Technical SEO Auditor
Audit a website’s technical SEO foundations and produce a prioritized, actionable remediation report.
The skill clearly describes URL auditing, optional APIs, and credential-related capabilities. Repository context provides positive evidence through SSRF protection, credential file permissions, read-only CI permissions, security policy, and the MIT license. However, this path does not define least-privilege network access, user confirmation, sensitive-data flows, external side effects, or rollback; the README also retains a curl-download-and-execute installation path. Deducted 10 points.
The skill covers nine technical SEO categories and documents handling for unreachable URLs, missing robots.txt, HTTPS failures, and unavailable CWV data. Repository CI and tests provide partial indirect support. Key audit paths are not reproduced by tests in the assessed skill, while several scripts and optional MCP dependencies may be unavailable. Static calibration limits the score to 8.
Trigger phrases, URL input, target scenarios, and Markdown output structure are reasonably clear for technical SEO audits. Non-fit boundaries, exclusion triggers, and environment requirements are incomplete. Documentation is primarily English and core extensions may depend on overseas Google, DataForSEO, or Firecrawl services with uncertain mainland-China reachability. Deducted 7 points.
Front matter supplies the name, trigger description, argument hint, MIT license, and version. Categories, output template, and error-handling table are well organized. Installation and dependency guidance is mostly externalized to the README, while limitations, FAQs, maintenance ownership, changelog coverage, and parameter stability are incomplete for this skill path. Deducted 7 points.
The nine audit categories, category scores, prioritized issue sections, and concrete metrics can produce a directly usable technical SEO report, so the core value is clear. Correctness depends on live fetching, browser rendering, third-party APIs, and the execution environment. Because this review is static and cannot confirm output completeness or practical advantage over manual alternatives, the score is capped at 6.
The skill cites Google, Web.dev, and related technical guidance and provides specific thresholds, protocols, and failure cases. Repository context also supplies CI, tests, and security documentation. However, cited material was not independently verified here, and the tests mainly cover other scripts rather than this skill's key audit flow. Deducted 6 points; static calibration limits the score to 4.
- The workflow fetches arbitrary user-supplied URLs and may use OAuth, Google APIs, DataForSEO, or Firecrawl; confirm target scope, credential use, network isolation, and data retention before deployment.
- The skill contains 2025-2026 claims about search engines and AI crawlers that were not temporally verified in this review; recheck official documentation before use.
- Core data may depend on Google, DataForSEO, or Firecrawl, creating mainland-China reachability, quota, and credential risks; no Chinese-language output or local fallback is documented.
- Referenced scripts, reference files, and optional MCP capabilities were not all included in the supplied material, so end-to-end executability remains unconfirmed.
What does this skill do, and when should you use it?
Technical SEO Auditor is the single technical module profiled from the claude-seo repository. It covers nine areas: crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals, structured data, JavaScript rendering, and IndexNow. It checks items such as robots.txt, XML sitemaps, canonical tags, HTTPS, security headers, mobile behavior, and server-rendered versus JavaScript-injected SEO elements. The output includes a 0–100 technical score, category scores, prioritized issues, and remediation guidance. Playwright, DataForSEO, and Google API integrations can enrich the audit but are optional.
Reads and evaluates a target URL’s robots.txt, XML sitemap, noindex directives, canonical tags, duplicate-content signals, pagination, hreflang, HTTPS, security headers, URL structure, mobile layout, Core Web Vitals, structured data, and JavaScript rendering; checks AI-crawler robots.txt policies, accessibility-tree signals, and agent-friendly page characteristics; when available, runs Playwright and Python scripts or uses DataForSEO, PageSpeed Insights, CrUX, and Search Console integrations; produces a technical score, a nine-category breakdown, severity-ranked issues, and recommended actions.
- An SEO consultant needs a rapid technical health check before a client review and wants a scored, prioritized issue list.
- A web team is investigating crawl, indexing, or JavaScript-page problems and needs checks for robots.txt, canonical tags, noindex directives, status codes, and rendering.
- An e-commerce team is improving performance and product markup and needs checks for LCP, INP, CLS, server-rendered HTML, and structured-data delivery.
- An international site is preparing a launch and needs to review hreflang, mobile-first indexing, URL structure, and duplicate-content risks.
- A site owner is deciding how to manage AI crawlers and wants to assess robots.txt rules for GPTBot, ClaudeBot, Google-Extended, and similar crawlers.
What are this skill's strengths and limitations?
- Covers nine clearly defined technical SEO categories.
- Produces an overall score, category scores, and severity-based priorities.
- Includes AI-crawler management, accessibility-tree checks, and forward-looking agent-friendly page signals.
- Can use Playwright, PageSpeed Insights, CrUX, Search Console, and optional MCP integrations.
- MIT-licensed and usable without external API credentials for the core workflow.
- The supplied material does not provide separate test coverage for this individual module; README test counts refer to the repository collection.
- Without Google API or CrUX data, Core Web Vitals may rely on Lighthouse lab data or estimates.
- Pages whose critical content loads after scrolling or user interaction can still produce noisy findings and may require additional Playwright or visual review.
- DataForSEO, Google APIs, and other MCP extensions require separate credentials or accounts.
- The documented installation targets the Claude Code collection; other clients must provide the required shell, filesystem, and network runtime themselves.
How do you install this skill?
This skill is distributed inside the AgriciDaniel/claude-seo repository at skills/seo-technical/SKILL.md. For the Claude Code plugin, run /plugin marketplace add AgriciDaniel/claude-seo, then /plugin install claude-seo@agricidaniel-claude-seo. On Unix/macOS/Linux, run git clone --depth 1 https://github.com/AgriciDaniel/claude-seo.git, followed by bash claude-seo/install.sh. On Windows PowerShell, clone the repository and run powershell -ExecutionPolicy Bypass -File claude-seo\install.ps1.
How do you use this skill?
In Claude Code, run /seo technical https://example.com, or ask for a technical SEO audit using a target URL and phrases such as “technical SEO,” “crawl issues,” “robots.txt,” “Core Web Vitals,” “site speed,” or “security headers.” Configure Google APIs when you need PSI, CrUX, or Search Console data. Use the Playwright-based scripts when rendered-page inspection is needed.
How does this skill compare with similar options?
The README compares Claude SEO with Screaming Frog and Ahrefs Site Audit: Screaming Frog is more focused on deep, fast link-graph crawling, while Ahrefs Site Audit provides a proprietary backlink index and link intelligence. This skill emphasizes conversational technical SEO analysis, synthesized recommendations, and verifiable remediation output.