Hire an AI Shopify product, menu and build planner

Everything it can hand back

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

• Each product's type, a variant table and a fill-in checklist
• Collections, filters and a short menu, with a click-depth check
• Product page sections matched to buyer doubts, with the settings to switch on
• A Claude Code kickoff prompt, a section-by-section plan and safe steps to publish

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

• 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 to try Claude Code on your Shopify theme but have never set up the products it would build around.

• Step 1: Products and variants. Each product's type, shared options, a variant table and a list of what is still missing.
• Step 2: Collections and menu. Tags, collections with rules, filters in order, a short menu and a click-depth check.
• Step 3: Product page sections. Each buyer doubt matched to a section, the proof that settles it and the settings to switch on.
• Step 4: AI build plan. A tools check, a safe theme copy, the Claude Code kickoff prompt, a section plan and publish steps.
• Hand-back summary. Each step's file, any step not run and every MISSING line in one list.

How the work is checked

• No product, price or variant is invented, and each gap is marked.
• The menu puts every product within two or three clicks of the home page.
• Every product page section answers a named buyer doubt and names its proof.
• The build plan works only on a copy of the theme and never on the live one, and each section has a review point.
• 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

• Set up products and variants. Picks a type for each product, builds the shared options, makes a variant table with price, stock, weight and photo, and lists what is still missing.
• Plan collections, filters and the menu. Fixes product type names and tags, makes a collection for each way shoppers look, picks the filters in order and checks every product is two or three clicks away.
• Plan the product page sections. Lists each buyer doubt, matches it to a section and the proof that settles it, uses the collections from step 2 to pick products to recommend, orders the page and lists the settings and proof still to collect.
• Get the safe AI build plan. Writes the Claude Code kickoff prompt, a section plan with a review after each, and steps that build on a copy of the theme and push it unpublished.

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 plan-your-store-pages-and-get-a-safe-ai-build-plan 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/plan-your-store-pages-and-get-a-safe-ai-build-plan/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 product list with prices, options, stock and what ships
• Your catalogue size and platform
• The doubts buyers have, and any proof you hold (optional)
• Your store domain, theme name and screenshots of sections you like (optional)

Tools and access

• Shopify: Variants, compare-at price and a continue-selling stock setting are built in.
• WooCommerce: Global attributes, five product types and bulk actions on variations are built in.
• Any good chat AI: Any current chat AI can build the table from your list.
• Shopify Search & Discovery: A Shopify app for filters and synonyms, with filters you can order by importance. Check its current price in the Shopify app store.
• Shopify: Smart collections, nested menus and a bulk editor for tags and types are built in.
• Any good chat AI: Any current chat AI can sort a product list into tags and collections.
• Shopify: Metafields, sticky add-to-cart in many themes, variant media grouping and collapsible tabs depend on the theme but are built into the platform.
• Any good chat AI: Any current chat AI can map doubts to proof and order the sections.
• Claude Code: It reads the theme files and builds sections from your plan.
• Shopify CLI: It pulls the theme to your computer, previews it and pushes it back as unpublished.
• Shopify theme editor: Where you edit text, images and section order after the build and check mobile view.

Functions and deliverables

• Shopify product, menu and build planner: Share product facts and buyer questions. Get variant tables, collections, menus, page sections and an AI coding brief.
  • Each product's type, a variant table and a fill-in checklist
  • Collections, filters and a short menu, with a click-depth check
  • Product page sections matched to buyer doubts, with the settings to switch on
  • A Claude Code kickoff prompt, a section-by-section plan and safe steps to publish
• Product and variant setup planner: Plan your product variants before you enter them. List what you sell and get a product type, a variant table and a fill-in sheet for each.
  • A product type for each item and a shared option list
  • A variant table: option combination, SKU, price, stock, weight and image
  • Categories, tags, and upsell and cross-sell links
  • One sheet per product to fill in, and a list of what is still missing
• Collections and menu planner: Plan your store collections and menu: give it your product list and get tags, collections, filters, a short menu and search settings.
  • A tag and product type list to use everywhere
  • Collections with the type (manual or smart) and the rule for each
  • A filter list, in order of importance
  • A menu tree up to three levels, a click-depth check and search settings
• Product page section planner: Plan your product page sections from buyer doubts. Give it your product and price. You get ordered sections, Shopify settings and proof to collect.
  • An ordered list of sections, with what each one proves
  • The Shopify settings to switch on or off
  • A list of dynamic fields (metafields) to create
  • The photos and proof to collect
• Shopify theme build planner: Share a Shopify store, products and design references. Get an asset checklist, Claude Code kickoff prompt and theme build plan with review points.
  • An asset folder checklist
  • A kickoff prompt for Claude Code
  • An ordered section plan with a review checkpoint after each
  • A final polish prompt, publish steps and a log of which copy was edited
• 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 to try Claude Code on your Shopify theme but have never set up the products it would build around.
• Your last theme edit looked generic, with made-up products and a menu that did not fit.
• You are worried an AI edit could break the live store.

Limits to check before starting

• Your store already has its products and menu set up: use the Landing page design planner to plan a single page.
• You sell on WooCommerce or another platform: stop here. Steps 3 and 4 are for Shopify only.
• You need one small text change: use your store's own theme editor.
• You want a page that matches one ad: use the Ad-matched landing page writer.

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".
• Give real products with real prices. Without them, the build will invent some.
• Before step 4, check that you have a paid Claude plan that includes Claude Code, plus Node, Git and the Shopify CLI. You also need a Shopify store you can sign in to.
• Run the build on a copy of your theme only. Publish it yourself after you check it on your phone.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/plan-your-store-pages-and-get-a-safe-ai-build-plan 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.