Technical SEO skills
Technical SEO Skills-md for SEOs, Marketers, Claude & Codex
Technical SEO skills are SKILL.md files that turn Claude, Codex and other AI agents into careful site auditors. They check crawling, indexing, rendering, speed, redirects and structured data against Google’s own documentation, then return fixes ranked by impact and effort. All 13 are below: copy one, download it, or take the set.
13 skills, 23,329 words, version 1.1.0.
Technical SEO Audit
Run a complete, prioritised technical SEO audit of any website, from crawl and indexation through rendering, speed, structured data, internal links and AI crawler access, and return a scored action plan.
Crawlability and Indexation Audit
Diagnose why pages are not being crawled, rendered or indexed by Google and Bing, and fix the earliest broken step first. Covers every Search Console Page indexing status ("Crawled, currently not indexed", "Discovered, currently not indexed", soft 404, duplicate without user-selected canonical, Google chose different canonical, blocked by robots.txt, excluded by noindex, redirect, 5xx), crawl stats and host status, bot blocking at the CDN or WAF, index bloat and new-page discovery.
Robots.txt and Robots Directives
Write, audit, test and debug robots.txt files, meta robots tags and X-Robots-Tag headers for Google, Bing and AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Applebot-Extended, CCBot and others), including separate policies for search, AI answers and AI training.
XML Sitemaps
Plan, generate, audit, segment and monitor XML sitemaps and sitemap indexes, including image, video, news and hreflang sitemaps, honest lastmod dates, and batch segmentation for large, programmatic and multilingual sites.
Canonicalization and Duplicate Content
Find duplicate and near-duplicate URLs and make Google and Bing choose the canonical you want, by aligning rel=canonical, redirects, internal links, sitemaps, hreflang and parameter handling. Covers www and non-www, HTTP and HTTPS, trailing slashes, case, tracking and sort parameters, product paths inside collections, pagination, syndication, near-duplicate location or currency pages, and canonicals with hreflang.
Redirects and HTTP Status Codes
Audit and fix redirects (301, 302, 307, 308, meta refresh and JavaScript), redirect chains and loops, 404 and 410 handling, soft 404s, 5xx errors and 503 maintenance responses, build and test redirect maps, and write rules for Apache, Nginx, Cloudflare, Vercel, Netlify and WordPress.
Site Migration SEO
Plan, run and monitor SEO-safe website migrations: domain changes, HTTP to HTTPS, CMS re-platforming (for example WordPress to headless, Webflow to Strapi), URL restructures, redesigns, site mergers, subdomain to subfolder moves and international restructures, with benchmarks, redirect maps, pre-launch checks, launch-day tests and a 90-day recovery watch.
Core Web Vitals and Page Experience
Diagnose and improve Core Web Vitals (Largest Contentful Paint, Interaction to Next Paint and Cumulative Layout Shift) from CrUX and Search Console field data, with lab debugging in Lighthouse, PageSpeed Insights and Chrome DevTools, template-level fixes for WordPress, Elementor, Shopify, Webflow, React and Next.js, and a release check so gains don't slip back.
JavaScript SEO and Rendering
Make JavaScript-heavy sites (React, Next.js, Vue, Nuxt, Angular, Svelte, headless CMS builds and single-page apps) crawlable and indexable: choosing SSR, SSG, ISR or CSR per template, comparing raw and rendered HTML, crawlable links, lazy-loaded content, client-side routing, status codes and meta tags in apps, hydration problems, and visibility to AI crawlers that do not run JavaScript.
Structured Data and Schema Markup
Plan, write, validate and debug structured data (JSON-LD and schema.org) for rich results and entity understanding: Organization, Person, WebSite, WebPage, Article, Product, Offer, merchant listings, Review and AggregateRating, BreadcrumbList, LocalBusiness, Event, JobPosting, VideoObject, SoftwareApplication and connected @graph markup with stable @id values, plus Search Console enhancement reports and policy checks.
Internal Linking and Site Architecture
Audit and design internal linking and site architecture: URL and folder structure, click depth, orphan pages, hub and spoke topic clusters, anchor text, navigation and footer links, breadcrumbs, pagination, related-content modules, links to redirects or noindexed pages, and routing link equity to the pages that make money.
Log File Analysis for SEO
Analyse server, CDN or hosting access logs to see how Googlebot, Bingbot and AI crawlers actually crawl a site: verifying real bots, crawl volume and frequency by template, crawl waste on parameters and redirects, status codes and response times served to bots, orphan URLs bots still request, new-page discovery speed, and AI crawler activity, with ready-to-run command-line and SQL queries.
Faceted Navigation and URL Parameters
Control crawling and indexing of faceted navigation, filters, sorting, internal search, pagination, infinite scroll and URL parameters on e-commerce, marketplace, listings, travel and programmatic sites: decide which filter combinations deserve indexable landing pages from search demand, block or consolidate the rest with robots.txt, canonicals, fragments and internal-link rules, and keep URL order, separators and empty results under control.
LCP Optimisation
Diagnose and fix Largest Contentful Paint: field data at the 75th percentile, the LCP element by template and device, the four LCP subparts (TTFB, load delay, load duration, render delay), fetchpriority, preload, no lazy-loading on the hero, AVIF and responsive images, critical CSS, fonts and WordPress fixes.
INP Optimisation
Diagnose and fix Interaction to Next Paint: field data at the 75th percentile, slow interactions from attribution data, the three phases (input delay, processing, presentation), long tasks, yielding to the main thread, debouncing, web workers, third-party scripts, DOM size, layout thrashing, instant feedback and WordPress fixes.
CLS Optimisation
Diagnose and fix Cumulative Layout Shift: field data at the 75th percentile, shift attribution, reserved space for images, embeds and ads, overlay banners, size-adjusted fallback fonts, transform-based animations, back/forward cache eligibility, code patterns and WordPress fixes.
No skill matches that search. Clear it or choose All.
On this page
What technical SEO skills do for an AI agent
Technical SEO is where general AI models go wrong most often. They repeat advice Google retired years ago, treat every crawler warning as urgent, and recommend fixes that contradict each other, such as blocking a URL in robots.txt and adding noindex to it at the same time. These skills give the agent the rules a senior technical SEO works from, with each rule tied to the Google, web.dev or protocol page it comes from.
Each skill also gives the agent an order of work. Crawling comes before indexing, indexing before ranking, so the audit fixes the earliest broken step first. Findings come back scored by impact and effort and labelled as confirmed, observed or inferred, which keeps the agent honest about what it actually knows.
Where to start: run a full audit with technical-seo-audit
The Technical SEO Audit skill is the entry point. It works through ten layers, from crawl access and indexation to rendering, page experience, structured data and AI crawler access, and hands each finding that needs depth to one of the other twelve skills. Install all 13 so those handoffs work. A first request can be as simple as:
Run a technical SEO audit of example.com. Our money pages are /pricing/ and /product/. Search Console exports and a crawl are attached.
The agent asks once for anything missing, then returns a summary, a scorecard by layer and an action plan with owners and the metric to watch for each fix.
Which skill fixes which problem
Use this table to go straight to the right skill when you already know the symptom.
| Symptom or task | Likely cause | Skill to use |
|---|---|---|
| Traffic dropped and nobody knows why | Anything from a release to a Google update | technical-seo-audit |
| “Crawled, currently not indexed” keeps growing | Thin, duplicate or weakly linked pages | crawlability-indexation-audit |
| “Blocked by robots.txt” or an AI crawler policy to set | A rule that matches more than intended | robots-directives |
| Submitted URLs far higher than indexed URLs | Sitemaps full of redirects, noindex or duplicates | xml-sitemaps |
| “Google chose different canonical than user” | Canonicals, links and sitemaps disagree | canonicalization |
| 404 spikes, redirect chains, soft 404s | Old URLs and rules stacked over time | redirects-status-codes |
| A new domain, CMS or URL structure is planned | Migration risk to rankings | site-migration |
| Failing LCP, INP or CLS in Search Console | Slow server, heavy images or scripts, layout shifts | core-web-vitals |
| Pages index without their text | Content rendered only in the browser | javascript-seo |
| Rich results missing or schema errors | Invalid or unsupported markup | structured-data |
| Good pages get little traffic | Buried pages, orphans, weak anchors | internal-linking |
| Slow indexing on a large site | Crawl spent on low-value URLs | log-file-analysis |
| Filter and parameter URLs in the index | Faceted navigation without crawl control | faceted-navigation-parameters |
Example prompts for each skill
Each skill triggers on everyday wording. These prompts are good starting points:
- Indexing: “Search Console says 4,000 pages are Discovered, currently not indexed. Here is the export. Why, and what should we fix first?”
- Robots: “Write a robots.txt that keeps us in Google and ChatGPT search but opts out of AI training.”
- Sitemaps: “Audit our sitemap index and split it by template so we can see indexing per section.”
- Migration: “We move from Webflow to a headless CMS next month. Build the migration plan and redirect map.”
- Speed: “Our product template fails INP on mobile. Here is the PageSpeed report. What is causing it?”
- JavaScript: “Check whether Google and AI crawlers can see the text on our React pricing page.”
- Schema: “Write connected JSON-LD for our article template, author page and homepage.”
- Logs: “Here are 30 days of Nginx logs. Where is Googlebot spending its crawl?”
What the agent needs from you
Skills work from evidence, so results improve with the data you share. The most useful inputs are:
- Google Search Console exports: Page indexing, Sitemaps, Crawl stats and Core Web Vitals reports.
- A crawl export from Screaming Frog, Sitebulb or a similar tool, with status codes, canonicals and inlinks.
- Server or CDN access logs for log file analysis, with personal data handled under your privacy policy.
- The list of pages that make money, and the dates of recent releases or migrations.
Without them the skills still audit what is public, such as robots.txt, sitemaps, rendered HTML and PageSpeed field data, and say which findings would change with more data.
What an agent cannot do in technical SEO
An agent with these skills diagnoses and plans; it does not change your site unless you give it access and approve the change. It cannot see Search Console or your logs unless you export them or connect them, and it cannot promise rankings: each skill says what a fix removes or enables and which metric to watch, never that traffic will rise. Decisions with business risk, such as removing pages or blocking a crawler, stay with you.
Frequently asked questions
How do I load the .md files into Claude Code or Codex?
Put each file in a folder named after the skill and rename it SKILL.md, for example ~/.claude/skills/xml-sitemaps/SKILL.md for Claude Code or ~/.agents/skills/xml-sitemaps/SKILL.md for Codex. The zip download already has this structure.
Are the skills up to date with Google's current guidance?
Version 1.0.0 was checked against Google Search Central and web.dev in October 2026, including the 2025 removal of several rich result types. Rules that change often carry a date and tell the agent to re-check the official page.
Do these skills cover AI search and AI crawlers?
They cover the technical side: allowing or blocking AI crawlers in robots.txt and making sure content is in server-rendered HTML. Getting cited in AI answers is covered by the separate AEO & GEO skill set.
Can I use them with smaller or local models?
You can, but results depend on the model. The skills are long and rule-heavy, and smaller models follow them less reliably. Test on a known site before trusting the output.
Will the skills fix soft 404s or redirects automatically?
No. They find the problem, explain the cause and give you the fix, such as a redirect map or server rules. Applying it is a separate step that you or your developer approve.
Can I adapt the skills for my team?
Yes, under CC BY 4.0. Add your tools, thresholds and templates, keep the credit notice at the end of each file, and link back to this page if you publish your version.
Sources and more marketing skills
- Google Search Central documentation
- Web Vitals, web.dev
- Simplifying the search results page, Google Search Central Blog, June 2025
- RFC 9309: Robots Exclusion Protocol
- Agent Skills specification
Checked on 9 October 2026. For AI crawler policy and citations, use the AEO & GEO skills. For keyword research, briefs, writing and refreshes, use the Content and On-Page SEO skills. See every subcategory on the Marketing Skills-md page, or read how I approach this work on my technical SEO page.
