{
  "schemaVersion": "1.0",
  "item": {
    "slug": "squirrelscan",
    "name": "audit website for SEO, security, performance and 200+ other issues",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/nc9/squirrelscan",
    "canonicalUrl": "https://clawhub.ai/nc9/squirrelscan",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/squirrelscan",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=squirrelscan",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/OUTPUT-FORMAT.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/squirrelscan"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/squirrelscan",
    "agentPageUrl": "https://openagent3.xyz/skills/squirrelscan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/squirrelscan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/squirrelscan/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Website Audit Skill",
        "body": "Audit websites for SEO, technical, content, performance and security issues using the squirrelscan cli.\n\nsquirrelscan provides a cli tool squirrel - available for macos, windows and linux. It carries out extensive website auditing\nby emulating a browser, search crawler, and analyzing the website's structure and content against over 230+ rules.\n\nIt will provide you a list of issues as well as suggestions on how to fix them."
      },
      {
        "title": "Links",
        "body": "squirrelscan website is at https://squirrelscan.com\ndocumentation (including rule references) are at docs.squirrelscan.com\n\nYou can look up the docs for any rule with this template:\n\nhttps://docs.squirrelscan.com/rules/{rule_category}/{rule_id}\n\nexample:\n\nhttps://docs.squirrelscan.com/rules/links/external-links"
      },
      {
        "title": "What This Skill Does",
        "body": "This skill enables AI agents to audit websites for over 230 rules in 21 categories, including:\n\nSEO issues: Meta tags, titles, descriptions, canonical URLs, Open Graph tags\nTechnical problems: Broken links, redirect chains, page speed, mobile-friendliness\nPerformance: Page load time, resource usage, caching\nContent quality: Heading structure, image alt text, content analysis\nSecurity: Leaked secrets, HTTPS usage, security headers, mixed content\nAccessibility: Alt text, color contrast, keyboard navigation\nUsability: Form validation, error handling, user flow\nLinks: Checks for broken internal and external links\nE-E-A-T: Expertise, Experience, Authority, Trustworthiness\nUser Experience: User flow, error handling, form validation\nMobile: Checks for mobile-friendliness, responsive design, touch-friendly elements\nCrawlability: Checks for crawlability, robots.txt, sitemap.xml and more\nSchema: Schema.org markup, structured data, rich snippets\nLegal: Compliance with legal requirements, privacy policies, terms of service\nSocial: Open graph, twitter cards and validating schemas, snippets etc.\nUrl Structure: Length, hyphens, keywords\nKeywords: Keyword stuffing\nContent: Content structure, headings\nImages: Alt text, color contrast, image size, image format\nLocal SEO: NAP consistency, geo metadata\nVideo: VideoObject schema, accessibility\n\nand more\n\nThe audit crawls the website, analyzes each page against audit rules, and returns a comprehensive report with:\n\nOverall health score (0-100)\nCategory breakdowns (core SEO, technical SEO, content, security)\nSpecific issues with affected URLs\nBroken link detection\nActionable recommendations\nRules have levels of error, warning and notice and also have a rank between 1 and 10"
      },
      {
        "title": "When to Use",
        "body": "Use this skill when you need to:\n\nAnalyze a website's health\nDebug technical SEO issues\nFix all of the issues mentioned above\nCheck for broken links\nValidate meta tags and structured data\nGenerate site audit reports\nCompare site health before/after changes\nImprove website performance, accessibility, SEO, security and more.\n\nYou should re-audit as often as possible to ensure your website remains healthy and performs well."
      },
      {
        "title": "Prerequisites",
        "body": "This skill requires the squirrel CLI installed and in PATH.\n\nInstall: squirrelscan.com/download\n\nVerify:\n\nsquirrel --version"
      },
      {
        "title": "Setup",
        "body": "Run squirrel init to create a squirrel.toml config in the current directory. If none exists, create one and specify a project name:\n\nsquirrel init -n my-project\n# overwrite existing config\nsquirrel init -n my-project --force"
      },
      {
        "title": "Intro",
        "body": "There are three processes that you can run and they're all cached in the local project database:\n\ncrawl - subcommand to run a crawl or refresh, continue a crawl\nanalyze - subcommand to analyze the crawl results\nreport - subcommand to generate a report in desired format (llm, text, console, html etc.)\n\nthe 'audit' command is a wrapper around these three processes and runs them sequentially:\n\nsquirrel audit https://example.com --format llm\n\nYOU SHOULD always prefer format option llm - it was made for you and provides an exhaustive and compact output format.\n\nFIRST SCAN should be a surface scan, which is a quick and shallow scan of the website to gather basic information about the website, such as its structure, content, and technology stack. This scan can be done quickly and without impacting the website's performance.\n\nSECOND SCAN should be a deep scan, which is a thorough and detailed scan of the website to gather more information about the website, such as its security, performance, and accessibility. This scan can take longer and may impact the website's performance.\n\nIf the user doesn't provide a website to audit, ask which URL they'd like audited.\n\nYou should PREFER to audit live websites - only there do we get a TRUE representation of the website and performance or rendering issuers.\n\nIf you have both local and live websites to audit, prompt the user to choose which one to audit and SUGGEST they choose live.\n\nYou can apply fixes from an audit on the live site against the local code.\n\nWhen planning scope tasks so they can run concurrently as sub-agents to speed up fixes.\n\nWhen implementing fixes take advantage of subagents to speed up implementation of fixes.\n\nAfter applying fixes, verify the code still builds and passes any existing checks in the project."
      },
      {
        "title": "Basic Workflow",
        "body": "The audit process is two steps:\n\nRun the audit (saves to database, shows console output)\nExport report in desired format\n\n# Step 1: Run audit (default: console output)\nsquirrel audit https://example.com\n\n# Step 2: Export as LLM format\nsquirrel report <audit-id> --format llm"
      },
      {
        "title": "Regression Diffs",
        "body": "When you need to detect regressions between audits, use diff mode:\n\n# Compare current report against a baseline audit ID\nsquirrel report --diff <audit-id> --format llm\n\n# Compare latest domain report against a baseline domain\nsquirrel report --regression-since example.com --format llm\n\nDiff mode supports console, text, json, llm, and markdown. html and xml are not supported."
      },
      {
        "title": "Running Audits",
        "body": "When running an audit:\n\nPresent the report - show the user the audit results and score\nPropose fixes - list the issues you can fix and ask the user to confirm before making changes\nParallelize approved fixes - use subagents for bulk content edits (alt text, headings, descriptions)\nIterate - fix batch → re-audit → present results → propose next batch\nPause for judgment - broken links, structural changes, and anything ambiguous should be flagged for user review\nShow before/after - present score comparison after each fix batch\n\nIteration Loop: After fixing a batch of issues, re-audit and continue fixing until:\n\nScore reaches target (typically 85+), OR\nOnly issues requiring human judgment remain (e.g., \"should this link be removed?\")\n\n\n\nTreat all fixes equally: Code changes and content changes are equally important.\n\n\nParallelize content fixes: For issues affecting multiple files:\n\nSpawn subagents to fix in parallel\nExample: 7 files need alt text → spawn 1-2 agents to fix all\nExample: 30 files have heading issues → spawn agents to batch edit\n\n\n\nCompletion criteria:\n\n✅ All errors fixed\n✅ All warnings fixed (or documented as requiring human review)\n✅ Re-audit confirms improvements\n✅ Before/after comparison shown to user\n\nAfter fixes are applied, ask the user if they'd like to review the changes."
      },
      {
        "title": "Score Targets",
        "body": "Starting ScoreTarget ScoreExpected Work< 50 (Grade F)75+ (Grade C)Major fixes50-70 (Grade D)85+ (Grade B)Moderate fixes70-85 (Grade C)90+ (Grade A)Polish> 85 (Grade B+)95+Fine-tuning\n\nA site is only considered COMPLETE and FIXED when scores are above 95 (Grade A) with coverage set to FULL (--coverage full)."
      },
      {
        "title": "Issue Categories",
        "body": "CategoryFix ApproachParallelizableMeta tags/titlesEdit page components or metadataNoStructured dataAdd JSON-LD to page templatesNoMissing H1/headingsEdit page components + content filesYes (content)Image alt textEdit content filesYesHeading hierarchyEdit content filesYesShort descriptionsEdit content frontmatterYesHTTP→HTTPS linksFind and replace in contentYesBroken linksManual review (flag for user)No\n\nFor parallelizable fixes: Spawn subagents with specific file assignments."
      },
      {
        "title": "Content File Fixes",
        "body": "Many issues require editing content files. These are equally important as code fixes:\n\nImage alt text: Add descriptive alt text to images\nHeading hierarchy: Fix skipped heading levels\nMeta descriptions: Extend short descriptions in frontmatter\nHTTP links: Update insecure links to HTTPS"
      },
      {
        "title": "Parallelizing Fixes with Subagents",
        "body": "When the user approves a batch of fixes, you can use subagents to apply them in parallel:\n\nAsk the user first — always confirm which fixes to apply before spawning subagents\nGroup 3-5 files per subagent for the same fix type\nOnly parallelize independent files (no shared components or config)\nSpawn multiple subagents in a single message for concurrent execution"
      },
      {
        "title": "Advanced Options",
        "body": "Audit more pages:\n\nsquirrel audit https://example.com --max-pages 200\n\nForce fresh crawl (ignore cache):\n\nsquirrel audit https://example.com --refresh\n\nResume interrupted crawl:\n\nsquirrel audit https://example.com --resume\n\nVerbose output for debugging:\n\nsquirrel audit https://example.com --verbose"
      },
      {
        "title": "Audit Command Options",
        "body": "OptionAliasDescriptionDefault--format <fmt>-f <fmt>Output format: console, text, json, html, markdown, llmconsole--coverage <mode>-C <mode>Coverage mode: quick, surface, fullsurface--max-pages <n>-m <n>Maximum pages to crawl (max 5000)varies by coverage--output <path>-o <path>Output file path---refresh-rIgnore cache, fetch all pages freshfalse--resume-Resume interrupted crawlfalse--verbose-vVerbose outputfalse--debug-Debug loggingfalse--trace-Enable performance tracingfalse--project-name <name>-n <name>Override project namefrom config"
      },
      {
        "title": "Coverage Modes",
        "body": "Choose a coverage mode based on your audit needs:\n\nModeDefault PagesBehaviorUse Casequick25Seed + sitemaps only, no link discoveryCI checks, fast health checksurface100One sample per URL patternGeneral audits (default)full500Crawl everything up to limitDeep analysis\n\nSurface mode is smart - it detects URL patterns like /blog/{slug} or /products/{id} and only crawls one sample per pattern. This makes it efficient for sites with many similar pages (blogs, e-commerce).\n\n# Quick health check (25 pages, no link discovery)\nsquirrel audit https://example.com -C quick --format llm\n\n# Default surface audit (100 pages, pattern sampling)\nsquirrel audit https://example.com --format llm\n\n# Full comprehensive audit (500 pages)\nsquirrel audit https://example.com -C full --format llm\n\n# Override page limit for any mode\nsquirrel audit https://example.com -C surface -m 200 --format llm\n\nWhen to use each mode:\n\nquick: CI pipelines, daily health checks, monitoring\nsurface: Most audits - covers unique templates efficiently\nfull: Before launches, comprehensive analysis, deep dives"
      },
      {
        "title": "Report Command Options",
        "body": "OptionAliasDescription--list-lList recent audits--severity <level>-Filter by severity: error, warning, all--category <cats>-Filter by categories (comma-separated)--format <fmt>-f <fmt>Output format: console, text, json, html, markdown, xml, llm--output <path>-o <path>Output file path--input <path>-i <path>Load from JSON file (fallback mode)"
      },
      {
        "title": "Config Subcommands",
        "body": "CommandDescriptionconfig showShow current configconfig set <key> <value>Set config valueconfig pathShow config file pathconfig validateValidate config file"
      },
      {
        "title": "Other Commands",
        "body": "CommandDescriptionsquirrel feedbackSend feedback to squirrelscan teamsquirrel skills installInstall Claude Code skillsquirrel skills updateUpdate Claude Code skill"
      },
      {
        "title": "Self Commands",
        "body": "Self-management commands under squirrel self:\n\nCommandDescriptionself installBootstrap local installationself updateCheck and apply updatesself completionGenerate shell completionsself doctorRun health checksself versionShow version informationself settingsManage CLI settingsself uninstallRemove squirrel from the system"
      },
      {
        "title": "Console Output (default)",
        "body": "The audit command shows human-readable console output by default with colored output and progress indicators."
      },
      {
        "title": "LLM Format",
        "body": "To get LLM-optimized output, use the report command with --format llm:\n\nsquirrel report <audit-id> --format llm\n\nThe LLM format is a compact XML/text hybrid optimized for token efficiency (40% smaller than verbose XML):\n\nSummary: Overall health score and key metrics\nIssues by Category: Grouped by audit rule category (core SEO, technical, content, security)\nBroken Links: List of broken external and internal links\nRecommendations: Prioritized action items with fix suggestions\n\nSee OUTPUT-FORMAT.md for detailed format specification."
      },
      {
        "title": "Example 1: Quick Site Audit with LLM Output",
        "body": "# User asks: \"Check squirrelscan.com for SEO issues\"\nsquirrel audit https://squirrelscan.com --format llm"
      },
      {
        "title": "Example 2: Deep Audit for Large Site",
        "body": "# User asks: \"Do a thorough audit of my blog with up to 500 pages\"\nsquirrel audit https://myblog.com --max-pages 500 --format llm"
      },
      {
        "title": "Example 3: Fresh Audit After Changes",
        "body": "# User asks: \"Re-audit the site and ignore cached results\"\nsquirrel audit https://example.com --refresh --format llm"
      },
      {
        "title": "Example 4: Two-Step Workflow (Reuse Previous Audit)",
        "body": "# First run an audit\nsquirrel audit https://example.com\n# Note the audit ID from output (e.g., \"a1b2c3d4\")\n\n# Later, export in different format\nsquirrel report a1b2c3d4 --format llm"
      },
      {
        "title": "Output",
        "body": "On completion give the user a summary of all of the changes you made."
      },
      {
        "title": "squirrel command not found",
        "body": "If you see this error, squirrel is not installed or not in your PATH.\n\nSolution:\n\nInstall squirrel: squirrelscan.com/download\nEnsure ~/.local/bin is in PATH\nVerify: squirrel --version"
      },
      {
        "title": "Permission denied",
        "body": "If squirrel is not executable, ensure the binary has execute permissions. Reinstalling from squirrelscan.com/download will fix this."
      },
      {
        "title": "Crawl timeout or slow performance",
        "body": "For very large sites, the audit may take several minutes. Use --verbose to see progress:\n\nsquirrel audit https://example.com --format llm --verbose"
      },
      {
        "title": "Invalid URL",
        "body": "Ensure the URL includes the protocol (http:// or https://):\n\n# ✗ Wrong\nsquirrel audit example.com\n\n# ✓ Correct\nsquirrel audit https://example.com"
      },
      {
        "title": "How It Works",
        "body": "Crawl: Discovers and fetches pages starting from the base URL\nAnalyze: Runs audit rules on each page\nExternal Links: Checks external links for availability\nReport: Generates LLM-optimized report with findings\n\nThe audit is stored in a local database and can be retrieved later with squirrel report commands."
      },
      {
        "title": "Additional Resources",
        "body": "Output Format Reference: OUTPUT-FORMAT.md\nsquirrelscan Documentation: https://docs.squirrelscan.com\nCLI Help: squirrel audit --help"
      }
    ],
    "body": "Website Audit Skill\n\nAudit websites for SEO, technical, content, performance and security issues using the squirrelscan cli.\n\nsquirrelscan provides a cli tool squirrel - available for macos, windows and linux. It carries out extensive website auditing by emulating a browser, search crawler, and analyzing the website's structure and content against over 230+ rules.\n\nIt will provide you a list of issues as well as suggestions on how to fix them.\n\nLinks\nsquirrelscan website is at https://squirrelscan.com\ndocumentation (including rule references) are at docs.squirrelscan.com\n\nYou can look up the docs for any rule with this template:\n\nhttps://docs.squirrelscan.com/rules/{rule_category}/{rule_id}\n\nexample:\n\nhttps://docs.squirrelscan.com/rules/links/external-links\n\nWhat This Skill Does\n\nThis skill enables AI agents to audit websites for over 230 rules in 21 categories, including:\n\nSEO issues: Meta tags, titles, descriptions, canonical URLs, Open Graph tags\nTechnical problems: Broken links, redirect chains, page speed, mobile-friendliness\nPerformance: Page load time, resource usage, caching\nContent quality: Heading structure, image alt text, content analysis\nSecurity: Leaked secrets, HTTPS usage, security headers, mixed content\nAccessibility: Alt text, color contrast, keyboard navigation\nUsability: Form validation, error handling, user flow\nLinks: Checks for broken internal and external links\nE-E-A-T: Expertise, Experience, Authority, Trustworthiness\nUser Experience: User flow, error handling, form validation\nMobile: Checks for mobile-friendliness, responsive design, touch-friendly elements\nCrawlability: Checks for crawlability, robots.txt, sitemap.xml and more\nSchema: Schema.org markup, structured data, rich snippets\nLegal: Compliance with legal requirements, privacy policies, terms of service\nSocial: Open graph, twitter cards and validating schemas, snippets etc.\nUrl Structure: Length, hyphens, keywords\nKeywords: Keyword stuffing\nContent: Content structure, headings\nImages: Alt text, color contrast, image size, image format\nLocal SEO: NAP consistency, geo metadata\nVideo: VideoObject schema, accessibility\n\nand more\n\nThe audit crawls the website, analyzes each page against audit rules, and returns a comprehensive report with:\n\nOverall health score (0-100)\nCategory breakdowns (core SEO, technical SEO, content, security)\nSpecific issues with affected URLs\nBroken link detection\nActionable recommendations\nRules have levels of error, warning and notice and also have a rank between 1 and 10\nWhen to Use\n\nUse this skill when you need to:\n\nAnalyze a website's health\nDebug technical SEO issues\nFix all of the issues mentioned above\nCheck for broken links\nValidate meta tags and structured data\nGenerate site audit reports\nCompare site health before/after changes\nImprove website performance, accessibility, SEO, security and more.\n\nYou should re-audit as often as possible to ensure your website remains healthy and performs well.\n\nPrerequisites\n\nThis skill requires the squirrel CLI installed and in PATH.\n\nInstall: squirrelscan.com/download\n\nVerify:\n\nsquirrel --version\n\nSetup\n\nRun squirrel init to create a squirrel.toml config in the current directory. If none exists, create one and specify a project name:\n\nsquirrel init -n my-project\n# overwrite existing config\nsquirrel init -n my-project --force\n\nUsage\nIntro\n\nThere are three processes that you can run and they're all cached in the local project database:\n\ncrawl - subcommand to run a crawl or refresh, continue a crawl\nanalyze - subcommand to analyze the crawl results\nreport - subcommand to generate a report in desired format (llm, text, console, html etc.)\n\nthe 'audit' command is a wrapper around these three processes and runs them sequentially:\n\nsquirrel audit https://example.com --format llm\n\n\nYOU SHOULD always prefer format option llm - it was made for you and provides an exhaustive and compact output format.\n\nFIRST SCAN should be a surface scan, which is a quick and shallow scan of the website to gather basic information about the website, such as its structure, content, and technology stack. This scan can be done quickly and without impacting the website's performance.\n\nSECOND SCAN should be a deep scan, which is a thorough and detailed scan of the website to gather more information about the website, such as its security, performance, and accessibility. This scan can take longer and may impact the website's performance.\n\nIf the user doesn't provide a website to audit, ask which URL they'd like audited.\n\nYou should PREFER to audit live websites - only there do we get a TRUE representation of the website and performance or rendering issuers.\n\nIf you have both local and live websites to audit, prompt the user to choose which one to audit and SUGGEST they choose live.\n\nYou can apply fixes from an audit on the live site against the local code.\n\nWhen planning scope tasks so they can run concurrently as sub-agents to speed up fixes.\n\nWhen implementing fixes take advantage of subagents to speed up implementation of fixes.\n\nAfter applying fixes, verify the code still builds and passes any existing checks in the project.\n\nBasic Workflow\n\nThe audit process is two steps:\n\nRun the audit (saves to database, shows console output)\nExport report in desired format\n# Step 1: Run audit (default: console output)\nsquirrel audit https://example.com\n\n# Step 2: Export as LLM format\nsquirrel report <audit-id> --format llm\n\nRegression Diffs\n\nWhen you need to detect regressions between audits, use diff mode:\n\n# Compare current report against a baseline audit ID\nsquirrel report --diff <audit-id> --format llm\n\n# Compare latest domain report against a baseline domain\nsquirrel report --regression-since example.com --format llm\n\n\nDiff mode supports console, text, json, llm, and markdown. html and xml are not supported.\n\nRunning Audits\n\nWhen running an audit:\n\nPresent the report - show the user the audit results and score\nPropose fixes - list the issues you can fix and ask the user to confirm before making changes\nParallelize approved fixes - use subagents for bulk content edits (alt text, headings, descriptions)\nIterate - fix batch → re-audit → present results → propose next batch\nPause for judgment - broken links, structural changes, and anything ambiguous should be flagged for user review\nShow before/after - present score comparison after each fix batch\n\nIteration Loop: After fixing a batch of issues, re-audit and continue fixing until:\n\nScore reaches target (typically 85+), OR\nOnly issues requiring human judgment remain (e.g., \"should this link be removed?\")\n\nTreat all fixes equally: Code changes and content changes are equally important.\n\nParallelize content fixes: For issues affecting multiple files:\n\nSpawn subagents to fix in parallel\nExample: 7 files need alt text → spawn 1-2 agents to fix all\nExample: 30 files have heading issues → spawn agents to batch edit\n\nCompletion criteria:\n\n✅ All errors fixed\n✅ All warnings fixed (or documented as requiring human review)\n✅ Re-audit confirms improvements\n✅ Before/after comparison shown to user\n\nAfter fixes are applied, ask the user if they'd like to review the changes.\n\nScore Targets\nStarting Score\tTarget Score\tExpected Work\n< 50 (Grade F)\t75+ (Grade C)\tMajor fixes\n50-70 (Grade D)\t85+ (Grade B)\tModerate fixes\n70-85 (Grade C)\t90+ (Grade A)\tPolish\n> 85 (Grade B+)\t95+\tFine-tuning\n\nA site is only considered COMPLETE and FIXED when scores are above 95 (Grade A) with coverage set to FULL (--coverage full).\n\nIssue Categories\nCategory\tFix Approach\tParallelizable\nMeta tags/titles\tEdit page components or metadata\tNo\nStructured data\tAdd JSON-LD to page templates\tNo\nMissing H1/headings\tEdit page components + content files\tYes (content)\nImage alt text\tEdit content files\tYes\nHeading hierarchy\tEdit content files\tYes\nShort descriptions\tEdit content frontmatter\tYes\nHTTP→HTTPS links\tFind and replace in content\tYes\nBroken links\tManual review (flag for user)\tNo\n\nFor parallelizable fixes: Spawn subagents with specific file assignments.\n\nContent File Fixes\n\nMany issues require editing content files. These are equally important as code fixes:\n\nImage alt text: Add descriptive alt text to images\nHeading hierarchy: Fix skipped heading levels\nMeta descriptions: Extend short descriptions in frontmatter\nHTTP links: Update insecure links to HTTPS\nParallelizing Fixes with Subagents\n\nWhen the user approves a batch of fixes, you can use subagents to apply them in parallel:\n\nAsk the user first — always confirm which fixes to apply before spawning subagents\nGroup 3-5 files per subagent for the same fix type\nOnly parallelize independent files (no shared components or config)\nSpawn multiple subagents in a single message for concurrent execution\nAdvanced Options\n\nAudit more pages:\n\nsquirrel audit https://example.com --max-pages 200\n\n\nForce fresh crawl (ignore cache):\n\nsquirrel audit https://example.com --refresh\n\n\nResume interrupted crawl:\n\nsquirrel audit https://example.com --resume\n\n\nVerbose output for debugging:\n\nsquirrel audit https://example.com --verbose\n\nCommon Options\nAudit Command Options\nOption\tAlias\tDescription\tDefault\n--format <fmt>\t-f <fmt>\tOutput format: console, text, json, html, markdown, llm\tconsole\n--coverage <mode>\t-C <mode>\tCoverage mode: quick, surface, full\tsurface\n--max-pages <n>\t-m <n>\tMaximum pages to crawl (max 5000)\tvaries by coverage\n--output <path>\t-o <path>\tOutput file path\t-\n--refresh\t-r\tIgnore cache, fetch all pages fresh\tfalse\n--resume\t-\tResume interrupted crawl\tfalse\n--verbose\t-v\tVerbose output\tfalse\n--debug\t-\tDebug logging\tfalse\n--trace\t-\tEnable performance tracing\tfalse\n--project-name <name>\t-n <name>\tOverride project name\tfrom config\nCoverage Modes\n\nChoose a coverage mode based on your audit needs:\n\nMode\tDefault Pages\tBehavior\tUse Case\nquick\t25\tSeed + sitemaps only, no link discovery\tCI checks, fast health check\nsurface\t100\tOne sample per URL pattern\tGeneral audits (default)\nfull\t500\tCrawl everything up to limit\tDeep analysis\n\nSurface mode is smart - it detects URL patterns like /blog/{slug} or /products/{id} and only crawls one sample per pattern. This makes it efficient for sites with many similar pages (blogs, e-commerce).\n\n# Quick health check (25 pages, no link discovery)\nsquirrel audit https://example.com -C quick --format llm\n\n# Default surface audit (100 pages, pattern sampling)\nsquirrel audit https://example.com --format llm\n\n# Full comprehensive audit (500 pages)\nsquirrel audit https://example.com -C full --format llm\n\n# Override page limit for any mode\nsquirrel audit https://example.com -C surface -m 200 --format llm\n\n\nWhen to use each mode:\n\nquick: CI pipelines, daily health checks, monitoring\nsurface: Most audits - covers unique templates efficiently\nfull: Before launches, comprehensive analysis, deep dives\nReport Command Options\nOption\tAlias\tDescription\n--list\t-l\tList recent audits\n--severity <level>\t-\tFilter by severity: error, warning, all\n--category <cats>\t-\tFilter by categories (comma-separated)\n--format <fmt>\t-f <fmt>\tOutput format: console, text, json, html, markdown, xml, llm\n--output <path>\t-o <path>\tOutput file path\n--input <path>\t-i <path>\tLoad from JSON file (fallback mode)\nConfig Subcommands\nCommand\tDescription\nconfig show\tShow current config\nconfig set <key> <value>\tSet config value\nconfig path\tShow config file path\nconfig validate\tValidate config file\nOther Commands\nCommand\tDescription\nsquirrel feedback\tSend feedback to squirrelscan team\nsquirrel skills install\tInstall Claude Code skill\nsquirrel skills update\tUpdate Claude Code skill\nSelf Commands\n\nSelf-management commands under squirrel self:\n\nCommand\tDescription\nself install\tBootstrap local installation\nself update\tCheck and apply updates\nself completion\tGenerate shell completions\nself doctor\tRun health checks\nself version\tShow version information\nself settings\tManage CLI settings\nself uninstall\tRemove squirrel from the system\nOutput Formats\nConsole Output (default)\n\nThe audit command shows human-readable console output by default with colored output and progress indicators.\n\nLLM Format\n\nTo get LLM-optimized output, use the report command with --format llm:\n\nsquirrel report <audit-id> --format llm\n\n\nThe LLM format is a compact XML/text hybrid optimized for token efficiency (40% smaller than verbose XML):\n\nSummary: Overall health score and key metrics\nIssues by Category: Grouped by audit rule category (core SEO, technical, content, security)\nBroken Links: List of broken external and internal links\nRecommendations: Prioritized action items with fix suggestions\n\nSee OUTPUT-FORMAT.md for detailed format specification.\n\nExamples\nExample 1: Quick Site Audit with LLM Output\n# User asks: \"Check squirrelscan.com for SEO issues\"\nsquirrel audit https://squirrelscan.com --format llm\n\nExample 2: Deep Audit for Large Site\n# User asks: \"Do a thorough audit of my blog with up to 500 pages\"\nsquirrel audit https://myblog.com --max-pages 500 --format llm\n\nExample 3: Fresh Audit After Changes\n# User asks: \"Re-audit the site and ignore cached results\"\nsquirrel audit https://example.com --refresh --format llm\n\nExample 4: Two-Step Workflow (Reuse Previous Audit)\n# First run an audit\nsquirrel audit https://example.com\n# Note the audit ID from output (e.g., \"a1b2c3d4\")\n\n# Later, export in different format\nsquirrel report a1b2c3d4 --format llm\n\nOutput\n\nOn completion give the user a summary of all of the changes you made.\n\nTroubleshooting\nsquirrel command not found\n\nIf you see this error, squirrel is not installed or not in your PATH.\n\nSolution:\n\nInstall squirrel: squirrelscan.com/download\nEnsure ~/.local/bin is in PATH\nVerify: squirrel --version\nPermission denied\n\nIf squirrel is not executable, ensure the binary has execute permissions. Reinstalling from squirrelscan.com/download will fix this.\n\nCrawl timeout or slow performance\n\nFor very large sites, the audit may take several minutes. Use --verbose to see progress:\n\nsquirrel audit https://example.com --format llm --verbose\n\nInvalid URL\n\nEnsure the URL includes the protocol (http:// or https://):\n\n# ✗ Wrong\nsquirrel audit example.com\n\n# ✓ Correct\nsquirrel audit https://example.com\n\nHow It Works\nCrawl: Discovers and fetches pages starting from the base URL\nAnalyze: Runs audit rules on each page\nExternal Links: Checks external links for availability\nReport: Generates LLM-optimized report with findings\n\nThe audit is stored in a local database and can be retrieved later with squirrel report commands.\n\nAdditional Resources\nOutput Format Reference: OUTPUT-FORMAT.md\nsquirrelscan Documentation: https://docs.squirrelscan.com\nCLI Help: squirrel audit --help"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nc9/squirrelscan",
    "publisherUrl": "https://clawhub.ai/nc9/squirrelscan",
    "owner": "nc9",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/squirrelscan",
    "downloadUrl": "https://openagent3.xyz/downloads/squirrelscan",
    "agentUrl": "https://openagent3.xyz/skills/squirrelscan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/squirrelscan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/squirrelscan/agent.md"
  }
}