mcpField
C
catalog-commerce

catalog-commerce

github.com/kelpi-aiMarketing & growth552 installsUpdated 17w ago
Repository

About catalog-commerce

A marketing skill for setting up Meta Ads catalogs and product sets, aimed at e-commerce advertisers. It audits catalog health and Pixel product ID matching before creating angle-based product sets with approval.

Key features

  1. 01Audit existing catalogs and product issues
  2. 02Check the catalog-to-Pixel connection
  3. 03Verify product IDs in purchase events
  4. 04Plan product sets and show filter logic
  5. 05Create product sets after approval

Use cases

  1. 01Check catalog readiness before dynamic ads
  2. 02Plan product sets for different marketing angles
  3. 03Determine whether a catalog is ready for an ad test

MCP support

Requires a Meta Ads MCP with write access. Write operations are confirmed before execution.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kelpi-ai/meta-ads-skills --skill catalog-commerce

After installing, type/catalog-commercein Claude Code to confirm it loaded.

Bundled filesskill.meta.json

Details

From the project README

Catalog & Commerce

Doctrine

Commerce plumbing is unglamorous and decisive: dynamic product ads cannot run without a healthy catalog, and a catalog wired to a broken pixel just automates showing people the wrong products. Order matters: pixel first (see pixel-conversions), catalog second, product sets third. Product sets are angles for inventory: "best sellers", "under $50", "new arrivals" are different promises to different buyers.

When to use

  • Ecom stores with enough SKUs that per-product creative is impractical.
  • Before any retargeting play that shows people what they browsed.
  • Needs a Meta Ads MCP with write access; creation steps are confirmed before running.

Run it

Catalog setup, step by step, confirm with me before each write:

1. List my existing catalogs and their product counts. If a catalog already exists, audit it instead of duplicating: how many products, how many rejected or missing images/prices?
2. Check the pixel link: is the catalog connected to my pixel, and are the product IDs in my purchase events matching catalog IDs? If not, stop and tell me; nothing downstream works until this does.
3. Propose 2-3 product sets that match my angles (for example: best sellers, entry-price items, the category my ads target). Show the filter logic.
4. On my approval, create the sets and tell me exactly which ad type they unlock (dynamic product ads, advantage+ catalog ads) and what a $20/day test on the best set would look like.

Guardrails

  • Audit before create: duplicate catalogs are how accounts end up advertising stale prices.
  • The pixel-to-catalog ID match is a hard gate. Skipping it produces ads for out-of-stock products at wrong prices.
  • Product sets mirror angles: a set nobody wrote an angle for is inventory, not a campaign.

Good output looks like

One healthy catalog, 2-3 named product sets tied to angles, and a clear go/no-go on whether dynamic ads are ready to test.

Comments

Markdown supported