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-dimension-drilldowngit 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-dimension-drilldown)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-dimension-drilldown"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-dimension-drilldown/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-dimension-drilldown"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-dimension-drilldown.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 | $0.00065 | $0.01444 |
| Opus 5 | $0.00032 | $0.00722 |
| Sonnet 5 | $0.00013 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
bi-dimension-drilldown 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-dimension-drilldown
对指标按归因维度逐层下拆,通过单维度扫描、交叉分析和层级下钻,定位驱动指标变动的关键维度(组)值。
典型场景:
- 用户要求"按渠道拆一下 DAU 的贡献度"
- 异动分析流程中,异常检测发现异常后需要定位原因
前置检查
开始前确认以下信息已明确:
- 下拆指标:需要下拆的指标及其类型(量值 / 率值 / 加权平均)
- 归因拆解维度:下拆的维度列表及其层级关系(哪些是 0 级平级维度,哪些有父子关系)
- 分布指标(可选):需要展示分布占比的重点指标
执行步骤
1:数据准备
根据前置检查确认的指标和维度,准备包含往期和当期数据的 CSV 文件,至少包含以下列:
| 列 | 说明 | 示例 |
|---|---|---|
| 维度列 | 所有涉及的归因拆解维度(每个维度一列,可能多列) | 渠道、端类型 |
| 往期值列 | 下拆指标的往期值 | DAU_往期 |
| 当期值列 | 下拆指标的当期值 | DAU_当期 |
| 分布指标列 | 分布指标值(可选,有分布指标时需要) | 访问用户数 |
若上游步骤已产出可用数据文件则直接使用,否则自行取数。
2:维度下拆
在每一步下拆中,针对当前拆解的维度(组),计算:
- 贡献度(相对于下拆指标):各维度(组)值对该下拆指标整体变动的贡献大小
- 分布占比(相对于需要展示占比的分布指标):各维度(组)值在分布指标整体中的比例
按以下步骤逐步拆解:
2.1 单维度扫描
对每个 0 级归因维度逐一执行贡献度计算和分布占比计算,筛选贡献度 Top-N 的维度值,记异常维度值集合为 D1。
2.2 交叉分析(平级维度)
若 D1 中多个平级维度同时出现异常维度值:
- 将 D1 中的异常维度两两组合
- 对每个组合执行贡献度计算和分布占比计算,筛选贡献度 Top-N 的维度组合,记异常维度组合集合为 D2
若只有一个维度出现异常,跳过此步。
2.3 层级下钻(层级维度)
取 D2(若存在)或 D1 中的异常维度(组),沿层级关系逐级向下拆解:
- 对异常维度值,找到其下一级子维度
- 在该异常维度值的数据范围内,执行贡献度计算和分布占比计算,筛选 Top-N
- 继续向下拆解(0 级 → 1 级 → 2 级 → ...),直到无更下级维度
每一级的下拆结果都保留,用于最终汇总。
补充说明:
- 默认参数:若用户未要求或其他源未指定,默认 N = 3
- 正负分离判断:默认按整体贡献度排序;当某方向变动量超过整体变动的 30% 时,说明正负抵消严重,需分别筛选正/负贡献度 Top-N
示例:下拆指标为 DAU(日活跃用户数),分布指标为访问用户数,0 级归因维度有"渠道"和"端类型","渠道"下有 1 级子维度"子渠道"。
- 单维度扫描:分别按"渠道"和"端类型"下拆 DAU,发现"渠道=自然流量"贡献度 +45%、"端类型=APP"贡献度 +30%,同时计算各维度值的访问用户数分布占比。两个维度均出现异常 → D1 = {渠道:自然流量, 端类型:APP}
- 交叉分析:"渠道"与"端类型"是平级维度,按"渠道 × 端类型"组合下拆,发现"自然流量 × APP"组合贡献度 +38% → D2 = {自然流量 × APP}
- 层级下钻:"渠道"下有子维度"子渠道",在"自然流量 × APP"这个组合下继续按"子渠道"下拆,发现"子渠道=搜索引擎"贡献度 +32%,最终定位到异常来源
3:汇总下拆结果
将各层级的下拆结果汇总输出。示例:
单维度扫描(渠道):
维度值 DAU贡献度 访问用户数占比
自然流量 +45% 52.3%
付费投放 -12% 28.1%
单维度扫描(端类型):
维度值 DAU贡献度 访问用户数占比
APP +30% 61.5%
Web +15% 38.5%
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 · 115 lines · 65 tokens per session scan A 4a19ca029534
bi-dimension-drilldown is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (72 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,444 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
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…