Explore in MochiBot. Install in chat.Hosted workspaces and MochiBot lightweight setups include the Skills assistant. Choose a Skill and ask for installation in chat. Other OpenClaw setups can follow the first-install guide.
How to use Skills →
MOCHILAB / AI SKILL
Product Import Preview
Preview supported Shopify CSV changes with omitted-column preservation, blank optional-field clearing and variant identity risks.
What it does
Preview supported Shopify CSV changes with omitted-column preservation, blank optional-field clearing and variant identity risks.
Model and scope
current and proposed are tables with headers and rows; every row is an object containing exactly every listed header and string cells, so header omission differs from an empty cell. profile must be shopify-current or shopify-legacy, and overwrite must be boolean. Current headers include URL handle and Title; legacy aliases are Handle, Variant SKU, Variant Price, Variant Grams and Body (HTML). Supported product fields are Title/Vendor/Type/Tags/Description, variant fields SKU/Price/Weight value (grams), and Option1/2/3 name/value pairs. Group by exact handle; first row carries product fields and later blanks are continuation cells. Conflicting nonblank continuation fields are flagged. Current variant identity is the full three-option value tuple. Unknown tuples are recreation risks, never joined by row position. Optional present blank product fields clear; omitted preserve. Title blanks and variant blanks/defaults are review risks. Unsupported headers, metadata, images, inventory locations, Markets and platform import validation are not simulated.
Try saying
Preview this product import against my export, especially blank Vendor cells and omitted Tags.
Use the explicit legacy header profile and show option identity changes before I import.
Runtime and outputs
Reads supplied normalized JSON and creates result.json, report.md and rows.csv with input and output hashes. Preserve raw CSV; ask the assistant to normalize exports against the bundled input reference. Python 3.10+ standard library only; no paid data key or MochiLab backend needed. Optional explanation uses your current agent model and its ordinary service costs separately. Existing output directories are refused. Includes fictional examples and independent offline domain tests. No API/store changes, uploads, automatic tasks, notifications, legal or tax decisions.
References