Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Datanpx agentmods add skills/agentscope-ai/qwenpaw-data/bi-clusteringWrote 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-clustering)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-clustering"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-clustering/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-clustering"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-clustering.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 | $0.03519 |
| Opus 5 | $0.00053 | $0.01759 |
| Sonnet 5 | $0.00021 | $0.00704 |
| Haiku 4.5 | $0.00011 | $0.00352 |
Grade A, and why
bi-clustering 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-clustering
将特征相似或策略上需区分的业务对象（用户、产品、门店等）划为若干群组。根据分群分析的目的。
执行流程
1. 分群方法的选择
分析数据分析的目的和两种方法的适用场景，明确是使用波士顿矩阵法对分析对象进行分群还是应该使用聚类技术对分析对象完成分群。
| 路径 | 更合适_when | 说明 |
|---|---|---|
| 波士顿矩阵法 | 策略上需要 2×2 象限（如「增长×份额」「客流×客单」）、维度含义清晰、便于与经典业务框架对齐 | 每条轴上把对象划为「高/低」两档，得到四象限；解释成本低，适合汇报与策略分派 |
| 聚类 | 需要 多特征综合、簇数/形状事先不明确、或簇非球形/需标出噪声点 | 用距离与密度在特征空间划分；可选 K-means、分层聚类、DBSCAN（参见下文） |
若仅能在「简单四象限」与「多簇细划」之间二选一：优先波士顿当业务叙事依赖两个主轴；优先聚类当维度多、需数据驱动定簇结构。
2. 特征维度的确定
确定分群所依据的维度：若采用波士顿矩阵法，则确定两个象限用以分群；若采用聚类方法，则按需选择合适的分群特征。
实务上，波士顿路径需选定横轴、纵轴各一个指标且与目标一致；聚类路径需注意缺失、异常、量纲与类别编码（高基数类别慎用无约束 one-hot）。
3. 分群数据准备
查看数据，确认数据中包含在步骤 2 中确定的特征维度；然后，整理数据为 CSV 格式，数据包含一个分析对象列，和分群所需的特征维度，每个特征应该对应一个数据列。
补充：对象为行粒度，按需完成对象级汇总（如事件级先聚合到用户/产品）、缺失与异常处理；聚类路径下数值特征由脚本的 --scale 处理缩放。
4. 数据分群
a) 波士顿矩阵法
若象限对应数据是离散的，根据离散值将其分成两个区间；若象限对应数据是连续的，在连续轴上选定分界统计量（平均数或中位数），按该值将数据分成「≤ 分界 / > 分界」两个区间。完成象限划分后，将分析对象划分至各个象限。
说明：平均数对极端值敏感、中位数更稳健；横轴与纵轴可分别指定（脚本参数 --x-continuous-split / --y-continuous-split，值为 mean 或 median，默认均为 mean）。离散轴仍按有序取值前半/后半分为两档；auto 模式下由列类型与去重个数判定连续/离散（见脚本 --discrete-max-uniques）。结果中 stderr 的 axes: 一行在连续轴上会附带 :mean 或 :median。可向业务侧标注象限名称（如 Q1–Q4）并统计规模与指标概要。
分群结果保存为 json 文件。
使用 <skill-dir>/scripts/boston_quadrant.py 脚本完成数据的划分，如
python scripts/boston_quadrant.py \
--input-file data.csv \
--id-col user_id \
--x-col 市场份额 \
--y-col 增长率 \
--x-continuous-split mean \
--y-continuous-split median \
--output-json result.json
参数说明：
| 参数 | 说明 | 默认值 |
|---|---|---|
--input-file |
输入 CSV 路径 | （必填） |
--id-col |
分析对象唯一标识列 | （必填） |
--x-col / --y-col |
横轴、纵轴特征列各一列 | （必填） |
--x-mode / --y-mode |
该轴划分方式：auto | continuous | discrete |
auto |
--discrete-max-uniques |
auto 时：数值列去重个数 ≤ 此阈值则按离散轴处理 |
12 |
--x-continuous-split |
横轴为连续时：用 mean（均值）或 median（中位数）作分界，低为 ≤、高为 > |
mean |
--y-continuous-split |
纵轴为连续时：同上 | mean |
--output-json |
象限分群结果 JSON（格式见「输出结果」） | （必填） |
What ships with it
3 files 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 · 187 lines · 107 tokens per session scan A dcc118bd5953
bi-clustering 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 3,519 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…