# Build my own fashion retail store on Crystallize, like Fashion Universe

I want a storefront for my business that works like **Fashion Universe** (https://fashion-universe.superfast.shop), a demo store built on Crystallize: Ten brands, each a style tribe: sign in as a shopper and the store re-ranks to their taste — with shoppable looks, colourways and sizes, and the supply chain behind every garment.

The content model and the wiring below are proven in that store: keep them for the features I want, and rename things to fit my trade. If a feature doesn't fit my business, leave its parts out rather than forcing it. Everything I see is mine to decide: brand, colours, typography, layout, copy and pages. Don't copy the demo's look; build my brand.

What the demo does: vector personalisation, shoppable content, campaigns, video, large variant sets, supply chain and co₂e, multiple markets, multi-currency, sale price lists. It is B2C, in English, Norwegian, Swedish, Dutch; my markets and languages may differ.

## How to work with me

- You need to run commands, edit files and use MCP tools. If you can't (for example in a plain chat), tell me, and suggest I paste this prompt into Claude Code, Cursor or another coding agent instead.
- Ask your questions a few at a time (three to five), in the order of the steps below, and suggest a sensible default for each so I can just say yes. Ask each thing once, even where two lists overlap, and ask the ones that change the build first. Don't start a step before the one before it is done.
- The technical detail below is for you. Talk to me in plain words, and explain a choice only when I need to make it.
- Keep the folder empty until step 5, apart from `.env.local`.
- Never ask me to paste an access token secret into the chat, and tell me not to paste a filled-in command or its output either. Tell me which command to run or which file to put it in, and I'll do it.
- Before you create or change anything in Crystallize, show me the plan (shapes, pieces, topics, price variants, markets) and wait for my yes. Before an import, show me a sample of five items.
- Use the Crystallize skills (the `skills` MCP tool, or the use-crystallize plugin) for how-to: `content-model`, `information-architecture`, `taxonomy`, `data-creation`, `mass-operations`, `pricing`, `query`, `mutation`, `js-api-client`, `responsive-images`, `payments`, and when this store needs them `subscriptions`, `bookable-resources`, `vector-ranking` and `permissions`. Where this prompt and a skill disagree, the skill wins. Check the live schemas with the MCP instead of guessing field names.
- When something I asked for isn't possible in Crystallize the way I pictured it, say so and offer the closest thing that is.
- **The storefront never reads from the Core API on customer-facing pages.** Products, public prices, stock and content come from the Discovery API and the Catalogue API; confidential prices (negotiated B2B price lists) from the Catalogue API on the server.
- **Use the Shop API for everything about customers:** carts, checkout, customers, orders (including orders created directly, such as renewals), order meta, pipeline stages, payments and subscription contracts. Take the customer identifier from the server session, never from the browser. The Core API is for setup scripts, back-office tools, scheduled jobs and what the Shop API can't do, always on the server and never once per page view.

## Step 1: Crystallize tenant, tokens and MCP

Ask me:
1. Do I have a Crystallize account and a tenant for this store? If not, I sign up for free at https://app.crystallize.com/signup and create an empty tenant. Ask for its **tenant identifier**.
2. Do I have access tokens? If not, tell me: in the Crystallize App, go to **Settings → Access Tokens → Generate a new token**, name it, and keep the ID and the secret (the secret is shown once). A token acts with its user's role, so while we build, that user needs to be Tenant Admin (or have a role that can write shapes, pieces, topics, items and prices and run mass operations). Once the store is built, switch the MCP to a token from a read-only user.
3. Is the Crystallize MCP connected, with write access? Check that you have its write tools (`run-mass-operation`, `mutate-core`), not only the read tools (`tenant-overview`, `fetch-content-model`): with only the read tools, it was added without `?exposeWrite=true`. If it's missing, have me run this in my terminal with my own token, then restart you:
   ```bash
   npx add-mcp "https://mcp.crystallize.com/mcp?exposeWrite=true" \
     --header "X-Crystallize-Access-Token-Id: <token id>" \
     --header "X-Crystallize-Access-Token-Secret: <token secret>"
   ```
   If the MCP can't be connected in my tool, say so and fall back to scripts that call the Crystallize APIs with the tokens from `.env.local`.
   In Claude Code, also suggest the Crystallize skills: `/plugin marketplace add crystallizeapi/ai`, then `/plugin install use-crystallize@crystallize-ai`. The plugin brings its own read-only Crystallize MCP entry with placeholder credentials: keep using the one added above (and add `&exposeSkills=false` to its URL once the plugin's skills are installed).
4. Confirm the connection with `tenant-overview`, and tell me what's already in the tenant. If it isn't empty, ask whether to build next to what's there or in a fresh tenant.

The storefront needs the tenant identifier and its own credentials: an access token pair for the Shop API (server only), and a static auth token if Discovery and the Catalogue API are secured. Don't reuse the admin build token in production. Put them in `.env.local` (have me fill in the secrets) and make sure `.env*` is in `.gitignore`.

## Step 2: my business and my brand

Ask me:
- What I sell, who buys it, and what makes us different. My brand name and a one-line pitch.
- My markets, currencies and languages, and my VAT/tax setup.
- Where my product data lives today: a spreadsheet or CSV, an export from Shopify, WooCommerce or another platform, a PIM or ERP, my current website, or nothing yet. Where my product images are.
- My brand: logo (SVG if I have it), colours, typefaces, tone of voice, and two or three sites whose look I like. If I have no brand guide, propose a direction from my answers and show it before building pages.
- Where it should run: my own domain, and hosting (suggest Vercel for Next.js).

Then ask what is particular to this kind of store:

- One brand or several? If several, what style segments (tribes) do my shoppers belong to?
- My variant axes (colour × size, wash, length) and size systems, and whether I have size guides.
- My product families and the specs shoppers filter on (denim fit and rise, outerwear membrane and fill power, heel height…).
- How I do markdowns: a was/now price per variant, or separate price lists?
- Do I have lookbook or campaign photography? Who places the hotspots: me, or you from my notes on what's in each photo?
- My warehouses and physical stores, and whether I offer click & collect.
- What I publish about materials and supply chain: composition, certifications, factories, CO₂e.
- My payment provider, and my order and return flow.
- Do I want the store to re-rank itself per shopper? Can I share margin, sales, ratings and return rates to rank on?

## Step 3: the content model

Create this in my tenant with the MCP, renamed to fit my trade, after I have approved the plan. Keep the structure: it is what the storefront's features depend on.

Build in dependency order, since mass operations run in sequence with no rollback: pieces and shapes (empty first, then their components), topic maps (at most 30 topics per `topic/create`), price variants, markets and VAT types, the folder tree (two to four levels, five to twelve per level), and only then items. Use lowercase-hyphen identifiers. Decide now which fields are translated and which are discoverable. Restrict every item relation with `acceptedShapeIdentifiers`. Never add price or stock components to a shape: variants have them built in.

Everything the storefront shows must be discoverable; translate the text components if I sell in more than one language.

- **product** (product): one style, with variants colour × size.
  - `tagline`, `summary` (rich text), `story` (paragraphs), `highlights` (repeatable chunk: title, text, image).
  - `brand` relation → brand (exactly one), `line` relation → product line, `style-number`, `season` selection, `launch-date`.
  - Pieces: `material`, `size-fit`, `seo`.
  - `specs`: a component choice of one typed spec piece per family: denim, apparel, outerwear, activewear, swim, footwear, accessory.
  - `videos`, `complete-the-look` relation → product (max 8), `services` relation → service (max 4).
  - Ranking signals as numerics: `margin`, `sold-30d`, `rating`, `review-count`, `return-rate`, `campaign-boost`.
  - Variant attributes `colour` and `size`. Variant components are plain fields only: `gtin`, `colour-family` selection, `colour-code`, `wash` selection, `size-order` (numeric sort key).
  - The first size of each colour carries all of that colourway's images and its video; the other sizes carry one image.
- **material** piece: composition (repeatable chunk: part, fibre, percent, certification), fabric, fabric weight, technologies, care (selection), certifications, recycled and organic share, origin, supply chain (repeatable chunk: role, relation → factory), CO₂e, water, traceability URL, sustainability text.
- **size-fit** piece: size system, fit advice, model height and size, notes, relation → size guide.
- **look** (document): headline, text, `images` (at least one, with hotspots), video, `products` relation → product (1 to 8), campaign, credits.
- **campaign** (document): brand, season, start and end, headline, hero, gallery, products, looks, call to action.
- **brand**, **product-line**, **technology**, **size-guide**, **factory** (country, city, certifications, workers) documents.
- **service** (product): hemming, repair, gift wrap.
- **landing-page** (document): a `blocks` component multiple choice of page-builder pieces: hero, product grid (curated, category, topic, personal or new), campaign banner, look grid, brand strip, category tiles, tribe picker, editorial split, USP bar, video.
- Folders: `category` and `section`. Catalogue roots: shop, brands, lines, campaigns, looks, factories, technology, pages, services. `/shop/<group>/<type>` mirrors the category topic map and is gender-neutral; women and men are storefront routes filtered by the gender topic (women = women OR unisex).
- Topic maps: brand, tribe, category (group → type), gender, colour, material, fit, occasion, weather, style, price tier, sustainability, season, offer (`/offer/sale`), image type.
- Vector vocabularies for taste ranking: `style` (tribe, style, brand), `wardrobe` (category, occasion, weather, gender), `palette` (colour, material, fit), `value` (price tier, sustainability).
- Pricing (the pricing skill's convention): prices excluding VAT; per currency a `retail-<cur>` price variant, always set, and a `sales-<cur>` price variant set only on marked-down variants. Show a strikethrough when sales is lower than retail. Sale items also get the `/offer/sale` topic (a filter on the sales price existing works too).
- Stock locations: `default` (web) plus one per store for click & collect.
- Order pipelines: Orders (new, picking, shipped, delivered, cancelled), Returns, and one click & collect board per store.

## Step 4: my data

Import my products and content with mass operations, mapping my data onto the model: validate each file with `build-mass-operation`, run it with `run-mass-operation` and follow it with `get-mass-operation-status`. Read the operation logs, not just the task status: a task can finish as complete with failed operations, and there is no rollback. Give every upsert a `resourceIdentifier` so a re-run updates instead of duplicating, and chunk large imports. Start with a small batch, check it in the Crystallize App with me, then run the rest.

Publish every imported item in each language: the storefront only sees published versions (in a mass operation, `item/publish` needs real `itemId`s). Import images from URLs with `copyRemoteAsset`, or upload them (presigned upload, then `registerImage`). Renditions are generated in a queue: after a large import, republish once they exist, and have the storefront fall back to the original image URL while `variants` is empty. Before building pages, query Discovery once; if the tenant isn't ignited yet, run `igniteDiscoApi` (with `stacks: opensearch` if we use vector ranking), wait for the task to complete, and allow a few minutes. If I have no data yet, create a small, clearly labelled placeholder set (ten or so products) so we can build the pages, and remind me to replace it.

- The demo's data comes from the brands' own sites, rewritten in its own words. Stock and ranking numbers are generated.
- Build order: tenant → model → topics → media → catalogue → marketing (campaigns, looks) → translations → pages → vectors → customers.
- From me: products with colourways, sizes, SKUs and GTINs, and prices per currency; packshots and on-model images per colourway, and product videos; look and campaign photos with which product and colourway is where; size guides, composition, care, origin and factories; brand logos and hero media; and, for ranking, margin, sales, ratings and return rates.
- Videos: `generatePresignedUploadRequest(type: MEDIA)` → upload → write `{ key, title }` on the videos component (`copyRemoteAsset` is images only). Crystallize transcodes them to HLS and DASH in about a minute.

## Step 5: the storefront

- Next.js (App Router) on Vercel, with plain `fetch` GraphQL clients. Routes are prefixed by language; unknown paths resolve the translated Crystallize path through Discovery.
- **Discovery API** for every read: browse with topic facets, `rankBy`, and `context: { userTaste }`; prices per price variant; stock per location.
- **Shop API** for bag and checkout:
  - The server exchanges the tokens for a JWT at `/auth/token`; the browser only holds the cart id in an httpOnly cookie.
  - `hydrate` all lines with `context.price { currency, selectedVariantIdentifier: sales-<cur>, fallbackVariantIdentifiers: [retail-<cur>], compareAtVariantIdentifier: retail-<cur>, pricesHaveTaxesIncludedInCrystallize: false, taxRate, decimals: 4 }`.
  - Line meta carries the product's topic paths, brand, size and colour. Hemming is a service line; the inseam goes in the garment's meta.
  - Checkout meta (market, language, delivery, store, gift wrap) goes on the cart with `hydrate(input: { meta })` and the customer with `setCustomer`; then `place` → `/order` `createFromCart(id, input: { pipelines: [{ identifier, stage }], stockLocationIdentifier })`, into Orders or the store's click & collect board. Later changes use `/order` `setMeta(id, meta, merge: true)`.
- **Shoppable looks with native hotspots:**
  - Write the hotspots in setup with Core `updateImage(key, language, input: { showcase: [...] })` (repeat per language if needed): `showcase: [{ hotspot: { x, y }, itemIds: [productId], skus: [first size of the colourway], meta: [{ key: "colourway", value }] }]`. x and y are fractions (0–1) of the image, at the centre of the garment.
  - Read them back from Discovery as `images { showcases { hotspot meta items { … } variants { sku attributes price images } } }`.
  - Draw dots at those positions (adjusted for cropping); each opens a card with price, was-price and a link to the product in that colourway.
- **Taste per shopper:** on the server, read the shopper's orders from the Shop API (`orders(customerIdentifier)`, identifier from the session) and build a taste from the topics on their order lines (older orders count less; returns count less). Pass it as `context.userTaste` (weights keyed `dimension:value`, with `magnitude` = the square root of the sum of squared weights) and rank with one `tasteCosine` term per vocabulary (`from: userTaste`) plus `fieldBoost` on sales, margin, rating and campaign boost, and a negative-weight `fieldBoost` on return rate. `tieBreaker` is required; don't pass `sorting` with ranking; page with `skip` and `limit` inside the rerank window (500 by default); leave `context` out entirely when there is no taste yet. Probe `__type(name: "RankByInput")` first: ranking is enabled per tenant.
- Env: `CRYSTALLIZE_TENANT_IDENTIFIER`, `CRYSTALLIZE_ACCESS_TOKEN_ID`, `CRYSTALLIZE_ACCESS_TOKEN_SECRET`, `NEXT_PUBLIC_SITE_URL`.

Build my design, not a demo's: my typefaces, colours and tone, with pages that suit my products. Show me the home page, a category and a product page early, and adjust the design with me before building the rest.

Every page is built for search engines, answer engines and AI agents from the start, not added at the end:
- **SEO:** server-rendered HTML, one `<h1>`, a unique title and description, canonical URLs, `hreflang` per language, a sitemap and `robots.txt`, and clean, translated paths.
- **Structured data:** JSON-LD on every page that has a subject: `Organization` and `WebSite` (with a `SearchAction`) on the home page, `Product` with `Offer` (price, currency, availability) on product pages, `BreadcrumbList` on categories and products, `Article` or `Recipe` on content. Generate it from the same data as the page.
- **GEO, for answer engines and agents:** `/llms.txt` (an H1, a summary, links to every section), `/llms-full.txt`, and a Markdown twin of every page (its URL plus `.md`, or `Accept: text/markdown`), with prices, stock and facts written out in plain sentences.
- **Agents can act, not only read:** register the store's actions (search, add to cart, check availability) with WebMCP (`navigator.modelContext.registerTool`, or annotated forms), and keep the accessibility tree clean: semantic HTML, labelled controls, real buttons and links.
- **Fast and stable:** responsive images from Crystallize, no layout shift (reserve space for images and late content), little client JavaScript. Aim for 100 in every Lighthouse category (Performance, Accessibility, Best Practices, SEO; heavy 3D or video pages may score lower on performance) and pass every Agentic Browsing check.

## Step 6: run it, then ship it

Run it locally and walk me through each feature above with my own data. Fix what I find. Before you call it done, run Lighthouse on the home page, a category and a product page (`npx lighthouse <url> --only-categories=performance,accessibility,best-practices,seo,agentic-browsing`), validate the JSON-LD (https://validator.schema.org), open `/llms.txt` and a page's `.md` twin, and fix what falls short. Deploy only when I ask: set the same environment variables on the host, point my domain, and give me the live URL.

## Watch out for

- Discovery field names are generated (`{componentId}_{subfield}_{type}`, e.g. `sold_30d_number`), and hit fields can be cased differently (`campaignBoost`). Introspect `TenantRankByField`, the filter inputs and the hit type instead of guessing.
- Setting item taste empties variant components on the draft: `setItemTaste` → rewrite the variants (one update replaces them all) → `publishItem` per item and language → `igniteDiscoApi(stacks: opensearch)`, poll the task until complete, then wait. Without `stacks: opensearch` there are no vectors, and no error either.
- Updating with `components` replaces all components in that language; translate with `updateComponent`, one at a time.
- `copyRemoteAsset` handles images only, and can return a key even when the copy failed. Wait for every copy task, then check the keys resolve. Don't call `registerImage` after a copy.
- Image renditions are generated in a queue: fall back to the original URL, and republish once they exist. Ask for specific renditions (webp, a width range) so a page of cards stays light.
- Number facets need `boundaries`. Discovery rejects `context: null`.
- Content chunks on variants aren't published; keep variant components plain.
- Create and change orders through the Shop API; editing an order in Core adds a duplicate to the Shop list.
- Don't use a per-SKU price list for the sale: pricing every product for everyone that way is too slow. Use the `sales-<cur>` price variants and the sale topic.
- Don't invent facts about my business (prices, stock, certifications, delivery promises). Ask, or leave a clearly marked placeholder.

And for every Crystallize store, from the skills:
- **Orders:** create and change them through the Shop API `/order` (`createFromCart`, `create`, `setMeta` with `merge: true`, `addToStage`, `setPayments`). Editing an order in Core adds a duplicate to the Shop API's list. Read a customer's orders with the identifier from the session, `limit: 100`, grouped by `coreId` (keep the newest). Seed order history through `/order` `create`, not Core `registerOrder`. The order id is the cart id; don't call `fulfill` after `createFromCart`.
- **Payments:** create the order from the payment provider's verified webhook, never from the browser, once per cart.
- **Cart meta** goes in `hydrate(input: { meta })`; `hydrate` is the whole cart, so send every line each time.
- **Images:** serve them straight from Crystallize (not through an image optimizer such as `next/image` in its default setup): a WebP `srcset` from the returned `variants` with an accurate `sizes`, falling back to the original URL while renditions are missing. Replace an image by uploading a new one, not with `registerImageRevision`.
- **Ranking (if the store ranks per shopper):** check that `__type(name: "RankByInput")` exists; pass `context` as a variable, with `userTaste` entries of `{ vocabulary, weights, magnitude }` (magnitude = the square root of the sum of squared weights); `tieBreaker` is required; don't combine `sorting` with ranking, and page with `skip` and `limit` inside the rerank window; introspect `TenantRankByField` for field names; leave `context` out when there's no taste; use `explain: true` only for tuning.
- **Bookings (if the store books):** durations are in seconds; the role needs the `bookingPolicies` permission; put the customer on the cart before `bookSkuItem`; every `hydrate` must resend each booked line with its window and unit, or the booking is cancelled; remove a booking by re-hydrating without it.

## Done when

- My tenant has the content model above with my products, prices and images in it.
- The storefront runs on my domain in my brand, and every feature I chose works with my data: we have clicked through each one together.
- Lighthouse scores close to 100 in every category and every Agentic Browsing check passes on the home, category and product pages.
- I know how to add a product, change a price and publish, in the Crystallize App.