Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro.
.claude/skills/davila7-popup-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 130% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 154% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 118% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 127% | 0% |
You are an expert in popup and modal optimization. Your goal is to create popups that convert without annoying users or damaging brand perception.
Before providing recommendations, understand:
Goal: Newsletter/list subscription
Best practices:
Copy structure:
Goal: Exchange content for email
Best practices:
Goal: First purchase or conversion
Best practices:
Goal: Last-chance conversion
Best practices:
Formats:
Goal: Site-wide communication
Best practices:
Goal: Less intrusive engagement
Best practices:
If recommending multiple popups:
Ideas to A/B test with expected outcomes
Banner Variations
Popup Formats
Position Testing
Timing Triggers
Behavior Triggers
Click Triggers
Headlines & Copy
CTAs
Visual Content
Dynamic Content
Audience Targeting
If you need more context:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | fail→fail | 19,796 | 16,634 | -16% | 1 | 1 | 0% | 4,133 | 6,084 | +47% | 0 | 0 | — |
case-01 | fail→fail | 16,899 | 17,158 | +2% | 1 | 1 | 0% | 2,861 | 5,584 | +95% | 0 | 0 | — |
case-02 | pass→pass | 11,897 | 14,765 | +24% | 1 | 1 | 0% | 1,970 | 4,829 | +145% | 0 | 0 | — |
case-03 | pass→pass | 10,977 | 11,829 | +8% | 1 | 1 | 0% | 1,760 | 4,721 | +168% | 0 | 0 | — |
case-04 | pass→pass | 11,316 | 11,634 | +3% | 1 | 1 | 0% | 2,027 | 4,426 | +118% | 0 | 0 | — |
case-05 | pass→pass | 9,278 | 12,034 | +30% | 1 | 1 | 0% | 1,560 | 4,709 | +202% | 0 | 0 | — |
case-06 | pass→pass | 8,992 | 8,602 | -4% | 1 | 1 | 0% | 1,608 | 4,282 | +166% | 0 | 0 | — |
case-07 | pass→pass | 11,435 | 13,591 | +19% | 1 | 1 | 0% | 1,865 | 4,956 | +166% | 0 | 0 | — |
case-08 | pass→pass | 12,915 | 12,459 | -4% | 1 | 1 | 0% | 2,370 | 5,203 | +120% | 0 | 0 | — |
case-09 | fail→fail | 11,435 | 10,014 | -12% | 1 | 1 | 0% | 1,910 | 4,318 | +126% | 0 | 0 | — |
case-10 | fail→pass | 11,165 | 13,313 | +19% | 1 | 1 | 0% | 1,822 | 4,850 | +166% | 0 | 0 | — |
case-11 | fail→pass | 11,344 | 8,858 | -22% | 1 | 1 | 0% | 1,827 | 4,204 | +130% | 0 | 0 | — |
case-12 | pass→fail | 14,509 | 16,345 | +13% | 1 | 1 | 0% | 2,412 | 5,270 | +118% | 0 | 0 | — |
case-13 | fail→fail | 16,124 | 14,792 | -8% | 1 | 1 | 0% | 2,891 | 5,264 | +82% | 0 | 0 | — |
case-14 | pass→fail | 12,719 | 13,429 | +6% | 1 | 1 | 0% | 2,260 | 5,126 | +127% | 0 | 0 | — |
case-15 | pass→pass | 12,750 | 13,405 | +5% | 1 | 1 | 0% | 2,047 | 4,813 | +135% | 0 | 0 | — |
case-16 | pass→pass | 9,110 | 8,271 | -9% | 1 | 1 | 0% | 1,556 | 4,132 | +166% | 0 | 0 | — |
case-17 | pass→pass | 13,843 | 14,554 | +5% | 1 | 1 | 0% | 2,408 | 5,270 | +119% | 0 | 0 | — |
case-18 | pass→pass | 9,781 | 14,011 | +43% | 1 | 1 | 0% | 1,725 | 4,921 | +185% | 0 | 0 | — |
case-19 | fail→pass | 10,739 | 9,861 | -8% | 1 | 1 | 0% | 1,766 | 4,485 | +154% | 0 | 0 | — |
case-20 | fail→fail | 20,043 | 18,558 | -7% | 1 | 1 | 0% | 3,282 | 5,847 | +78% | 0 | 0 | — |
case-22 | fail→fail | 26,627 | 21,846 | -18% | 1 | 1 | 0% | 4,645 | 6,779 | +46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.