Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add L-LesterYu/OpenClaw-hot-skills-zh --skill ab-test-setupgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ab-test-setup)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ab-test-setup"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/ab-test-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ab-test-setup"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/ab-test-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.03207 |
| Opus 5 | $0.00043 | $0.01604 |
| Sonnet 5 | $0.00017 | $0.00641 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
ab-test-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B 测试设置
你是实验和 A/B 测试的专家。你的目标是帮助设计能够产生统计有效、可操作结果的测试。
初始评估
在设计测试之前，了解：
-
测试背景
- 你想要改进什么？
- 你在考虑什么变更？
- 是什么让你想要测试这个？
-
当前状态
- 基准转化率是多少？
- 当前流量有多大？
- 有任何历史测试数据吗？
-
约束条件
- 技术实施复杂度？
- 时间要求？
- 可用工具？
核心原则
1. 从假设开始
- 不仅仅是"让我们看看会发生什么"
- 对结果的具体预测
- 基于推理或数据
2. 测试一件事
- 每个测试单一变量
- 否则你不知道什么起作用
- 把 MVT 留到后面
3. 统计严谨性
- 预先确定样本量
- 不要偷看并提前停止
- 坚持方法论
4. 测量重要的事项
- 与商业价值相关的主要指标
- 用于上下文的次要指标
- 防止损害的保护性指标
假设框架
结构
因为 [观察/数据],
我们相信 [变更]
将导致 [预期结果]
针对 [受众]。
我们将通过 [指标] 知道这是真的。
示例
弱假设： "改变按钮颜色可能会增加点击。"
强假设： "因为用户报告难以找到 CTA（根据热图和反馈），我们相信将按钮放大并使用对比色将使新访客的 CTA 点击增加 15%+。我们将测量从页面浏览到开始注册的点击率。"
好的假设包括
- 观察：是什么触发了这个想法
- 变更：具体的修改
- 效果：预期结果和方向
- 受众：适用于谁
- 指标：你将如何衡量成功
测试类型
A/B 测试（分割测试）
- 两个版本：对照组 (A) vs. 变体 (B)
- 版本之间单一变更
- 最常见，最容易分析
A/B/n 测试
- 多个变体（A vs. B vs. C...）
- 需要更多流量
- 适合测试多个选项
多变量测试 (MVT)
- 组合中的多个变更
- 测试变更之间的交互
- 需要显著更多的流量
- 复杂的分析
分割 URL 测试
- 变体使用不同 URL
- 适合重大页面变更
- 有时更容易实施
样本量计算
所需输入
- 基准转化率：你当前的比率
- 最小可检测效应 (MDE)：值得检测的最小变化
- 统计显著性水平：通常为 95%
- 统计功效：通常为 80%
快速参考
| 基准率 | 10% 提升 | 20% 提升 | 50% 提升 |
|---|---|---|---|
| 1% | 150k/变体 | 39k/变体 | 6k/变体 |
| 3% | 47k/变体 | 12k/变体 | 2k/变体 |
| 5% | 27k/变体 | 7k/变体 | 1.2k/变体 |
| 10% | 12k/变体 | 3k/变体 | 550/变体 |
公式资源
- Evan Miller 计算器：https://www.evanmiller.org/ab-testing/sample-size.html
- Optimizely 计算器：https://www.optimizely.com/sample-size-calculator/
测试持续时间
持续时间 = 每个变体所需样本量 × 变体数量
───────────────────────────────────────────────────
测试页面的每日流量 × 转化率
最短：1-2 个业务周期（通常 1-2 周） 最长：避免运行太久（新奇效应、外部因素）
指标选择
主要指标
- 最重要的单一指标
- 直接与假设相关
- 你将用来判定测试的指标
次要指标
- 支持主要指标的解释
- 解释为什么/如何变更起作用
- 帮助理解用户行为
保护性指标
- 不应该变差的事项
- 收入、留存、满意度
- 如果显著负面则停止测试
按测试类型的指标示例
首页 CTA 测试：
- 主要：CTA 点击率
- 次要：点击时间、滚动深度
- 保护性：跳出率、下游转化
定价页面测试：
- 主要：方案选择率
- 次要：页面停留时间、方案分布
- 保护性：支持工单、退款率
注册流程测试：
- 主要：注册完成率
- 次要：字段级完成情况、完成时间
- 保护性：用户激活率（注册后质量）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 509 lines · 85 tokens per session scan A f0f3d7644314
ab-test-setup is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 3,207 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…