mcpField
P
pixel-conversions

pixel-conversions

github.com/kelpi-aiMarketing & growth556 installsUpdated 17w ago
Repository

About pixel-conversions

A read-only skill for checking Meta Ads conversion tracking against store or CRM totals. It prioritizes measurement integrity and identifies likely tracking breaks before campaign optimization.

Key features

  1. 01List account pixels and campaign targets
  2. 02Review seven-day conversion events
  3. 03Flag zero or duplicate events
  4. 04Compare Meta and store totals
  5. 05Prioritize one suggested fix

Use cases

  1. 01Checking tracking before a first campaign
  2. 02Auditing tracking after checkout changes
  3. 03Investigating Meta and store discrepancies
  4. 04Running a monthly measurement review

MCP support

Requires read access to a Meta Ads MCP to inspect pixel and conversion data. It makes no changes.

Install

Copy the command and run it in a terminal.

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

After installing, type/pixel-conversionsin Claude Code to confirm it loaded.

Bundled filesskill.meta.json

Details

From the project README

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.

Comments

Markdown supported