conversion-tracking-checker
Skill2 starsChanged 4 months agoMITView on GitHub
Decide whether Google Ads conversion data is trustworthy enough for optimization by checking goals, action settings, duplicates, and campaign use. Use before changing bids, budgets, or performance targets.
In this repository11 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 14
Before a bid-strategy, target, budget, or scaling recommendation.
- Distinctive: line 15
When Google Ads conversions disagree with sales, CRM, or another source.
- Distinctive: line 16
Use a connected Google Ads MCP, or paste conversion-action, campaign-goal, recent performance, and downstream outcome exports.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Conversion Tracking Checker
Doctrine
Bidding can only optimize toward the goals it is given. An active action can still be the wrong business outcome, a page view can drown out a demo, and two actions can count the same event. Google Ads evidence can reveal those risks, but it cannot prove what happened inside GA4, GTM, a website, or a CRM without separate data.
When to use
- Before a bid-strategy, target, budget, or scaling recommendation.
- When Google Ads conversions disagree with sales, CRM, or another source.
- Use a connected Google Ads MCP, or paste conversion-action, campaign-goal, recent performance, and downstream outcome exports.
Run it
Run a READ-ONLY Google Ads conversion check. Use live account data if connected; otherwise use what I paste. Change nothing.
1. Build an action inventory with: name, category, origin, status, primary or secondary, account-default inclusion, campaign goal mapping, counting rule, value rule, recent conversions, and available diagnostics.
2. Map which campaigns are bidding on which actions. Do not assume account-default goals apply everywhere without checking.
3. Flag likely bidding-quality problems, including shallow actions marked primary, inactive goals, missing values for value-based bidding, and actions that may count the same business event.
4. Treat possible duplication as a risk, not a fact. Compare action definitions, timestamps, identifiers, attribution windows, and the source of truth before deciding two actions duplicate each other.
5. Reconcile Google Ads totals with supplied CRM or sales outcomes only when date ranges, timezone, attribution, and conversion delay are aligned.
6. Give a trust grade: ready, caution, or not ready. Explain what decisions are safe now and which must wait.
7. List exact verification steps for the website tag, imported action, offline conversion, or CRM, but state when those systems are outside the available evidence.
Do not change goals, primary status, counting, values, tags, attribution, bids, or budgets. End with "No changes were made."Guardrails
- "Active" in Google Ads does not prove the website tag, GA4 event, or CRM pipeline is correct end to end.
- An imported Google Analytics action is evidence about the Google Ads action only. Do not claim access to the underlying GA4 property unless it was supplied separately.
- Similar totals do not prove actions duplicate each other, and different totals do not prove one is broken.
- A page view or other shallow action marked primary is a serious bidding risk, but changing it still requires verification and approval.
- Hold bid, budget, and scaling changes when the primary optimization signal is contaminated or unresolved.
Good output looks like
A clear conversion-action inventory, a campaign goal map, an honest trust grade, and the shortest path to knowing which business outcome Google should optimize toward.
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.

