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-cohorts)<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/analyze-cohorts"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/analyze-cohorts/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/commands/killvxk/pm-skills-zh/analyze-cohorts"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/analyze-cohorts.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 | $0.00020 | $0.00915 |
| Opus 5 | $0.00010 | $0.00458 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
analyze-cohorts 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 11d 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-cohorts -- 同期群分析
按同期群分析用户留存与参与度规律。上传数据或描述需求，即可获得留存曲线、功能采用趋势及可执行洞察。
调用方式
/analyze-cohorts [上传一份用户活动数据的 CSV 文件]
/analyze-cohorts 分析 1—6 月注册用户的月度留存率，按获客渠道分组
/analyze-cohorts 帮我为新手引导改版设计一套同期群分析方案
工作流程
第一步：接收数据或明确分析目标
两种路径：
- 有数据：用户上传包含用户级数据的 CSV/电子表格（user_id、signup_date、activity_date、event_type 等字段）
- 无数据：用户描述分析需求 → 生成 SQL 查询语句和分析框架
第二步：定义同期群
需确认：
- 同期群的划分依据是什么？（注册周/月、获客渠道、套餐等级、首次使用的功能）
- 留存事件是什么？（登录、核心操作、任意活动、购买）
- 时间粒度？（日、周、月）
- 时间范围？
第三步：执行分析
应用 cohort-analysis 技能：
若已提供数据：
- 使用 Python（pandas）处理数据，生成同期群表
- 按同期群、按周期计算留存率
- 绘制留存曲线
- 识别规律：上升/下降中的同期群、季节性效应、异常值
- 对比各同期群的功能采用情况
若描述分析需求：
- 设计同期群分析框架
- 生成数据提取所需的 SQL 查询
- 创建分析用模板电子表格
- 定义指标与可视化方案
第四步：生成报告
## 同期群分析：[描述]
**日期**：[今天]
**同期群定义**：[例如：注册月份]
**留存事件**：[例如：完成一个项目]
**时间粒度**：[周/月]
### 留存表
| 同期群 | 规模 | 第1周 | 第2周 | 第3周 | ... | 第12周 |
|------|------|-------|-------|-------|-----|--------|
### 核心发现
1. **[发现]** — [支撑数据]
2. ...
### 同期群对比
- **表现最佳的同期群**：[哪个，为何]
- **表现最差的同期群**：[哪个，为何]
- **趋势**：[随时间改善/下滑/平稳]
### 留存率基准对比
| 周期 | 你的留存率 | 行业基准 | 差距 |
|------|-----------|---------|------|
### 建议
1. [基于发现，需要调查或改进的方向]
2. ...
### 后续查询
[用于深度分析的 SQL 查询]
如果已提供数据，将分析结果保存为 Markdown 报告和 CSV/电子表格两种格式。
第五步：提供后续行动选项
- "要我按另一个维度进一步细分吗？"
- "要不要基于这些留存阈值设置指标告警？"
- "要我为留存最弱的同期群设计实验，帮助改善留存吗？"
注意事项
- 同期群分析的质量取决于留存事件的定义——应选择有意义的行为，而非仅仅是"登录"
- 早期同期群往往因早期用户偏差而表现不同——对比时请特别说明
- 如果留存计算用到了 Python 脚本，请保存脚本，方便用户在有新数据时重复运行
- 季节性效应可能伪装成趋势——若同期群差异可能源于日历因素，需主动标注
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.
- 11d ago First seen · 100 lines · 20 tokens per session scan A 920b03996cda
analyze-cohorts is a command published in the GitHub repository killvxk/pm-skills-zh (159 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 915 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.