Hire an AI SEO specialist
Give it your site address. You get a site audit ranked by what blocks ranking most.
What you give
- Your site address
- The pages that matter most and the searches you want them to rank for
- Your brand voice, or two titles you like (optional)
What you get
- A site audit ranked by what blocks ranking most
- A technical audit with the fixes in order
- On-page fixes for each key page
An example
Your pages rank on page three for searches you should own.
You ask: “Audit my website and fix the supported page and technical issues. Give me the changes, evidence, checks and a ranked follow-up list.”
You get back:
- Step 1: Site audit. Problems ranked by how much they block ranking, with what is indexed, what is duplicated and what ranks today.
- Step 2: Technical audit. Speed, crawl errors, mobile, redirects, sitemaps and robots rules, with each fix in the order that pays.
- Step 3: On-page fixes. For each key page, fixes to headings, content, images and links, based on the search it should win.
An example, not your task.
Words used here
- SEO: getting your pages found in search results
Hire this specialist
It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.
Related specialists
Skills and workflows for this job: Get found in search and AI answers
Details
Everything it can hand back
Your task sets the actual outputs. The specialist picks the methods that cover them.
- A site audit ranked by what blocks ranking most
- A technical audit with the fixes in order
- On-page fixes for each key page
- New titles, meta descriptions and schema markup, ready to approve
How it does the job well
- Fix crawling and indexing blockers first. A page that is not indexed cannot rank.
- Give each page one main search intent. Do not target the same query with two pages.
- Write titles of about 60 characters with the main term early, and descriptions that earn the click.
- Use structured data only for content visible on the page, and validate it.
- Judge changes on Search Console clicks and impressions over comparable periods.
- Write for one named audience and one action. Each asset has a single job.
- Use the customer's own words from reviews, calls or surveys before inventing language.
Mistakes it avoids
- Keyword stuffing, doorway pages or other tactics against search engine guidelines.
- Promising rankings or dates.
- Changing URLs without 301 redirects.
- Generic copy that could fit any brand.
- Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
- Calling a test winner before there is enough data.
What a good result looks like
An example, not your task: Your pages rank on page three for searches you should own.
- Step 1: Site audit. Problems ranked by how much they block ranking, with what is indexed, what is duplicated and what ranks today.
- Step 2: Technical audit. Speed, crawl errors, mobile, redirects, sitemaps and robots rules, with each fix in the order that pays.
- Step 3: On-page fixes. For each key page, fixes to headings, content, images and links, based on the search it should win.
- Step 4: Titles and descriptions. A title and meta description for each key page, in your voice, with character counts.
- Step 5: Schema markup. Code to paste for your main page types, with a line on what each piece tells search engines.
- Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.
How the work is checked
- Each issue has the URL, the evidence and the exact fix.
- Fixes are ranked by impact and effort.
- Changed titles, descriptions and markup are listed before and after.
- Each step passed its own checks, or the run stopped at the step that failed and says why.
- States which checks passed, failed or could not run, and names missing inputs.
These checks have not been run against a model yet. Your AI uses them to check its own work.
Capabilities
- Audit the site. Audits the whole site: structure, indexing, duplicates, what ranks, with problems ranked by impact.
- Audit the technical side. Checks speed, crawl errors, mobile, redirects, sitemaps and robots rules, with fixes in order.
- Tune each key page. Reviews each key page's headings, content, images and links against its search, and writes the fixes.
- Write titles and descriptions. Writes a title and meta description per key page, in your voice, within length limits.
- Write the schema markup. Writes schema markup for your main page types as code ready to paste, for you to approve.
How the role works
- Checks your task, context and available tools.
- Picks the methods needed and prepares a work plan.
- Carries out supported tasks, with each method's limits and review gates.
- Checks the real deliverables and corrects supported faults.
- Hands back files, evidence and unresolved gaps.
Your specialist's working setup
Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.
Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.
Use this specialist through MCP or the API
Call prepare_specialist with role_id seo-specialist only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.
For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.
Complete ZIP: Download base specialist. API: GET /api/v1/specialists/seo-specialist/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.
Inputs and helpful context
The specialist starts from the task brief. Only active methods require their inputs.
For the primary method, when used
- Your site address
- The pages that matter most and the searches you want them to rank for
- Your brand voice, or two titles you like (optional)
- Your site platform, such as Shopify or WordPress (optional)
- A search console export with dates, queries, pages, clicks and positions (optional)
Helpful context (optional)
- Search console export
- A crawl of the site
- Your platform's SEO settings screen
Tools and access
- Website or page files
- Search Console exports when available
- A browser or crawler for live checks
- Any good chat AI: Every step is a plan or a piece of writing.
- Your search console: Shows what searchers see and which pages have problems.
- A site crawler: Finds every page, redirect and error on a larger site.
- A markup validator: Checks the schema before it goes live.
- Claude, ChatGPT or Gemini with web access: It can open your pages and sitemap. Without web access, paste the text and titles.
- Claude Code: It can keep the keeper folder, read last month's files and run every step on a schedule.
- Google Search Console: Export queries and pages for the last 6 months, with clicks, impressions and position.
- Shopify: Title, listing and handle fields, a redirect on rename, and the notify-me and shop-similar buttons through apps or theme edits. You need a paid Shopify plan.
- Google Search Console: Free. Shows whether a product page gets impressions before you decide to rank or noindex it.
- Any good chat AI: Drafts the copy from your facts and checks the character counts.
- Shopify: Handles, redirects on rename, metafields for reviews and the Search and Discovery app for the grid are built in.
- Google Search Console: Free. Shows how the page performs in search after it goes live.
- Any good chat AI: Drafts the copy from your product facts and helps with the description-splitting code.
- A real browsing agent, such as Claude in Chrome: Only a real agent can show if a task can be finished. The chat AI reviews code and cannot. Claude in Chrome runs in the Chrome browser and needs a paid Claude plan, so check the current terms.
- Claude, ChatGPT or Gemini: Any of them can read your form code and write the fixes.
- Any chat AI: No code needs to run. Attach the template files from the skill folder if your tool accepts files.
Functions and deliverables
- Website SEO editor: Review search problems, rank fixes and draft page improvements, titles, descriptions and structured data for your site.
- A site audit ranked by what blocks ranking most
- A technical audit with the fixes in order
- On-page fixes for each key page
- New titles, meta descriptions and schema markup, ready to approve
- SEO reviewer: Get an SEO review of your site: pages that compete, keyword gaps, content fixes and technical problems, ranked by what to fix first.
- An overlap check: which pages compete for the same search, and which page should own it
- A technical review: crawling, sitemap, speed, mobile and page markup, with what to fix
- A keyword plan: terms grouped by what searchers want, each tied to one page
- Content fixes: title, heading and page changes for your main pages
- A ranked fix list by impact and effort, and the checks left for you to run
- Store SEO results reviewer: Review store search traffic, investigate drops and size page fixes to your available hours. Track earlier changes without promising rankings.
- Non-branded clicks against the last period, with a score and the sums
- A verdict on each change from last month, as worked, no effect, worse or too early
- A drop investigation, or up to five pages to push
- A change list to approve that fits your hours
- The numbers to watch next month
- Product page SEO builder: Build a product page SEO plan: a rank-or-not call, title, H1, page copy, image names, markup list and stock-out rules from your product facts.
- A rank, keep-live or noindex call with a reason
- Title tag, H1, address and search listing
- A page layout with short and long copy, a spec table and an FAQ
- Image names and alt text, a markup list and stock-out rules
- Collection page SEO builder: Build a collection page SEO setup: give it a collection, products and one keyword. You get the title, H1, URL, listing, copy, FAQ and links.
- Title tag, H1 and address, plus a search listing written to win the click
- A short description for above the grid and a long one for below it
- An FAQ, three featured reviews and a link plan
- Notes for splitting the description in Shopify
- AI search visibility reviewer: Check if an AI browsing agent can book, buy or sign up on your site. Get a task scorecard, the steps where it gets stuck and fixes.
- A scorecard per task that shows if an agent can find it, start it and finish it, and where it drops.
- A step-by-step friction map marked Pass, Degraded or Fail, with the cause of each failure.
- A fix list, each tied to a stuck point. Fixes are form markup, field changes or flow changes.
- WebMCP markup for forms that fit it, or a script outline for dynamic actions.
- A test sheet to run with a real browsing agent before and after your changes.
- SEO site auditor: Share the site, goals and target topics. It reviews accessible pages and signals, then ranks findings with evidence and limits.
- A ranked list of SEO issues
- Fixes for each issue
- Technical, on-page and content findings
- A correct schema check
- Technical SEO auditor: Share your site and crawl data. Get technical SEO issues and fixes in order.
- Findings across six layers
- Priorities for each issue
- Specific fixes
- A short list to do first
- On-page SEO tuner: Share a page and target search phrase. Review titles, headings, content, links, images, URLs and schema, then draft ranked fixes.
- Rewritten title and meta description
- Heading structure fixes
- Internal link suggestions
- Image, URL and structured data fixes
- Title and meta tag writer: Turn page details and keywords into title options, meta descriptions, and social tags with length checks.
- Title tag options
- Meta description options
- Open Graph and Twitter tags
- Length checks
- Schema markup writer: Share your page type and visible content. Get JSON-LD markup, missing-field checks and steps to test it before publishing.
- One JSON-LD block for each schema type that fits your page
- A table showing which types pass and which have missing fields
- A list of issues, each with the exact fix
- Steps to paste the code and test it in Google's Rich Results Test
- A final checklist to run before you publish
- Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
- A folder of eight plain files, from a start file for your AI to a claims list and a change log
- A tag on every fact, and every claim marked approved, pending or banned
- A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
- A short slice for your next step, if you name one
Tasks you can use it for
- Your pages rank on page three for searches you should own.
- You never set titles and descriptions and they show as "Home" and "Product".
- An agency sent you a hundred-row audit and you do not know where to start.
Limits to check before starting
- You only want a title and description for one page: use the Title and meta tag writer on its own.
- Your traffic comes from paid ads: use the Ad sales drop analyst to find out why results fell.
- Your search traffic fell after a change and you want the cause: use the Shopify search traffic recovery reviewer workflow.
Best way to use this role
Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.
- Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
- Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
- Paste your site address and the pages that matter. It audits the site and the technical side.
- Read the ranked fixes. Give the technical ones to whoever runs the site.
- Approve the titles, descriptions and markup, then publish them.
Read it as data
Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/seo-specialist for its role instructions and pinned sources.
This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.