Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't...
.claude/skills/sickn33-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✓→✗ | ▼ Worse | 66% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 224% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 37% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 73% | 0% |
| case-08 | ✓→✓ | = Same ✓ | 58% | 0% |
Use this skill when you need when the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't...
You are a conversion rate optimization expert. Your goal is to analyze marketing pages and provide actionable recommendations to improve conversion rates.
Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before providing recommendations, identify:
Analyze the page across these dimensions, in order of impact:
Check for:
Common issues:
Evaluate:
Strong headline patterns:
Primary CTA assessment:
CTA hierarchy:
Check:
Types to look for:
Placement: Near CTAs and after benefit claims
Common objections to address:
Address through: FAQ sections, guarantees, comparison content, process transparency
Look for:
Structure your recommendations as:
Easy changes with likely immediate impact.
Bigger changes that require more effort but will significantly improve conversions.
Hypotheses worth A/B testing rather than assuming.
For key elements (headlines, CTAs), provide 2-3 alternatives with rationale.
When recommending experiments, consider tests for:
For comprehensive experiment ideas by page type: See references/experiments.md
For detailed form CRO guidance — including field optimization, multi-step forms, error handling, and form-specific experiments — see references/form.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 25,327 | 18,615 | -27% | 1 | 1 | 0% | 4,041 | 4,079 | +1% | 0 | 0 | — |
case-02 | fail→fail | 12,280 | 9,742 | -21% | 1 | 1 | 0% | 2,608 | 3,451 | +32% | 0 | 0 | — |
case-03 | fail→fail | 17,067 | 18,218 | +7% | 1 | 1 | 0% | 3,710 | 4,988 | +34% | 0 | 0 | — |
case-04 | fail→fail | 1,924 | 3,586 | +86% | 1 | 1 | 0% | 273 | 1,905 | +598% | 0 | 0 | — |
case-05 | pass→pass | 10,864 | 6,816 | -37% | 1 | 1 | 0% | 1,779 | 2,431 | +37% | 0 | 0 | — |
case-06 | fail→fail | 6,376 | 5,512 | -14% | 1 | 1 | 0% | 1,138 | 2,304 | +102% | 0 | 0 | — |
case-07 | pass→pass | 9,666 | 8,134 | -16% | 1 | 1 | 0% | 1,557 | 2,694 | +73% | 0 | 0 | — |
case-08 | pass→pass | 10,465 | 8,228 | -21% | 1 | 1 | 0% | 1,633 | 2,580 | +58% | 0 | 0 | — |
case-09 | fail→fail | 6,677 | 4,696 | -30% | 1 | 1 | 0% | 1,077 | 2,174 | +102% | 0 | 0 | — |
case-10 | pass→pass | 8,649 | 7,204 | -17% | 1 | 1 | 0% | 1,558 | 2,624 | +68% | 0 | 0 | — |
case-11 | pass→pass | 10,493 | 9,037 | -14% | 1 | 1 | 0% | 1,647 | 2,830 | +72% | 0 | 0 | — |
case-12 | pass→pass | 13,719 | 10,158 | -26% | 1 | 1 | 0% | 2,136 | 3,055 | +43% | 0 | 0 | — |
case-13 | pass→pass | 12,869 | 11,355 | -12% | 1 | 1 | 0% | 2,070 | 3,178 | +54% | 0 | 0 | — |
case-14 | pass→pass | 11,004 | 12,668 | +15% | 1 | 1 | 0% | 1,891 | 3,507 | +85% | 0 | 0 | — |
case-15 | pass→pass | 11,555 | 8,540 | -26% | 1 | 1 | 0% | 1,876 | 2,607 | +39% | 0 | 0 | — |
case-16 | pass→pass | 13,414 | 15,039 | +12% | 1 | 1 | 0% | 2,304 | 3,866 | +68% | 0 | 0 | — |
case-17 | pass→pass | 10,006 | 8,733 | -13% | 1 | 1 | 0% | 1,781 | 2,761 | +55% | 0 | 0 | — |
case-18 | pass→pass | 12,806 | 14,482 | +13% | 1 | 1 | 0% | 2,269 | 3,734 | +65% | 0 | 0 | — |
case-19 | pass→fail | 11,329 | 8,232 | -27% | 1 | 1 | 0% | 1,634 | 2,707 | +66% | 0 | 0 | — |
case-20 | pass→pass | 12,779 | 6,808 | -47% | 1 | 1 | 0% | 1,798 | 2,452 | +36% | 0 | 0 | — |
case-21 | pass→pass | 12,337 | 9,954 | -19% | 1 | 1 | 0% | 1,899 | 2,756 | +45% | 0 | 0 | — |
case-22 | pass→fail | 4,718 | 4,425 | -6% | 1 | 1 | 0% | 613 | 1,986 | +224% | 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 -100 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.
Other measured skills in the registry, with their headline benchmark lift.