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 cohort-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/cohort-analysis)<a href="https://agentmods.dev/skills/killvxk/pm-skills-zh/cohort-analysis"><img src="https://agentmods.dev/badge/skills/killvxk/pm-skills-zh/cohort-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/cohort-analysis"><img src="https://agentmods.dev/badge/skills/killvxk/pm-skills-zh/cohort-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 | $0.00058 | $0.01268 |
| Opus 5 | $0.00029 | $0.00634 |
| Sonnet 5 | $0.00012 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
cohort-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 10d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
同期群分析与留存探查
用途
通过同期群分析用户参与度和留存规律，识别用户行为、功能采用及长期参与度的趋势。将定量洞察与定性研究建议相结合。
工作原理
第一步：读取并验证数据
- 接受包含用户同期群信息的 CSV、Excel 或 JSON 数据文件
- 验证数据结构：同期群标识符、时间周期、参与度指标
- 检查缺失值和数据质量问题
- 汇总关键统计信息（同期群规模、日期范围、可用指标）
第二步：生成定量分析
- 计算同期群留存率和参与度趋势
- 识别留存曲线、流失节点和异常值
- 计算各同期群的功能采用率
- 计算环比或周期性变化
- 如有需要，使用 pandas 和 numpy 生成 Python 分析脚本
第三步：创建可视化图表
- 生成留存热力图（同期群 vs. 时间周期）
- 创建展示同期群走势的折线图
- 构建功能采用率对比图
- 可视化流失节点和参与度趋势
- 输出为交互式图表或静态图片
第四步：识别洞察与规律
- 发现一个或多个显著规律：
- 特定同期群的早期高流失
- 后期参与度变化
- 功能采用的聚类特征
- 季节性或时间性趋势
- 突出意外发现和偏差
- 与基准线进行同期群绩效对比
第五步：建议后续研究方向
- 推荐定性研究方法：
- 与流失用户进行针对性访谈
- 对高活跃同期群开展功能使用调研
- 回放关键交互模式的会话录屏
- 对高留存 vs. 低留存同期群进行赢/输分析
- 设计后续定量研究
- 建议 A/B 测试或功能实验
使用示例
示例一：上传 CSV 数据
上传 cohort_engagement.csv，包含以下字段：cohort_month、weeks_active、
user_id、feature_x_usage、engagement_score
需求："分析留存规律，并找出 Q4 2025 同期群为何相比 Q3 表现欠佳"
示例二：描述数据格式
"我有 2025 年 1—12 月的月度用户同期群。每行包含：
同期群日期、用户 ID、购买频次和客服工单数量。
分析哪些同期群的长期留存率最高。"
示例三：功能采用分析
上传包含同期群采用数据的 feature_usage.xlsx。
需求："对比各同期群新功能的采用曲线。
哪些同期群采用速度最快？有什么规律？"
核心能力
- 数据读取：导入 CSV、Excel、JSON、SQL 查询结果
- 留存分析：计算并可视化随时间变化的留存率
- 同期群对比：跨同期群对比各项指标
- 异常检测：标记异常规律或流失节点
- Python 脚本：生成可复用的分析代码，支持持续分析
- 可视化：创建热力图、图表和交互式数据看板
- 研究设计：建议针对性的后续研究和访谈方案
- 统计摘要：提供定量指标和相关性分析
最佳实践建议
- 包含时间维度：提供跨多个时间周期的数据
- 明确定义同期群：清楚说明同期群的划分依据（注册月份、功能上线日期等）
- 提供背景信息：说明该时期内的产品变更、上线内容或重要事件
- 多维指标：包括留存率、参与度、功能使用情况、营收等
- 充足数据量：至少 3—4 个同期群，才能发现有意义的规律
- 明确输出要求：注明需要可视化图表、Python 脚本还是研究建议
输出格式
你将收到：
- 数据摘要：同期群概览和数据质量评估
- 定量发现：关键指标、留存率及趋势分析
- 可视化图表：展示留存曲线和采用规律的图表
- 规律识别：从数据中提炼的 2—3 个重要洞察
- 研究建议：具体的定性与定量后续研究方向
- 分析脚本（如有需要）：可复现分析的 Python 代码
- 后续行动：基于发现的优先级行动清单
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.
- 10d ago First seen · 114 lines · 58 tokens per session scan A 24426cadaebc
cohort-analysis is a skill published in the GitHub repository killvxk/pm-skills-zh (158 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,268 once invoked, about $0.0003 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…