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-retention-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-retention-analysis)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-retention-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-retention-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-retention-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-retention-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 | $0.00142 | $0.02589 |
| Opus 5 | $0.00071 | $0.01295 |
| Sonnet 5 | $0.00028 | $0.00518 |
| Haiku 4.5 | $0.00014 | $0.00259 |
Grade A, and why
bi-retention-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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-retention-analysis
对留存执行完整的分析流程，核心目标是算清楚用户留不留、留多少、有没有变化：定义口径 → 取数 → 计算留存率 →（可选）拆分维度 →（可选）对比/归因 → 解读与输出。
前置条件
开始执行前，确认以下信息已就绪：
- 留存锚点明确，即作为 day0 的起算时间点（如注册日、首次访问、首次付费等）已定义
- 留存事件已确定，即衡量「留下来」的行为（如再次访问、再次使用、再次付费等）口径清晰
- 留存窗口已确定（如次日、7 日、30 日等），对应 day0 / dayn 口径清晰
- 数据获取能力可用，能取到计算留存率所需的 CSV 或等价数据
- 分析范围明确，包括时间窗口、对象范围，以及是否需要拆分维度或做对比
若留存锚点、留存事件或留存窗口不明确，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
主要步骤
| 步骤 | 用途 | 是否必选 |
|---|---|---|
| 定义口径 | 确定锚点、留存事件、留存窗口 | 必选，见步骤 1 |
| 取数 | 按口径取 day0 / dayn 数据 | 必选，见步骤 2 |
| 计算留存率 | 计算 day0 用户在 dayn 的留存率 | 必选，见步骤 3 |
| 拆分维度 | 按渠道、端、国家、版本等分别计算 | 可选，见步骤 4 |
| 对比/归因 | 跨时间、群体等维度对比留存差异 | 可选，见步骤 5 |
| 解读 & 输出 | 留存曲线、关键节点、变化趋势、差异结论 | 必选，见步骤 6 |
典型产出：留存率表、留存曲线、分维度留存对比。
最短路径：定义口径 → 取数 → 算留存率 → 看曲线 / 报数字（即步骤 1 → 2 → 3 → 6，跳过步骤 4、5）。
本 workflow 主要提供留存分析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. 定义口径
明确留存分析的三要素，这是后续取数与计算的基础：
| 要素 | 含义 | 常见取值 |
|---|---|---|
| 锚点（day0） | 用户被纳入留存统计的起算时间点 | 注册日、首次访问、首次付费等 |
| 留存事件 | 衡量「留下来」的目标行为 | 再次访问、再次使用、再次付费等 |
| 留存窗口 | 在锚点后第几天考察留存 | 次日（D1）、7 日（D7）、30 日（D30）等 |
要点：
- 同一分析可包含多个留存窗口（如同时看 D1/D7/D30 以绘制留存曲线）
- 同一分析可包含多种留存事件（如访问留存 vs 使用留存），需分别定义口径
- 口径一旦确定，后续取数、计算、对比须保持一致，避免分子分母错配
2. 取数
按步骤 1 确定的口径取数，准备留存率计算所需的数据。
数据准备
整理 CSV，包含：
- 第 0 天用户数（分母，即锚点当日纳入统计的用户数，如当日新增用户数、当日首次访问用户数）
- 第 n 天留存用户数（分子，即上述用户在 dayn 仍触发留存事件的用户数）
- 如需多个留存窗口或多种留存事件，分别取对应的分子列
示例：
date,当日新增用户数,次日访问用户数,7日访问用户数
2025-01-01,10000,3000,1500
2025-01-02,10500,3200,1600
若计划在步骤 4 拆分维度，取数时一并带出维度列（如渠道、端、国家、版本），或按维度分别取数。
3. 计算留存率
计算 day0 用户在后续第 n 天的留存率。
计算执行
- 对每个需要报告的留存率指标（如次日留存、第 7 日留存、访问留存 vs 使用留存）按留存率公式（dayn 留存用户数 / day0 用户数）或可用脚本进行计算
- 不遗漏任何必要的留存窗口与留存事件
- 多窗口时，输出可绘制留存曲线的结果（如 D1/D3/D7/D14/D30 各点留存率）
- 保存计算结果
若已规划拆分维度，可在此步先算整体留存率，维度拆分在步骤 4 展开。
4. （可选）拆分维度
根据分析要求，判断是否需要按维度分别计算留存率：
需要拆分 → 按维度分别计算，完成后进入步骤 5 无需拆分 → 跳过本步骤，直接进入步骤 5（最短路径在此跳过）
判断依据
| 信号 | 示例 |
|---|---|
| 按已有维度拆分 | 「按渠道/端/国家/版本看留存」（维度已在数据中，直接分组计算） |
| 需发现未知用户子结构 | 「哪些用户群体留存更高」「用户自然分群后的留存差异」（走聚类分群） |
| 多维特征综合分群 | 需结合多个用户属性（消费、活跃、渠道等）划分群体再算留存（走聚类分群） |
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 · 186 lines · 142 tokens per session scan A b5e1756de3be
bi-retention-analysis is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (72 stars, last pushed today), licensed Apache-2.0. It adds 142 tokens to every session and 2,589 once invoked, about $0.0007 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…