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-causal-attributiongit 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-causal-attribution)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-causal-attribution"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-causal-attribution/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-causal-attribution"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-causal-attribution.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 | $0.00076 | $0.03274 |
| Opus 5 | $0.00038 | $0.01637 |
| Sonnet 5 | $0.00015 | $0.00655 |
| Haiku 4.5 | $0.00008 | $0.00327 |
Grade A, and why
bi-causal-attribution 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-causal-attribution
从外部证据源（运营周报、活动记录、产品发布文档、对话输入等）中发现业务事件，与指标异常时间窗口对齐，生成有证据支撑的因果归因假设并按可信度排序。
与相邻归因技能的关系：
| 技能 | 回答的问题 | 输入 |
|---|---|---|
bi-attribution-analysis |
哪个维度对指标变动贡献了多少（量化） | 结构化 CSV |
bi-causal-attribution（本技能） |
为什么发生这种变动（因果） | 外部文档证据 |
bi-time-impact-attribution |
已知具体事件后，量化其影响度 | 结构化事件列表 |
典型场景：
- "人均GAAP这周为什么下降了" → 已有异常检测结论，需从周报/活动记录中找原因
- "企业用户 Token 消耗为什么上月明显增长" → 结合产品发布记录和运营文档解释驱动因素
前置条件
开始前确认以下信息已就绪：
- 指标异常信息：异常指标名称、时间窗口（起止日期）、变动方向（上升/下降）、变动幅度，来自
bi-anomaly-detection输出或用户描述 - 受影响维度（可选）：已定位的关键维度（组）值，来自
bi-attribution-analysis或bi-dimension-drilldown；若无则留空，维度吻合度评分将降级为中性值 - 证据源：至少一种可用的证据来源（见步骤 2）
若异常信息不完整，需先调用 bi-anomaly-detection 获取。
执行步骤
1：构建异常锚点
整理指标异常的关键信息，作为后续事件匹配的基准，落盘至 data/processed/anomaly_anchor.csv：
| 字段 | 说明 | 示例 |
|---|---|---|
| 指标名 | 发生异常的指标 | 国内人均GAAP |
| 异常开始日期 | 异常时间窗口起始 | 2026-06-08 |
| 异常结束日期 | 异常时间窗口结束 | 2026-06-14 |
| 变动方向 | 上升 / 下降 / 波动 |
下降 |
| 变动幅度 | 环比/同比变化值或百分比 | -12% |
| 关键维度 | 已定位的受影响维度值（选填） | 企业用户 |
2：证据源接入
支持以下两类证据源，可同时使用：
2a. 对话输入 / 文件上传
证据直接出现在对话上下文或用户上传的文件中，包括：
- 运营周报（文字粘贴或文档上传）
- 营销活动计划表
- 产品发布记录
- 用户直接描述的业务事件（如"这周 618 活动在做折扣"）
处理方式：从对话上下文或文件内容中直接提取，无需额外接口调用，进入步骤 3。
2b. 文档工具 API
通过工具调用从外部系统检索业务事件信息（如活动日历接口、产品发布记录接口）。
查询时，以异常时间窗口为中心，向前扩展 7 天构建检索范围，覆盖事件通常在指标变动前已发生的情况：
检索范围 = [异常窗口开始日期 - 7天, 异常窗口结束日期]
按以下优先级取值，命中即停：
| 优先级 | 来源 | 示例 |
|---|---|---|
| 1 | 用户显式指定的接口/工具 | 用户要求"查一下活动日历接口" |
| 2 | 域知识包（若存在） | 域知识包指定活动记录接口名称 |
| 3 | 语义层接口（若可用） | 通过语义层查询业务事件配置 |
若两类来源均可用，合并结果并去重（按事件名称+时间去重）；若均不可用，终止执行并提示用户提供证据源。
3：事件提取与标准化
对每份证据内容，提取其中描述的业务事件，按以下字段标准化，落盘至 data/processed/extracted_events.csv：
| 字段 | 说明 | 示例 |
|---|---|---|
| 事件名称 | 简洁描述事件 | 618活动折扣 |
| 开始日期 | 事件生效起始（不确定则留空，推断值需加 [推测]） |
2026-05-22 |
| 结束日期 | 事件生效结束（持续中则填异常窗口末尾，留空规则同上） | 2026-06-22 |
| 预期方向 | 事件对目标指标的预期效果：正向 / 负向 / 双向 / 不确定 |
双向 |
| 影响维度 | 事件主要影响的用户群或业务维度（不确定则留空） | 企业用户 |
| 来源类型 | 结构化文档 / 周报 / 对话输入 |
周报 |
| 原文摘要 | 支撑提取结论的原文片段（100字以内） | "【来源原文节选，100字以内，直接引用，不改写】" |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 246 lines · 76 tokens per session scan A 7b33b426af6b
bi-causal-attribution is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (72 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 3,274 once invoked, about $0.0004 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
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
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.
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…