Shopify Catalog Hygiene Agent

Reviews every new Shopify product against your listing standards and posts one Slack note to merchandising: what is missing, plus any price sitting far outside its own category, with the comparison shown.

0 in use19
Loading preview…
Guided setup — test it before connecting anything.

Watch it work before it's live

Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.

Merino Base Layer - Womens

Paid

Rosa Tavares, merchandising · nordkap-outdoor.myshopify.com

Created 08:40 as a draft. Description runs to twelve words, one image on the product and none on the three colour variants. Variants: Slate 89.00 CAD, Moss 89.00 CAD, Rust 8.90 CAD. Product type is blank, vendor is Nordkap, no tags. Eighteen other base layers in the store sell between 79.00 and 119.00 CAD.

Set up in minutes

Using this template drops you into a guided setup. It asks exactly this, nothing else:

  1. Connect Shopify

    One sign-in. The agent acts through your account, scoped to what this template uses.

  2. Connect Slack

    One sign-in. The agent acts through your account, scoped to what this template uses.

  3. Listing standards

    What a finished listing looks like in your store: the title pattern, the shortest description you accept, how many images and which angles, the tags and product type you require, and the price gap against similar products that is worth flagging.

  4. Choose which agent runs it

    NoClick's built-in models work out of the box — or bring Claude Code, Codex, and other coding agents on your own subscription.

  5. Watch it handle a test run

    A staged conversation against a simulated world — then it’s live.

About this agent

New products get created in a hurry, usually by whoever happened to have the photos, and the gaps only surface when a shopper bounces or a price looks wrong on the storefront. This agent reviews each product the moment it exists, measures it against the standards you wrote down, and compares its prices with the products sitting next to it in the same category. It posts one note to merchandising and changes nothing, so a deliberate premium price stays a decision instead of becoming a correction.

What people use it for

  • Catch the missing decimal - A variant entered at 8.90 instead of 89.00 sells out overnight and costs real money. Comparing it against its siblings surfaces the gap in the minutes after creation, not in the weekly report.
  • One standard, applied evenly - Listing quality usually depends on who happened to review it and how busy they were. Every product gets measured against the same written rules, so the hundredth listing is checked as carefully as the first.
  • Outliers with their evidence - A price flag with no context is noise. Each one arrives showing the sibling range, the number of products compared, and the gap, so merchandising can agree or dismiss it in one read.
  • Nothing edited behind you - Automatic fixes to titles and prices are how a catalog quietly drifts away from what the team intended. This one only writes to Slack, so every change to the store is still made by a person.

Before you fork

What access does it need to my store?

A Shopify credential that receives the product created event and can read products and product images, plus the Slack channel merchandising watches. No write scope is used anywhere. You then write the listing standards, and the Test Runs let you tune the wording against three staged products before real ones start arriving.

Can it fix the listing instead of reporting it?

No, and that is the point. Nothing in this template can edit a title, rewrite a description, adjust a price, or change publication status, so its whole output is a note. Deliberate choices like a limited edition price survive contact with it, which an auto correcting version would not allow.

We carry thousands of products. Does the price check hold up?

The comparison is deliberately narrow: only products sharing the new one's type, vendor, or collection, because a candle tells you nothing about a coat. The note always states how many products the range was drawn from, so a flag built on four siblings reads differently from one built on ninety.

Run it with your coding agent

Works with

Put Shopify Catalog Hygiene Agent to work

Free to start. Guided setup, a test run against staged conversations, and it's live.