SkillTrust

← All skills

split-test-evaluator

95 / 100 · Low risk

Fine to try.

By tabtin-ai/TabTin (GitHub) · other · 454 stars · scanned at commit b84fb2b

A/B测试分析工具:对A/B测试数据进行全面统计分析,包括计算转化率差异、进行显著性检验(Z检验/卡方检验)、构建置信区间、评估统计功效以及估算最小样本量,输出JSON结果和中文建议报告。当用户提供A/B测试的访客和转化数据,或询问如何分析、解读、设计A/B测试,以及使用诸如“A/B测试结果”、“显著性”、“转化率提升”、“统计功效”、“样本量估算”等关键词时触发。

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this.

Found in 1 place.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'split-test-evaluator' ] || [ -L ~/.agents/skills/'split-test-evaluator' ]; then echo 'A skill folder named split-test-evaluator already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/tabtin-ai/TabTin' "$d" && git -C "$d" checkout --quiet 'b84fb2b9810cd71df8350a0e52486c5327c2c929' -- 'packages/apps/tabtin-data-toolkit-pack/skills/split-test-evaluator' && mkdir -p ~/.agents/skills && cp -R "$d"/'packages/apps/tabtin-data-toolkit-pack/skills/split-test-evaluator' ~/.agents/skills/'split-test-evaluator' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'split-test-evaluator' ~/.claude/skills/'split-test-evaluator' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for tabtin-ai/TabTin shows the score of its lowest-scoring skill.

SkillTrust badge for tabtin-ai/TabTin

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/tabtin-ai/TabTin.svg)](https://zalavijaysinh.github.io/skilltrust/repos/tabtin-ai/TabTin/)

Score history

DateVersionScore
2026-11-07b84fb2b95