Vector Cluster
ruvnet/ruflo
Cluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)
对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。
Apache-2.0Auto-check passed
Install Bi Clustering
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clustering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .claude/skills/bi-clustering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .claude/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clusteringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clustering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .agents/skills/bi-clustering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .agents/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clustering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .cursor/skills/bi-clustering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .cursor/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentscope-ai/QwenPaw-Data.git --path packages/qwenpaw-data-skills/skills/atomic/bi-clustering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clustering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .gemini/skills/bi-clustering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .gemini/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clusteringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .github/skills/bi-clustering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .github/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-clustering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-clustering .opencode/skills/bi-clustering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bi-clustering" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/atomic/bi-clustering into .opencode/skills/bi-clustering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-clustering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
bi-clustering- GitHub stars
- 127
- Token cost
- ~1.6k tokens
- SKILL.md length
- 356 words
- Files
- 4 (incl. scripts)
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。
- Works in 5 steps: 分群方法的选择 → 特征维度的确定 → 分群数据准备 → …
- SKILL.md covers 执行流程, 输出结果 and 注意事项
- Runs Python scripts from its folder; calls python
What it does
Bi Clustering is an agent skill from agentscope-ai/QwenPaw-Data. 对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/boston_quadrant.py`, `scripts/clustering.py` and `scripts/json_groups.py`).
The repository describes itself as: Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host). The licence is Apache-2.0.
Example prompts
- “/bi-clustering”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e0bae36. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bi Clustering loads about 1.6k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 356 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from agentscope-ai/QwenPaw-Data at commit e0bae36, republished under its Apache-2.0 licence (© agentscope-ai). 356 words, ~1,568 tokens.
Download SKILL.mdSave it as
.claude/skills/bi-clustering/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- bi-clustering
- description
- 对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。
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） |
b) 聚类分析
聚类方法选择：
| 方法 | 适用场景 | 适合的数据类型 / 形态 |
|---|---|---|
| K-means | K 可预估或可试算；簇大致球形、规模相近；样本量大、需快速迭代 | 主要为连续数值（脚本内会按 --scale 处理）；对离群点敏感 |
| 分层聚类 | 需要树状结构或 K 不固定、多层解读；样本量中等 | 数值矩阵 + 选定距离/连接法（脚本中欧氏 + linkage） |
| DBSCAN | 簇数未知；形状任意、密度不均；需显式噪声/未分类 | 调节 eps、min_samples；高维时距离区分度可能下降 |
使用聚类脚本：
使用 <skill-dir>/scripts/clustering.py执行聚类，分群结果保存为 json 文件。脚本调用示例如下，
python scripts/clustering.py \
--input-file data.csv \
--id-col user_id \
--feature-cols 年龄 消费金额 访问次数 \
--method kmeans \
--n-clusters 5 \
--output-json result.json调优示例（K-means 按轮廓系数选 K；--output-json 仍必填，写出最终簇划分）：
python scripts/clustering.py \
--input-file data.csv \
--id-col user_id \
--feature-cols 年龄 消费金额 访问次数 \
--method kmeans \
--tune \
--k-min 2 \
--k-max 10 \
--output-json result.json \
--tuning-report-file ./out/tune.jsonDBSCAN 调优示例（--tune 时必须同时提供 --tune-eps 与 --tune-min-samples）：
python scripts/clustering.py \
--input-file data.csv \
--id-col user_id \
--feature-cols f1 f2 \
--method dbscan \
--tune \
--tune-eps 0.3,0.5,0.8,1.2 \
--tune-min-samples 3,5,10 \
--max-noise-ratio 0.35 \
--output-json result.json \
--tuning-report-file ./out/tune.json聚类脚本参数说明
| 参数 | 含义 | 默认 |
|---|---|---|
--input-file | 输入 CSV 路径 | （必填） |
--id-col | 分析对象唯一标识列名 | （必填） |
--feature-cols | 参与聚类的数值特征列名，多个列名以空格分隔（脚本内 pd.to_numeric） | （必填） |
--method | kmeans | hierarchical | dbscan | （必填） |
--output-json | 聚类分群结果 JSON 路径 | （必填） |
--scale | 聚类前特征缩放：standard | minmax | none | standard |
--random-state | K-means 随机种子 | 42 |
--n-init | K-means n_init | 10 |
--n-clusters | K-means / 分层聚类的簇数 K；未使用 --tune 时与上述方法搭配为必填 | 无 |
--linkage | 分层聚类连接法：ward、complete、average、single | ward |
--eps | DBSCAN 邻域半径；未使用 --tune 时与 --min-samples 同时必填 | 无 |
--min-samples | DBSCAN min_samples；未使用 --tune 时与 --eps 同时必填 | 无 |
--skip-drop-na | 含 NaN 的特征行不丢弃（需 --fill-mean 或数据已无 NaN） | 默认会丢弃含 NaN 行 |
--fill-mean | 用列均值填补特征中的 NaN | 关闭 |
--centroids-file | 若指定且为 K-means：另写出质心 CSV（列为 --feature-cols，与聚类一致的缩放后空间；并带 cluster_label） | 无 |
--tune | 开启超参搜索：K-means/分层按轮廓系数选 K（分层可同时试多种 --tune-linkages）；DBSCAN 在非噪声点上算轮廓且受 --max-noise-ratio 约束 | 关闭 |
--k-min / --k-max | K-means / 分层在 --tune 时的 K 搜索范围 | 2 / 10 |
--tune-linkages | 分层 --tune 时要尝试的连接法列表（每项为 ward 等） | 仅用当前 --linkage |
--tune-eps | DBSCAN --tune 必填：逗号分隔的 eps 候选，如 0.3,0.5,0.8 | 无 |
--tune-min-samples | DBSCAN --tune 必填：逗号分隔的 min_samples 候选，如 3,5,10 | 无 |
--max-noise-ratio | DBSCAN --tune 时：噪声占比超过该值的参数组合被淘汰 | 0.35 |
--tuning-report-file | 可选：写出调优过程与最终选中超参数的 JSON（不是分群 ID 列表文件） | 无 |
Show full SKILL.md (73 more words)Show less
拟合后结合写出的 JSON 汇报各簇（及噪声）规模、方法与全部关键超参数，并做业务解读。
5. 报道结果（两类路径共用）
必备内容：
- 输出物：主结果
--output-json文件路径（及调优 JSON 若使用）；可得自脚本的 stderr 相对路径与 stdout 中的 JSON 内容 - 数据与特征：对象粒度、样本量、特征列表、预处理（缺失、标准化、编码）
- 方法与参数：波士顿两轴定义与分割规则（连续轴的 mean/median 与离散分档）；或聚类方法理由与全部关键超参数
- 群组规模：各象限或各簇的样本量、占比；DBSCAN 单独汇报噪声数量与占比
- 群组画像：相对总体或跨组的业务指标/特征对比；避免仅有算法指标而无业务解释
- 稳定性与局限（视情况）：参数微扰或随机种子对标签的影响；高维、小样本对结论的影响
质量检查
- 行粒度与「一个待分群对象」一致
- 波士顿：两维分割规则在文档中一致且可复现
- 聚类：连续特征缩放策略明确；方法与数据形态匹配
- 各象限/簇规模可解释，结论能指向可执行动作
输出结果
分群/聚类结果以 JSON 格式呈现，包含以下字段和对应的聚类结果：
- 聚类（
clustering.py）：键为"cluster 1"、"cluster 2"、…（对应sklearn簇标签0、1、…）；DBSCAN 中标签-1的样本归入"noise"（仅当存在噪声点时才有此键）。仅当簇内至少有一个对象时才出现对应键，不会出现空数组的簇键。 - 波士顿象限（
boston_quadrant.py）：恒包含"cluster 1"～"cluster 4"四键（象限含义见该脚本文件头注释），某象限无对象时值为[]。连续轴分界可为 均值（mean） 或 中位数（median）；运行结束后 stderr 中axes:一行对连续轴会附带:mean或:median，便于核对所用规则。
聚类另可选用 --tuning-report-file 写出调优网格与选中超参数的 JSON，与上述「ID 分组」主结果文件相互独立。
注意事项
- 可解释性：无监督分群的组是否业务上有意义，需结合画像与验证；不宜单凭轮廓系数定成败。
- 高维：维度过高时距离趋于均匀；可考虑特征选择或领域驱动子集。
- 公平与合规：分群若用于差异化策略，需遵守隐私与反歧视相关规范。
© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts) in packages/qwenpaw-data-skills/skills/atomic/bi-clustering of agentscope-ai/QwenPaw-Data.
- SKILL.md
- scripts/boston_quadrant.py
- scripts/clustering.py
- scripts/json_groups.py
Open the folder on GitHubat commit e0bae36
Compare with similar skills
Bi Clustering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bi Clustering this skillagentscope-ai/QwenPaw-Data | 127 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Vector Clusterruvnet/ruflo | 74k | — | ~540 | Automated safety check: Notes | MIT | |
| Exploring LLM ClustersPostHog/posthog | 40k | — | ~3.1k | Automated safety check: Pass | Custom licence | |
| SEO Keyword ClusteringAgriciDaniel/claude-seo | 19k | 2 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Exploring MCP Intent ClustersPostHog/posthog | 40k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Running Clustering Algorithmsjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Exploring LLM Clusters
PostHog/posthog
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
SEO Keyword Clustering
AgriciDaniel/claude-seo
Clusters keywords by how much their search results overlap and designs a hub-and-spoke content plan with an internal link matrix and an interactive cluster map.
- Official
Exploring MCP Intent Clusters
PostHog/posthog
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent…
Running Clustering Algorithms
jeremylongshore/tons-of-skills-marketplace
Analyze datasets by running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups.
- Official
Gke Cluster Autoscaler
google/skills
Trigger on mention of GKE cluster autoscaler, node autoscaling, node pool auto-creation / node auto-provisioning.
More from agentscope-ai/QwenPaw-Data
All 29 skills in this repoBi Report Generation
agentscope-ai/QwenPaw-Data
将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.
Fetch Data
agentscope-ai/QwenPaw-Data
取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL，经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发：(1) 直接索要指标或记录，如「DAU 多少」「上月销售额」「3…
Bi Adaptive Threshold
agentscope-ai/QwenPaw-Data
通过量化历史数据的自然波动幅度，自适应计算判定阈值。当需要从数据本身确定阈值（如波动阈值、影响度阈值等）、而非使用固定值时调用。仅适用于日/周粒度阈值确定。
Bi Anomaly Detection
agentscope-ai/QwenPaw-Data
基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用. An agent skill from agentscope-ai/QwenPaw-Data.
Bi Attribution Analysis
agentscope-ai/QwenPaw-Data
计算各维度（组）值对指标变动的贡献度，支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。
Bi Causal Attribution
agentscope-ai/QwenPaw-Data
从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件，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排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。
Questions about Bi Clustering
What does Bi Clustering do?
对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。. Bi Clustering is an agent skill from agentscope-ai/QwenPaw-Data.
How do I install Bi Clustering in Claude Code?
Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a claude-code`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/atomic/bi-clustering in agentscope-ai/QwenPaw-Data) into .claude/skills/bi-clustering in your project. Claude Code loads it when a task matches its description.
How do I install Bi Clustering in Codex?
Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a codex`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/atomic/bi-clustering in agentscope-ai/QwenPaw-Data) into .agents/skills/bi-clustering in your project. Codex loads it when a task matches its description.
Can I use Bi Clustering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-clustering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bi-clustering, .gemini/skills/bi-clustering, .github/skills/bi-clustering and .opencode/skills/bi-clustering in your project.
What does Bi Clustering need to run?
Going by SKILL.md and its folder, Bi Clustering needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Bi Clustering access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Bi Clustering safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Bi Clustering use?
Bi Clustering is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Bi Clustering use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Bi Clustering?
Skills that share tags, products or a category with Bi Clustering: Vector Cluster (ruvnet/ruflo, 74k stars), Exploring LLM Clusters (PostHog/posthog, 40k stars), SEO Keyword Clustering (AgriciDaniel/claude-seo, 19k stars) and Exploring MCP Intent Clusters (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bi Clustering?
agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw-Data, which has 127 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 5, 2026.
Source: agentscope-ai/QwenPaw-Data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.