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 agentscope-ai/QwenPaw-Data --skill bi-cohort-analysisgit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote 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/agentscope-ai/qwenpaw-data/bi-cohort-analysis)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-cohort-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-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/agentscope-ai/qwenpaw-data/bi-cohort-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-cohort-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.02177 |
| Opus 5 | $0.00053 | $0.01089 |
| Sonnet 5 | $0.00021 | $0.00435 |
| Haiku 4.5 | $0.00011 | $0.00218 |
Grade A, and why
bi-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 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-cohort-analysis
把用户按同一批/同一类分组，比较各群体后续表现：定义 cohort 规则 → 取数 → 划分 cohort → 按 cohort 汇总后续表现 → 跨 cohort 对比 → 解读与输出。
前置条件
开始执行前，确认以下信息已就绪：
- 分析对象明确，通常为「用户」，且能唯一标识（如
user_id） - cohort 规则已确定，即按什么分群（如注册周、获客渠道、首单金额档、首日行为等）
- 跟踪指标已确定，即 cohort 形成后要比较的后续指标（如留存、转化、LTV、复购等）及其时间窗口
- 数据获取能力可用，能取到对象级起始特征数据及对应后续行为/指标数据
若 cohort 规则或跟踪指标不明确，需先回到规划阶段补充，或向用户确认后再开始执行。
分析原则
同期群定义
同期群（cohort）指在相同时点或具备相同起始特征的用户集合。本 workflow 通过 cohort 规则分群 定义 cohort，再比较各 cohort 在 后续时间窗口 内的指标表现。
主要步骤
| 步骤 | 用途 | 是否必选 |
|---|---|---|
| 定义 cohort 规则 | 确定分群依据与跟踪指标 | 必选，见步骤 1 |
| 取数 | 取用户 ID、起始特征、后续行为/指标 | 必选，见步骤 2 |
| 划分 cohort | 将每个用户分到对应群体 | 必选，见步骤 3 |
| 汇总后续表现 | 按 cohort 聚合跟踪指标 | 必选，见步骤 4 |
| 跨 cohort 对比 | 对比各群差异、幅度与显著性 | 必选，见步骤 5 |
| 解读 & 输出 | cohort 画像、表现对比、业务建议 | 必选，见步骤 6 |
典型产出：cohort 矩阵、群间对比表、cohort 留存曲线（多条线对比）等。
最短路径：定义分群规则 → 划 cohort → 跟踪各群指标 → 跨群对比（即步骤 1 → 3 → 4 → 5，取数随分群展开）。
本 workflow 主要提供 cohort 场景下的编排与数据衔接逻辑，各步骤的具体执行按相应分析方法的标准流程进行。
1. 定义 cohort 规则
明确「按什么分群」与「跟踪什么指标」，这是后续取数与划分的基础：
| 要素 | 含义 | 常见取值 |
|---|---|---|
| 分群依据 | 划分 cohort 所依据的起始特征 | 注册周/注册月、获客渠道、首单金额档、首日关键行为、获客活动等 |
| 跟踪指标 | cohort 形成后要比较的后续指标 | 留存率、转化率、LTV、复购次数等 |
| 时间窗口 | 在哪些 dayn 观测跟踪指标 | D1/D7/D30 留存、30 日内 LTV、首周转化率等 |
要点：
- 分群依据可为单一维度（如注册周）或多维特征组合（如消费 + 活跃 + 渠道，优先走聚类，见步骤 3）
- 对象粒度须为「一行一用户」；若原始数据为事件级，先聚合到用户级
- 规则一旦确定，后续取数、划分、汇总须保持一致
2. 取数
按步骤 1 的规则取数，准备划分 cohort 与汇总后续表现所需的数据。
数据准备
整理 CSV，包含：
- 对象标识列（如
user_id） - 起始特征列：用于划分 cohort（如注册周、获客渠道、首单金额；多维聚类可有多列数值特征）
- 后续行为/指标列：用于汇总跟踪指标（如各 dayn 是否留存、是否转化、累计付费金额等）
示例：
user_id,注册周,获客渠道,D7是否留存,30日LTV
u001,2025-W01,自然量,1,128.0
u002,2025-W01,广告,0,0.0
后续指标若来自另一张表，可仅取用户 ID + 起始特征，待步骤 3 划分后再按 user_id 关联后续指标表。
3. 划分 cohort
以步骤 1 的规则为输入，将每个用户分到对应群体。
划分方式
- 按已有特征分群：以起始特征列（如注册周、获客渠道、首单金额档）为分组键，直接将用户归入对应 cohort
- 两维策略型分群（如「增长 × 份额」）：优先波士顿矩阵法
- 多维综合分群：优先 K-means / 分层聚类 / DBSCAN
分群结果保存为 JSON，键为 cohort 标识（如 "2025-W01"、"cluster 1"），值为该 cohort 内的用户 ID 列表（供步骤 4 按 user_id 关联）。
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 · 160 lines · 107 tokens per session scan A 54d7e7d659d4
bi-cohort-analysis is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (72 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 2,177 once invoked, about $0.0005 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
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…