**\n```bash\nsquirrel --version\n```\n\n## Installing\n\nPick the path for your tool:\n\n| Tool | Install |\n|------|---------|\n| Any agent (Agent Skills standard) | `npx skills add squirrelscan/skills` |\n| Claude Code | `/plugin marketplace add squirrelscan/skills` then `/plugin install squirrelscan@squirrelscan` |\n| Cursor | `npx skills add squirrelscan/skills`, or the plugin / MCP deeplink below |\n| OpenAI Codex | `npx skills add squirrelscan/skills` (lands in `.agents/skills/`) |\n| squirrel CLI | `squirrel skills install` |\n| Manual | clone + symlink `skills/*` into your agent's skills dir |\n\n### Agent Skills via npx (works everywhere)\n\n```bash\nnpx skills add squirrelscan/skills\n```\n\nInstalls 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](https://agentskills.io) standard, so the same `SKILL.md` works across tools. To install just one skill:\n\n```bash\nnpx skills add squirrelscan/skills --skill audit-website\n```\n\n### Claude Code plugin (recommended for Claude Code)\n\n```\n/plugin marketplace add squirrelscan/skills\n/plugin install squirrelscan@squirrelscan\n```\n\nOne step installs both skills and connects the hosted squirrelscan MCP server. Updates ship automatically with new commits to this repo.\n\n### Cursor\n\nThree options, lightest to fullest:\n\n1. **Skills**: `npx skills add squirrelscan/skills`. Cursor reads Agent Skills from `.cursor/skills/`, `.agents/skills/`, and their `~/` equivalents (it also picks up `~/.claude/skills/`).\n2. **MCP only, one click**: [Add squirrelscan MCP to Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=squirrelscan&config=eyJ1cmwiOiJodHRwczovL21jcC5zcXVpcnJlbHNjYW4uY29tL21jcCJ9)\n3. **Plugin**: this repo is also a Cursor plugin (`.cursor-plugin/`) bundling both skills and the MCP server, for install via the Cursor Marketplace.\n\n### OpenAI Codex\n\nCodex reads skills from `.agents/skills/` (project) or `~/.agents/skills/` (global). `npx skills add squirrelscan/skills` installs there, or clone and symlink the `skills/*` directories.\n\n### From the squirrel CLI\n\n```bash\nsquirrel skills install\nsquirrel skills update\n```\n\n### Manual\n\n```bash\ngit clone https://github.com/squirrelscan/skills.git\n```\n\nThen 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).\n\n## MCP server\n\nThe 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](https://docs.squirrelscan.com/developers/mcp)\n\n## Example prompts\n\n```\nAudit this website and fix all errors and warnings\n```\n\n```\nRun an audit on example.com and show me the top 5 critical issues\n```\n\n```\nCheck my site for broken links and leaked secrets\n```\n\n```\nRe-audit after the deploy and diff against the last report\n```\n\n## Contributing\n\nContributions are welcome! To suggest new skills or improvements:\n\n1. Open an issue to discuss your idea\n2. Fork this repository\n3. Create a feature branch\n4. Submit a pull request\n\nAll skills follow the [Agent Skills Standard](https://agentskills.io/specification).\n\n## License\n\nMIT License — See [LICENSE](LICENSE) file for details.\n\n---\n\n**Learn more:** [docs.squirrelscan.com](https://docs.squirrelscan.com) | [squirrelscan.com](https://squirrelscan.com)\n",
  "bytes": 5156,
  "sha": "33b36015222ac0b20c76ad1ae2f931d7b6d17ab3009052add68b96aba0844ec4",
  "repo_slug": "squirrelscan/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_squirrelscan_skills_squirrelscan_6bf91ecc/readme"
}