// 01, The ad

The opening, on the record.

A Nivea YouTube spot opening with a direct product showcase. Watch the first three seconds, the can is on-screen immediately, which is the strongest thing this opening has going for it.

Nivea · YouTube · DE

Click to play the full ad.

15.1s · YouTube / brand channel
benchmark_only = true · scored 2026-05-18

02 · Archived result

Directional creative evidence.

67
Archived raw composite · not outcome confidence

The archived runner returned SHARPEN. This is a historical rule label, not a current decision recommendation. No matched-cohort sample or repeated-run estimate is attached to this example.

Meta has no held-out validation. A platform match alone also does not establish coverage for a market, category or format. Keep these examples directional unless the specific cohort evidence supports a stronger statement.

// 03, The five KPIs

Where the score comes from.

Archived raw KPI outputs below. Labels describe diagnostic ranges only; they are not measured retention, recall, persuasion or emotional intensity.

// KPI breakdown, Nivea YouTube DE

Beat the Skip
25%
Beat the Skip, White background, NIVEA blue disc-logo in the top-right corner, brand_in_first_3s = yes, full stop.0.5s
75
Archived model diagnostic. Inspect the linked frame and the full sequence; no viewer response was measured.
Get Noticed
20%
Get Noticed, Continuing skin-focus shot with the NIVEA mark held, visual hierarchy is clean.2.0s
70
Archived model diagnostic. Inspect the linked frame and the full sequence; no viewer response was measured.
Brand Impact
20%
Brand Impact, The 'Schutz vor DEO-FLECKEN' problem caption, clothing close-up. Brand mark still anchored top-right.4.0s
70
Archived model diagnostic. Inspect the linked frame and the full sequence; no viewer response was measured.
Sell Proposition
20%
Sell Proposition, Product family hero, Black & White Invisible 72h range across women's and Men's variants on a sky-blue stage.MID
70
Archived model diagnostic. Inspect the linked frame and the full sequence; no viewer response was measured.
Build Brand
15%
Build Brand, Codes compounding, NIVEA blue, 72h proof point, Black & White range typography all aligned.75%
55
Archived model diagnostic. Inspect the linked frame and the full sequence; no viewer response was measured.
// 04, Creative classification

What the pipeline tagged.

Hook type
Product-Showcase
Opening motion
Static
Brand in first 3s
Yes
Attention risk
None
Value prop type
Benefit-Led
CTA timing
End
Subcategory
Deodorant
Matrix label
goal
Note on matrix label. The pipeline tagged this ad with matrix_label = goal, which typically corresponds to the SCALE band. However the rule-derived verdict is SHARPEN, composite 67 is below the SCALE floor of 70. This is a minor inconsistency in the scoring runner where the matrix label is computed independently of the composite band rule. The rule-derived verdict (SHARPEN) is authoritative; we surface this as transparency rather than hide it.
05 · Interpret the run

Read the model output.

The archived runner tagged the hook as Product-Showcase, opening motion as Static and value proposition as Benefit-Led. Check these labels against the full creative. Review whether the distinctive product cues remain visible beyond the first pack shot.

06 · Proposed revision

An edit to test.

Nivea ad closing frameEND

Test a repeated product cue at a relevant demonstration moment. Keep the original, record the change and agree the outcome measure before testing. There is no measured score uplift or campaign result for this proposed revision.

07 · Coverage and stability

Coverage limits.

This archive identifies the platform and country, but does not attach a matched-cohort sample, a percentile calculation or a repeat-run stability estimate. We therefore do not rank this ad in a category quintile. Validation of the separate platform-native attribute model does not validate these five KPI outputs.

08 · Decision and follow-through

Record the human choice.

Use the example to frame a review question. A human reviewer should record the brief, chosen revision, proposed test and actual result. No client acceptance or in-market outcome is claimed for this case. See the methodology and the brand-cue review guide.

Archived run evidence. Scored 18 May 2026. Raw scores and classifications are preserved from the archived scoring output. Prompt hash, temperature, seed, matched-cohort coverage and repeat-run stability were not recorded in that archive. All interpretations here are directional. These are real ad assets with model-generated diagnostics, not synthetic consumer measurements. No sales, ROAS, conversion, retention, emotional-strength or brand-recall result is established. Current methodology and separate model-validation evidence.