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.
git 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/commands/killvxk/pm-skills-zh/analyze-test)<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/analyze-test"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/analyze-test.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01163 |
| Opus 5 | $0.00014 | $0.00581 |
| Sonnet 5 | $0.00006 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
analyze-test 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 7d 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
/analyze-test -- A/B 测试分析
以严格的统计方法评估实验结果,并将发现转化为清晰的产品决策:上线、延长还是停止。
调用方式
/analyze-test 对照组:4.2% 转化率(n=5000),实验组:4.8% 转化率(n=5100)
/analyze-test [上传一份测试结果的 CSV 文件]
/analyze-test [上传实验平台的截图]
工作流程
第一步:接收测试数据
支持以下任意格式:
- 汇总统计数据(各组的转化率和样本量)
- 原始事件数据(包含 user_id、variant、converted、timestamp 字段的 CSV)
- 实验平台截图(Optimizely、LaunchDarkly 等)
- 实验及结果的文字描述
第二步:验证测试设计
在分析结果之前,先检查:
- 样本量是否充足?(执行统计功效分析)
- 测试运行时间是否足够?(需覆盖完整的周期循环,至少 1—2 个业务周期)
- 随机化是否干净?(检查样本比例失配问题)
- 测试期间是否存在外部干扰因素?
如发现问题,需标记——来自有缺陷测试的结论可能具有误导性。
第三步:分析结果
应用 ab-test-analysis 技能:
- 统计显著性:计算 p 值和置信区间
- 效应量:两组间的绝对差值和相对差值
- 实际显著性:效应是否大到对业务有实质影响?
- 置信区间:真实效应的合理范围是多少?
- 分层分析:如数据允许,检查各用户分层是否存在差异化效应
第四步:生成分析报告
## A/B 测试分析:[测试名称]
**日期**:[今天]
**测试时长**:[X 天/周]
**总样本量**:[N 名用户]
### 结果汇总
| 分组 | 样本量 | 指标 | 比率 | 95% CI |
|------|--------|------|------|--------|
| 对照组 | [n] | [指标] | [X%] | [X% - Y%] |
| 实验组 | [n] | [指标] | [X%] | [X% - Y%] |
### 统计分析
- **相对提升**:[+X%]([CI 范围])
- **p 值**:[X]
- **统计显著**:在 95% 置信度下 [是/否]
- **最小可检测效应(MDE)**:[X%](测试统计功效所针对的最小效应量)
### 样本量检验
- **所需样本量**:每组 [N](在 80% 统计功效下检测 [X%] 的 MDE)
- **实际样本量**:每组 [N]
- **结论**:[统计功效充足 / 统计功效不足 / 统计功效过剩]
### 决策
**建议:[上线 / 延长 / 停止]**
[清晰说明原因,综合考量统计显著性与实际显著性]
### 业务影响估算
若上线至全量用户:
- **预期影响**:[每月/每季度的指标变化]
- **营收影响**:[如适用]
- **置信度**:[对该估算的确定程度]
### 注意事项
- [关于测试有效性的顾虑]
- [结果存在差异的用户分层]
- [需考虑的新奇效应或其他偏差]
### 后续行动
- [基于本次发现,下一步可测试的方向]
- [若上线实验组,监控计划]
第五步:提供后续行动选项
- "要我基于这些发现设计后续实验吗?"
- "要不要针对特定用户分层单独运行分析?"
- "要我生成 SQL,用于上线后持续监控该指标吗?"
注意事项
- 统计显著性 ≠ 实际显著性——数据量足够大时,0.1% 的提升可以达到统计显著,但不一定值得上线
- 结论可信之前,务必先检查样本比例失配(SRM)
- 新奇效应可能导致短期结果虚高——建议在上线后持续监控 2—4 周
- 如果测试统计功效不足,正确的结论通常是"延长测试"而非"无效果"
- 对于营收类指标,使用置信区间来估算最乐观和最悲观的业务影响
- 如果数据以 CSV 格式提供,使用 Python 的 scipy.stats 库执行完整分析
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.
- 7d ago First seen · 110 lines · 28 tokens per session scan A cf8913e6946a
analyze-test is a command published in the GitHub repository killvxk/pm-skills-zh (151 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,163 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.