메뉴
Use when designing A/B tests. Covers hypothesis-driven testing, sample-size calculation, the test-design template, and the cultural rituals that make testing productive.
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.
SOC 직업 분류 기준
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/x3allamerican/design-skills-fleetsafety --skill ab-test-design-rituals명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Use when designing 404 pages and the broader empty-state pattern library. Covers tone, illustration, search recovery, and the difference between 'no data yet' and 'this URL doesn't exist'.
Use when shipping any user-facing UI. Covers the non-negotiable accessibility baseline: contrast, focus states, semantic HTML, keyboard navigation, screen-reader support, motion preferences. The minimum to avoid embarrassment and ADA risk.
Use when targeting WCAG AAA (highest accessibility tier). Covers what AAA requires beyond AA, the trade-offs, and when AAA is worth pursuing.
| name | ab-test-design-rituals |
| description | Use when designing A/B tests. Covers hypothesis-driven testing, sample-size calculation, the test-design template, and the cultural rituals that make testing productive. |
A/B tests answer questions. Run a test without a clear question and you'll have a clear non-answer.
We believe [change] will result in [outcome] for [audience], measured by [metric]. We'll know we're right if [primary metric] improves by [X%] within [Y days].
Use a calculator (e.g., evanmiller.org). 5% baseline rate + 10% relative lift = ~7,000 visitors per arm.
Minimum 1 week (captures day-of-week variation). Don't peek and stop early.
A/B (two variants). A/B/n (multiple variants — more samples required). Multivariate (combinations — even more).
Stopping early when 'looks good'. Multiple metrics without primary. Underpowered tests (false negatives). 'Winning' variant that doesn't ship (no cultural follow-through).
Applied across the X3 Compass design system.