메뉴
A/B testing methodology for cold email optimization
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/MadAppGang/claude-code --skill ab-testing-patterns명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | ab-testing-patterns |
| version | 1.0.0 |
| description | A/B testing methodology for cold email optimization |
plugin: instantly updated: 2026-01-20
CRITICAL: Only change one element per test for clear attribution.
| Test Type | Variable | Keep Same |
|---|---|---|
| Subject Line | Subject only | Body, CTA, timing |
| Opening Line | First sentence | Subject, rest of body |
| CTA | Call to action | Subject, body intro |
| Send Time | Delivery time | All copy elements |
| Confidence Level | Minimum Sample per Variant |
|---|---|
| 90% | 100 |
| 95% (standard) | 150 |
| 99% | 200 |
Formula:
sample_size = (Z^2 * p * (1-p)) / E^2
Where:
Z = 1.96 for 95% confidence
p = expected conversion rate (use 0.5 if unknown)
E = margin of error (typically 0.05)
| Category | Control Example |
|---|
| Variant Example |
|---|
| Curiosity vs Specific | "Quick question" | "2 min about {{company}}'s pipeline" |
| Personal vs Generic | "{{first_name}}, saw this" | "Your team might like this" |
| Question vs Statement | "Struggling with X?" | "How we fixed X for [Company]" |
| Short vs Medium | "Quick win?" | "{{first_name}}, 2 ideas for {{company}}" |
| Element | Low-Lift | High-Lift |
|---|---|---|
| Opening hook | Different pain point | Different approach entirely |
| Social proof | Different company name | No social proof |
| Value proposition | Reframe benefit | Different benefit |
| CTA | Soft vs hard ask | Different action |
PAS vs AIDA:
Test Hypothesis: PAS performs better for pain-point-heavy ICPs, AIDA for solution-seekers.
| Variable | Options to Test |
|---|---|
| Day of week | Tue vs Thu (typically best) |
| Time of day | 8-10am vs 2-4pm |
| Timezone | Send in prospect's local time vs batch send |
| Sequence gaps | 2-day vs 3-day follow-up gaps |
Optimal Sending Windows:
Primary: Tuesday-Thursday, 9-11am local time
Secondary: Tuesday-Thursday, 2-4pm local time
Avoid: Monday morning, Friday afternoon
| Total Sample | Lift Needed for 95% Confidence |
|---|---|
| 200 (100 per variant) | 15%+ lift |
| 500 (250 per variant) | 10%+ lift |
| 1000 (500 per variant) | 7%+ lift |
IF lift >= 15% AND sample >= 100/variant:
Declare winner with medium confidence
IF lift >= 10% AND sample >= 250/variant:
Declare winner with high confidence
IF lift < 10% OR sample < 100/variant:
Continue test or call it inconclusive
move_leads_to_campaign to assign leadsupdate_campaign_sequence)## A/B Test Log
**Test ID**: {uuid}
**Campaign**: {campaign_name}
**Variable**: {what_was_tested}
**Hypothesis**: {expected_outcome}
**Control**:
- Version: {control_description}
- Sample: {n}
- Open Rate: {x}%
- Reply Rate: {y}%
**Variant**:
- Version: {variant_description}
- Sample: {n}
- Open Rate: {x}%
- Reply Rate: {y}%
**Result**: {Winner|Inconclusive}
**Lift**: {z}%
**Confidence**: {confidence}%
**Learning**: {what_we_learned}
SOC 직업 분류 기준