🦀 ClawHub
ab-test-calculater
by @eelowl
Feed it two data sets — one plain-language verdict on whether to ship. No decoding p-values required. Pure Python from scratch.Plain-language verdict engine: synthesizes p-value, effect size, and power into one actionable sentence
TERMINAL
clawhub install ab-test-calculator📖 About This Skill
version: "2.0.0" name: ab-test-calculator description: "A/B测试计算器。样本量计算、统计显著性检验、实验时长预估、结果报告、贝叶斯分析。AB test calculator with sample size, significance testing, duration estimation, reports." author: BytesAgain homepage: https://bytesagain.com source: https://github.com/bytesagain/ai-skills
A/B Test Calculator Skill
A/B测试统计计算器 — 科学决策，数据驱动。
Commands
Run via: bash scripts/abtest.sh
| Command | Description | |--------------|--------------------------------| | calculate | 计算两组的统计显著性 | | sample | 计算所需最小样本量 | | significance | 检验p值和置信区间 | | duration | 预估实验所需天数 | | report | 生成完整A/B测试报告 | | bayesian | 贝叶斯方法分析胜率 |
Usage Examples
# 计算显著性（访客数 转化数）
bash scripts/abtest.sh calculate 1000 50 1000 65计算样本量（基线转化率 最小可检测提升 显著性水平）
bash scripts/abtest.sh sample 0.05 0.02 0.95预估实验时长（日均流量 所需样本量）
bash scripts/abtest.sh duration 5000 16000贝叶斯分析
bash scripts/abtest.sh bayesian 1000 50 1000 65生成报告
bash scripts/abtest.sh report 1000 50 1000 65 "按钮颜色测试"
💬 Feedback & Feature Requests: https://bytesagain.com/feedback Powered by BytesAgain | bytesagain.com