catalog-commerce
Skill3 starsChanged 5 months agoMITView on GitHub
Set up product catalogs and product sets so ecom ads can pull live products (dynamic ads) instead of static images. Use for stores with more than a handful of SKUs, after the pixel is verified.
In this repository15 other files it gives its agents.
- angle-writerSkill
- audience-builderSkill
- brand-readerSkill
- budget-pacerSkill
- buyer-language-minerSkill
- competitor-ad-teardownSkill
- copy-formulasSkill
- creative-directorSkill
- daily-auditorSkill
- fatigue-detectorSkill
- lead-gen-builderSkill
- media-buyerSkill
- pain-to-promiseSkill
- performance-analystSkill
- pixel-conversionsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Before any retargeting play that shows people what they browsed.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

