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 killvxk/pm-skills-zh --skill ab-test-analysisgit clone --depth 1 https://github.com/killvxk/pm-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/killvxk/pm-skills-zh/ab-test-analysis)<a href="https://agentmods.dev/skills/killvxk/pm-skills-zh/ab-test-analysis"><img src="https://agentmods.dev/badge/skills/killvxk/pm-skills-zh/ab-test-analysis/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/killvxk/pm-skills-zh/ab-test-analysis"><img src="https://agentmods.dev/badge/skills/killvxk/pm-skills-zh/ab-test-analysis.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 | $0.00074 | $0.01023 |
| Opus 5 | $0.00037 | $0.00511 |
| Sonnet 5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
ab-test-analysis 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 9d 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.
What it actually says
A/B 测试分析
以严格的统计方法评估 A/B 测试结果，并将发现转化为清晰的产品决策。
背景
你正在分析 $ARGUMENTS 的 A/B 测试结果。
如果用户提供了数据文件（CSV、Excel 或数据分析平台导出文件），直接读取并分析。如有需要，生成 Python 脚本执行统计计算。
操作步骤
-
理解实验背景：
- 假设是什么？
- 改动了什么（实验组的变化）？
- 主要指标是什么？是否有护栏指标？
- 测试运行了多长时间？
- 流量分配比例是多少？
-
验证测试设置：
- 样本量：样本量是否足以检测预期效应量？
- 使用公式：n = (Z²α/2 × 2 × p × (1-p)) / MDE²
- 如果统计功效不足（< 80%），需标记
- 时长：测试是否至少运行了 1—2 个完整业务周期？
- 随机化：是否有样本比例失配（SRM）的迹象？
- 新奇效应/首因效应：时间是否足够让初期行为变化消退？
- 样本量：样本量是否足以检测预期效应量？
-
计算统计显著性：
- 对照组和实验组各自的转化率
- 相对提升：(实验组 - 对照组) / 对照组 × 100
- p 值：使用双尾 z 检验或卡方检验
- 置信区间：差值的 95% CI
- 统计显著性：p < 0.05 吗？
- 实际显著性：提升幅度对业务有意义吗？
如果用户提供了原始数据，生成并运行 Python 脚本来计算上述结果。
-
检查护栏指标：
- 是否有护栏指标（营收、参与度、页面加载时间）出现下降？
- 主要指标获胜但护栏指标恶化，不一定是真正的胜利
-
解读结果：
结果 建议 显著正向提升，无护栏问题 上线 — 全量推送 显著正向提升，存在护栏顾虑 进一步调查 — 理解权衡后再上线 不显著，但有正向趋势 延长测试 — 需要更多数据或更大效应 不显著，基本持平 停止测试 — 未检测到有意义的差异 显著负向提升 不上线 — 回退到对照组，分析原因 -
提供分析摘要：
## A/B 测试结果：[测试名称] **假设**：[我们的预期] **时长**：[X 天] | **样本量**：[N 对照组 / M 实验组] | 指标 | 对照组 | 实验组 | 提升 | p 值 | 是否显著？ | |---|---|---|---|---|---| | [主要指标] | X% | Y% | +Z% | 0.0X | 是/否 | | [护栏指标] | ... | ... | ... | ... | ... | **建议**：[上线 / 延长 / 停止 / 进一步调查] **理由**：[原因] **后续行动**：[下一步]
逐步思考。保存为 Markdown 格式。如果提供了原始数据，生成 Python 脚本执行计算。
延伸阅读
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.
- 9d ago First seen · 83 lines · 74 tokens per session scan A 789899118374
ab-test-analysis is a skill published in the GitHub repository killvxk/pm-skills-zh (156 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 1,023 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…