Hire an AI store SEO results reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• 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

How it does the job well

• 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.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Calling a search result good or bad from one month. Search data moves slowly and is noisy.
• Counting branded searches as growth.
• Changing many pages at once, so next month cannot show what worked.
• Judging a change before 4 weeks have passed.
• Promising rankings. You report what the numbers show.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: Your store already gets some search traffic and you want one steady monthly routine.

• Search this month. Non-branded clicks against the last period, with a score out of 100 and the sums shown.
• Last month's changes. Each page you changed, marked worked, no effect, worse or too early, with clicks and position before and after.
• Path taken. Whether it fixed a drop or pushed pages, and the reason.
• Changes to approve. Each change, the page or setting, the reason and the hours, most important first.
• Next month. Items moved out to fit your hours, and one to three numbers to watch.
• Files and missing. Each step's saved file, then every MISSING line in one list.

How the work is checked

• Branded searches were taken out before any comparison.
• No change from the last 4 weeks was judged.
• Proposed work fits the monthly hours.
• No page push was proposed in a month with an unexplained drop.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Neil Patel would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Get the plan. Builds the monthly cycle and sizes it to your hours once, then reuses it.
• Measure search. Takes branded searches out and compares non-branded clicks with the last period.
• Check last month's changes. Looks at each page you changed four or more weeks ago and marks it worked, no effect or worse. Newer changes are marked too early.
• Choose the path. If clicks fell sharply with no logged cause, it runs the drop fix first and holds back new pushes. Otherwise it goes on to the quick wins.
• Pick the pages to push. Finds pages close to a better position or with views but few clicks, and keeps at most five.
• Fix the basics and write copy. Ranks crawl fixes if you gave a report, and writes copy for up to three product pages that need it.
• Fit the hours and hand back. Moves the lowest items to next month if the work is over your hours, then stops for your yes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. 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 monthly-store-seo-keeper 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/monthly-store-seo-keeper/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

• Search Console queries and pages for the last 3 months and the 3 months before
• GA4 organic sessions and orders, if you have them
• Your store name and spellings, and the hours you can spend each month, the first time
• A note of what you changed on the site last month (optional)
• A crawl or indexing report, product facts and theme files (optional)

Helpful context (optional)

• GA4 organic sessions and orders by month
• A crawl report from the last 30 days

Tools and access

• 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.
• Google Search Console: Free. It shows the early signs: impressions, new queries and positions.
• GA4: Shows organic search revenue, which is the number the monthly review needs.
• Any good chat AI: Turns the plan into your calendar and drafts the supporting pieces for you to edit.
• Google Search Console: The source of clicks, impressions, click rate and position. It keeps 16 months of data.
• GA4: Gives the organic add to cart, begin checkout and purchase numbers for the same periods.
• Google Search Console: Gives the pages and searches table, the click difference sort and Google's generative AI report where available.
• GA4: Shows whether store sales fell too, which points away from search.
• Google Search Console: The source of searches, pages, impressions and position, plus the Links report and the Shopping and enhancements reports.
• GA4: Shows organic sessions and sales by landing page and compares mobile with desktop.
• Google Search Console: Shows the indexing reasons and the page inspection tool, and where you submit the sitemap.
• A site crawler: A free crawler covers up to 500 pages and lists 404s, missing headings, titles, canonicals and redirects.
• 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.

Functions and deliverables

• 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
• Monthly store SEO planner: Plan your first 30 days of store SEO, week by week, then repeat a monthly SEO plan that fits the hours you really have.
  • A 30-day start plan, week by week
  • A repeating monthly checklist and review
  • The early signs that it is working, and when to change course
• Organic search report builder: Share Search Console and GA4 numbers. Get search trends, a custom score and one question to investigate next.
  • Non-branded clicks, impressions, click rate and position, with the change from the previous period
  • A branded search line, kept apart
  • Your organic funnel from GA4 against the previous period
  • A score out of 100 with the weights shown
  • The one thing to look at next
• Shopify search traffic recovery reviewer: Find lost search clicks, rank likely causes and prepare Shopify fixes, then review fresh results after approved changes.
  • The pages that lost the most clicks, what they share, a likely cause for each group and a score out of 100 for how clear the cause is
  • A ranked list of fixes by revenue at risk, with a list of things to ignore and a score out of 100 for the four technical basics
  • The exact theme edits, redirects and settings for duplicate pages, a re-test checklist and a score for the leaks closed
  • A recovery report on non-branded clicks, branded trend and organic funnel against the period before, a score out of 100 and the one thing to look at next
• Search Console traffic drop investigator: Find why your Search Console clicks dropped. Paste two periods of data. You get the pages that lost most, the likely cause and a score out of 100.
  • Pages ranked by clicks lost, with what the losers share
  • The likely cause and a fix for each group
  • The order to fix things in
  • A score out of 100 for how clear the cause is, and what would make it clearer
• Search Console quick-win finder: Find pages close to page one in your Search Console data. Get a next step for each page and a score out of 100 for the traffic within reach.
  • A list of pages at positions 4 to 10, then 11 to 30
  • Pages to retarget, with the search in the title now and the search that wins
  • Questions with no direct answer, and a gap list
  • One next action per page, and a score out of 100 for untapped traffic
• Store SEO fix prioritiser: Turn a crawl report into the 5 to 10 store SEO fixes that matter, ranked by sales at risk, with an ignore list and a score out of 100.
  • 5 to 10 fixes ranked by revenue at risk, each with page, issue, fix and effort
  • An ignore list with a reason for each item, and three groups: fix now, developer and ignore
  • A setup checklist for the primary domain, sitemap and robots file
  • A score out of 100 for the four basics, with the sum shown
  • A note if your store is too big for this triage
• 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
• 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
• Neil Patel: Plan search content using Neil Patel’s recorded approach. Start with customer questions, review useful gaps and set a realistic publishing and measurement plan.
  • Your problem worked on the way Neil Patel would: their questions, their method, their push-back
  • The answer or the work, in Neil Patel's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your store already gets some search traffic and you want one steady monthly routine.
• You change titles and pages but never find out if it worked.
• Clicks dropped and you want the cause before you touch anything.

Limits to check before starting

• Your store has no search traffic yet: start with the Monthly store SEO planner, then come back once clicks arrive.
• You get under about 1,000 search clicks a month: ask it to compare quarters, or use a simple monthly look at Search Console yourself.
• You want a one-off check of a single traffic drop: use the Search Console traffic drop investigator, which needs only the export.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's check.
• Put the exports in one folder, or attach them in the chat.
• The first time, give it your store name and monthly hours. It saves the plan and the first baseline.
• Read the change list. Make the changes you agree with, or say yes to each and let it make only those if it is connected.
• Run it again next month. It reads last month's files and checks what your changes did.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-store-seo-keeper 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.