📗 This is the user manual for the Suite for ChatGPT Ads, the tool in the Ninja Scripts panel. Here you can search it, listen to it, highlight it and save it to favourites. It is updated with every release of the tool.
A health snapshot of the whole account, with a score from 0 to 100 and the list of what to fix in order of severity. It's recalculated on every visit and after every read (hourly): it costs nothing, it doesn't go out to the internet and it writes nothing in your account.
Where you find out: the email report (weekly and monthly) carries its 🩺 «Account health» block — score, how much it has gone up or down since the start of the period, and the critical findings; and in the panel, the red badge with the number of criticals in the 💡 Optimise menu, visible from any screen and the immediate warning. The audit sends no emails of its own: the report is what tells you about it.
The six areas and their weight
| Area | The question it answers | Weight |
|---|---|---|
| 🚦 Delivery | can it serve? | 18 % |
| 🧱 Structure | is it well built? | 18 % |
| 🖼️ Ads | is there something to compete with and something to test? | 16 % |
| 📏 Measurement | do we know what works? | 18 % |
| 💶 Money | is the spend going where it should? | 15 % |
| 📐 Relevance | does everything talk about the same thing? | 15 % |
Each area starts at 100 and loses points per finding: 40 for a critical, 18 for an important, 7 for an improvement. The score is the weighted mean. An area with no data doesn't score: its weight is shared out among the others, rather than penalising you for something that can't be measured.
≥ 80 good · ≥ 55 needs work · below that, poor.
Two caps that prevent a misleading score
- With critical findings the score cannot say «good». With one it won't go above 79; with two or more, above 54. Without this, five areas at 100 masked a collapsed delivery and the account came out «good» with its campaign paused and a rejected ad.
- Spending for real (50 of your currency in 30 days) with no target cost per conversion caps you at «needs work». It isn't an accusation — nobody knows whether it's wrong: it's refusing to hand out a pass when nobody can say whether that money is well spent. It lifts as soon as you set the target, which is one field.
The score card tells you when the score is capped and why.
The fourth state: «can't be judged yet»
Besides critical, important and improvement, there are two categories that exist to avoid noise:
- Not a worry (no points lost): for example, features that need another Ninja tool.
- Can't be judged yet: not enough volume, no relevance index calculated yet, an account just connected, or campaigns created less than 24 hours ago — which the panel creates paused on purpose. Also when the ⏰ Schedule has campaigns paused because it should: that isn't a finding, that's the schedule working.
Those things are said rather than kept quiet. On a new channel, without this state half the report would be noise and the other half silence.
📐 One case worth knowing: if you haven't saved your OpenAI key, the relevance index is worked out with an approximate method, and with it the 📐 Relevance area doesn't score — its 15 % is shared out among the others and it shows under «can't be judged yet». That's deliberate: the two scales aren't comparable, and accusing with the approximate one would be judging the instrument, not the account. Save the key (pennies) and that area starts counting.
What it checks
It doesn't repeat the 💡 Recommendations rules: it absorbs them, with their own wording, so if their thresholds ever change the audit changes with them. On top of that, its own checks:
- Delivery: brand and integrity review, delivery issues, rejected or in-review ads, an account with not one impression, nothing active.
- Structure: campaigns with no ad groups, groups with no ads or no hints, too few (under 4) or too many (over 40) hints, everything in one bag (a single group with ≥ 12 hints and ≥ 3 ads), the same hint in several groups (they compete with each other).
- Ads: text that gets cut off or that wastes the card, ads with no image, twin ads (same headline or line within the group), a single ad in a group that has traffic.
- Measurement: a campaign with no conversion event, ads with no
utm_contenttag or with a repeated tag, a landing page that looks like a bare sign-up form, spend with no conversions at all. - Money: with a target set, having spent 3 targets without a single conversion (critical) and cost per conversion above it (important from 1.2×, critical from 2×); with no target it's logged as an improvement; missing budget and low bid.
Thresholds in plain sight
Every finding carries its figure and its threshold in the wording itself, and the screen publishes the full threshold table in a collapsible panel. That way you can argue with a threshold instead of believing a score.
The history
One row per day is stored, with the score and its areas, and the screen draws the 30-day trend. It's the only thing that can't be reconstructed backwards: it starts the day it's first calculated, so on a freshly connected account the chart takes a few days to say anything.