data-creation

Generates formatted Crystallize PIM catalogue items as json.itemData payloads from spreadsheet or user-supplied data.

4|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/CrystallizeAPI/ai --skill data-creation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-creation
Source: https://github.com/CrystallizeAPI/ai/tree/main/use-crystallize/skills/data-creation
Command: npx skills add https://github.com/CrystallizeAPI/ai --skill data-creation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual effort of creating and formatting large batches of realistic Crystallize PIM catalog items by generating the exact json:itemData payload the item-import grid expects.

Core Features & Use Cases

  • Bulk sample/demo item generation: Create 5–10 demo items from scratch or generate one item per provided spreadsheet row.
  • Correct shape mapping: Transform user-supplied data into component values that match the target shape’s types, options, units, and constraints.
  • Folder-aware placement: Assign item locations using existing folder paths, and intentionally flag new paths that must be created via information-architecture.

Quick Start

Ask the AI to generate json:itemData for your product shape using your sample dataset and include the correct folder locations and required fields (sku, price, stock).

Frequently Asked Questions about data-creation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a Crystallize PIM catalog import payload from spreadsheet data?

Generate a Crystallize PIM catalog import payload by mapping spreadsheet rows into the json:itemData format. The tool transforms your supplied data into shape components, enforcing item-level fields, unique SKUs, and variant rules.

What is the json:itemData format used for in catalog item imports?

The json:itemData format is the exact payload structure required by the Crystallize item-import grid. It structures catalog items by applying component values, folder locations, and variant rules to ensure valid bulk data ingestion.

Can I generate sample demo items for Crystallize without an existing dataset?

Yes, you can generate 5 to 10 realistic demo items from scratch. The generation process creates valid catalog items with required fields like SKU, price, and stock, correctly mapped to your target shape.

How do I assign folder locations when importing PIM catalog items?

Assign folder locations by using existing folder paths within the import payload. The tool places items in the correct folders and intentionally flags any new paths that must be created via information-architecture.

How does variant SKU mapping work for Crystallize catalog items?

Variant SKU mapping enforces globally unique SKUs and variant rules within the import payload. It ensures exact option and unit matching for selection and numeric components using dot-notation sub-components.

What happens if my spreadsheet data does not match the target shape constraints?

The tool transforms user-supplied data to match the target shape's types, options, units, and constraints. It enforces item-level product fields and exact option matching to prevent invalid imports.