agentleFS
kelpi-aikelpi-ai/meta-ads-skills/skills/pixel-conversions/SKILL.md

pixel-conversions

Skill3 starsChanged 5 months agoMITView on GitHub

Verify the tracking is telling the truth: which events fire, which double-fire or died, and whether Meta's numbers can be reconciled with your store's. Use before launch, after any site change, and whenever dashboards disagree.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Before the first campaign, after every site or checkout change, and monthly regardless.

    line 12
  2. Distinctive:

    Read-only; fixes happen on the site or in Events Manager by a human.

    line 29
  3. Distinctive:

    Never explain a gap away: "a 15% gap is normal attribution behavior" and "your purchase event died Tuesday" are different findings.

    line 30
  4. Distinctive:

    If store numbers are unavailable, say the reconciliation is incomplete rather than trusting Meta's side alone.

    line 31

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pixel & Conversions

Doctrine

If the pixel is broken, every other number is a lie, and the algorithm optimizes toward the lie. The most common ownerside symptom is "Meta says my ads are fine, Shopify says sales are down": that is either attribution's normal flattery or a real tracking break, and knowing which is worth more than any optimization. Measurement integrity precedes optimization, always.

When to use

  • Before the first campaign, after every site or checkout change, and monthly regardless.
  • Whenever Meta's dashboard and your store/CRM disagree hard.
  • Needs a Meta Ads MCP, read access.

Run it

Tracking truth check, READ-ONLY:

1. List the pixels on my account and which one my active campaigns optimize toward.
2. For the last 7 days: which conversion events fired, at what volume? Flag anything that looks broken: purchase events at zero while traffic flows, events double-firing, or a custom event that silently replaced a standard one.
3. Compare Meta's reported conversions for the period against my store's number: [MY STORE'S COUNT]. State the gap as a percentage and explain the plausible causes in plain language (attribution windows, view-through, genuine breakage), ranked by likelihood.
4. Tell me the ONE fix worth doing first if anything is broken, and what it would confirm.
5. Change nothing.

Guardrails

  • Read-only; fixes happen on the site or in Events Manager by a human.
  • Never explain a gap away: "a 15% gap is normal attribution behavior" and "your purchase event died Tuesday" are different findings; say which one the data shows.
  • If store numbers are unavailable, say the reconciliation is incomplete rather than trusting Meta's side alone.

Good output looks like

A verdict in one line ("your tracking is telling the truth" or "purchase events died on [date]"), the evidence, and one prioritized fix.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.