Hire an AI store speed reports and fix review

Everything it can hand back

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

• Your field score now and last month, and which metrics moved
• A keep, remove, delay or one-page-only call on each new app
• A ranked fix list with effort, risk, who does it, and the gain in orders as a range
• Code for a duplicate theme where a fix needs it
• A sale-day checklist when a sale is near

How it does the job well

• Work from the real catalogue, prices, stock and policies. Check variants and currencies.
• Judge changes by contribution margin, not revenue alone.
• Change one thing at a time on a live store and keep a way to roll back.
• Keep product claims consistent with supplier data and labels.

Mistakes it avoids

• Chasing a perfect 100. Stop when the real-user numbers pass on the pages that get paid and organic traffic.
• Blaming a fix that is under 28 days old.
• Delaying or removing a tracking tag.
• Editing live products, prices or themes without approval or a backup.
• Ignoring shipping, returns and fees when judging profit.
• Copying competitor listings.

What a good result looks like

An example, not your task: You want your store's speed checked the same way every month.

• This month. Your field score now and last month, and which speed metrics moved, page by page.
• Path taken. Whether it held, checked apps, or ran fixes, and the reason.
• Apps. Each new or removed app with a keep, remove, delay or one-page-only call.
• Fixes to approve. A ranked list with page, owner, effort, risk, gain in orders as a range, and how to check it.
• Sale check. A speed budget and checklist if a sale is within 30 days.
• Look again. The date to re-check, since real-user data takes about 28 days to move.

How the work is checked

• Pass or fail is judged on field data, not on one lab score.
• Last month's fixes under 28 days old were judged on lab runs and marked that way.
• Tracking tags were left alone.
• Every code change is for a duplicate theme and has a test list.
• 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

• Read the reports. Scores real-user data, reads each page, and names the cause on the lab run.
• Compare with last month. Shows the change in score and in each metric, and lists apps that are new or removed.
• Choose the path. If all is good and nothing is new, it stops with no work. If an app is new or the score fell, it checks the apps first.
• Run the fixes that match. Leftover code after a removal, heavy features, the hero image, page jumping or blocking scripts. Only the ones that apply.
• Rank by money. Prices each fix in orders a month as a range, and ranks by gain per hour. The range is your sessions times your conversion rate times an assumed lift, from vendor-quoted figures the ranker names or from a lift you set. It is a rough estimate, not a promise.
• Check for a sale. If a sale is within 30 days, it adds a speed budget and a checklist.
• Save the baseline. Stores this month's numbers and app list so next month can compare.

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-speed-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-speed-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

• PageSpeed results for the homepage, a collection page and a product page, mobile and desktop. Include the real-user (field) score, the LCP, INP and CLS bands, the lab score and its main findings
• Your installed apps and theme app embeds, as a screenshot or a pasted list with one name per line
• Monthly sessions by page type, conversion rate and average order value
• Theme files, if you want code fixes (optional)
• What changed this month, such as apps added or removed with their dates, and any sale date (optional)

Helpful context (optional)

• A list of every app you added or removed since last month, with dates
• Your sale and campaign dates for the next 30 days

Tools and access

• Claude Code: It can keep the speed folder, read last month's baseline and edit a duplicate theme folder.
• PageSpeed Insights: Run it on the same three pages each month. It gives real-user data and lab diagnostics.
• Shopify: The app list, the theme app embeds and a duplicate theme to test on.
• Google PageSpeed Insights: Free. It shows real-user (field) data and a lab test for any public URL, which is exactly what this skill reads.
• Google Search Console: Its Core Web Vitals report groups your pages by status over time, so you can check the 28-day picture.
• Shopify online store speed report: Shows the speed score Shopify builds from your homepage, a collection and a product page.
• Google PageSpeed Insights: Its third-party and blocking time sections show which scripts cost the most.
• Shopify admin Apps and theme editor: The Apps list and the theme editor's App embeds show what is installed and what is switched on.
• Any good chat AI: Reads your screenshots and matches scripts to apps. No code or paid tool needed.
• Shopify theme editor and code editor: Lets you duplicate a theme, download it, and preview a copy before it goes live.
• A code editor with search across files: One search covers every file in the theme folder. Any free editor works.
• Google PageSpeed Insights: Shows how heavy a page is and which files cost the most.
• A heatmap tool such as Microsoft Clarity: Free click maps show whether shoppers use quick view, sliders and popups.
• Shopify theme library: Lets you try a free default theme on a copy before you decide.
• Google PageSpeed Insights: Gives the problems and lab numbers to feed in, and the real-user data to measure against.
• Shopify analytics: Gives visits by page, conversion rate and order value, the inputs that turn seconds into orders.
• Google Analytics (GA4): Splits mobile and desktop conversion and bounce, so you can check a speed gain against your own data.
• Google PageSpeed Insights: Names the LCP element and lets you measure the fix with three runs.
• Chrome DevTools: Throttle to slow 3G and 4G, switch the cache off and watch the image arrive.
• Shopify theme editor: Duplicate a theme, edit the copy and preview it before you publish.
• Google PageSpeed Insights: Lists the shifting elements and a loading filmstrip for each page.
• Chrome DevTools: The inspector shows each image's rendered size, and the performance trace shows when elements move.
• Google Search Console: Its Core Web Vitals report shows when real-user layout shift passes.
• Google PageSpeed Insights: Lists render-blocking requests and blocking time, and lets you average three runs.
• Chrome DevTools: The console shows errors after each change, and the network tab shows when each script loads.
• Google PageSpeed Insights: Gives the scores and page weights to set limits from.
• Shopify online store speed report: Tracks your store's speed score over time.
• Google Search Console: Shows real-user results after the sale.

Functions and deliverables

• Store speed reports and fix review: Review store speed and app changes. Get ranked fixes, draft code where supported and clear checks before anything goes live.
  • Your field score now and last month, and which metrics moved
  • A keep, remove, delay or one-page-only call on each new app
  • A ranked fix list with effort, risk, who does it, and the gain in orders as a range
  • Code for a duplicate theme where a fix needs it
  • A sale-day checklist when a sale is near
• Store speed report analyst: Share PageSpeed reports for key pages. Get field scores where traffic allows, lab clues and three fixes.
  • A real-user (field) against lab verdict for each page and metric
  • A field score out of 100, with the sum shown
  • The element that causes the slow load and the page shift on each page
  • Your first three fixes, what to retest and when
• Store app script reviewer: Give it your apps and speed report. Get each app marked keep, remove or delay, and a score.
  • A table with each app, what it loads, which pages need it, the verdict and the reason
  • A score out of 100 for your apps, now and after the changes, with the sum shown
  • A list of apps to uninstall, with a follow-up for the leftover app code finder
  • A list of apps to delay, for the theme script and style loader
  • A rule for the next app you install
• Leftover app code finder: Find leftover app code in your Shopify theme. Give it your theme files and removed apps. You get each file and line to delete, plus a clean score.
  • A list of files and line numbers that mention each removed app
  • A safe edit plan: delete or comment out, one change at a time
  • Unknown scripts you should ask someone about
  • A cleanliness score out of 100, now and after the edits, with the sum shown
• Slow website feature review: Find which sliders, popups and videos slow your store. Give it your pages. You get a keep, change or remove call on each, and a lightness score.
  • A list of heavy features with what each costs, and keep, change or remove
  • A replacement for each (static hero, lite video embed, thumbnail)
  • Theme advice
  • A score out of 100 for how light your pages are now, with the sum shown, and a projected score after the changes
• Website performance fix ranker: Rank your store speed fixes by orders gained per hour of work. Give it your audit problems and sales numbers. You get a plan for this week and next month.
  • A ranked fix list with expected gain as a range, effort, risk and who does it
  • The money at stake written as orders and revenue per month
  • A plan: top three this week, next five next month, the rest parked with a reason
  • What to measure before and after each fix
• Hero image loading fixer: Fix a slow hero image on your store. Give it your PageSpeed result and theme code. You get edited image code, a preload line and size targets.
  • The edited image tag and section code, with eager loading and high priority
  • A Liquid loop that loads only the first item eagerly
  • A preload line for the head, per template
  • Compression and size targets for that image, and a test list
• Layout shift fixer: Fix layout shift on your store. Give it your PageSpeed CLS report and theme code. You get the jumping element, its cause and the CSS fix.
  • The element that shifts and its cause
  • CSS or theme changes: reserved space, image sizes, a closer fallback font
  • Test steps and the date to recheck real-user data
• Shopify script and style loader: Share your Shopify theme, app embeds and fonts. Get safer load rules and code changes for scripts, styles and fonts.
  • Code that holds chosen scripts back until the first scroll, tap or key press
  • An edited tag for each script and stylesheet, with the reason
  • Font rules with swap and a close fallback
  • Reserved space for widgets that load late
  • A list of what was delayed, what was left alone and why
  • A test for every change, and how to undo it
• Store website speed reviewer: Plan your store's speed budget before a sale. Give it your speed results and sale date. You get limits, a test routine and a pre-sale checklist.
  • A speed budget: maximum page weight, minimum scores, maximum outside scripts
  • A monthly and after-change testing routine
  • A pre-sale checklist, with an app freeze date
  • A plan for what to do if traffic overloads the site
• 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

• You want your store's speed checked the same way every month.
• You add apps often and want to know which ones cost you speed.
• A sale is coming and you want the store checked beforehand.

Limits to check before starting

• You want a one-time speed check with no monthly comparison: use the Store speed report analyst on its own.
• Your store already passes everywhere and rarely changes: skip a month when last month said no work, nothing changed and no sale is due, then run it again the month after.
• You need someone to edit your live theme or remove an app: ask a developer, because this agent only writes code for a copy of your theme.
• Your store gets under about 1,000 sessions a month: there is too little data to price a fix in orders. Run the Store speed report analyst once instead.

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 (a paid tool; PageSpeed Insights is free), add it as a skill or save it in .claude/agents, then ask it to run this month's speed check. In a free chat, paste last month's baseline and save the new one yourself.
• Run PageSpeed Insights on the same three pages each month, three times each if you can, and give it the results with your app list.
• The first month it saves a baseline. Every month after, it compares against it.
• Read the list. Test each change on a duplicate theme, then say yes to the ones you want.
• Run it again next month. Wait 28 days before judging a fix on real-user data.

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-speed-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.