Updated today
by agentscope-ai
QwenPaw-Data
Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)
136 GitHub stars (136)
+42 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | +11 |
| Oct 6 | +4 |
| Oct 7 | +3 |
| Oct 8 | 0 |
| Oct 9 | +11 |
| Oct 10 | +3 |
| Oct 11 | +3 |
| Oct 12 | +1 |
| Oct 13 | +1 |
| Oct 14 | +2 |
| Oct 15 | +1 |
| Oct 16 | +2 |
- 30 skills (30 skills found in its SKILL.md files)
- 25 forks (25 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add agentscope-ai/QwenPaw-Data
Asks which skills and agents to install. Just one: npx skills add agentscope-ai/QwenPaw-Data --skill qwenpaw-data-cli — add -g for every project.
Claude Code
git clone https://github.com/agentscope-ai/QwenPaw-Datacp -r "QwenPaw-Data/skills/qwenpaw-data-cli" ~/.claude/skills/
Copies the qwenpaw-data-cli skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add agentscope-ai/QwenPaw-Data
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 32 files.
-
qwenpaw-data-cli
指导外部自动化 agent 使用 QwenPaw Data CLI 发现 Data Bridge 数据源、通过自然语言规划与执行数据分析任务、复用 SOP YAML，并根据流式输出、执行摘要和错误信息验收结果。用于需要调用本地 `qwenpaw-data` 命令完成数据任务、选择 `run` 或 `plan`/`execute`、传入 `--datasource-id`、处理长任务输出或排查 CLI 失败的场景。
skills/qwenpaw-data-cli/SKILL.md on GitHub (opens in a new tab) -
bi-adaptive-threshold
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。
packages/qwenpaw-data-skills/skills/atomic/bi-adaptive-threshold/SKILL.md on GitHub (opens in a new tab) -
bi-anomaly-detection
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。
packages/qwenpaw-data-skills/skills/atomic/bi-anomaly-detection/SKILL.md on GitHub (opens in a new tab) -
bi-attribution-analysis
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。
packages/qwenpaw-data-skills/skills/atomic/bi-attribution-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-causal-attribution
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。
packages/qwenpaw-data-skills/skills/atomic/bi-causal-attribution/SKILL.md on GitHub (opens in a new tab) -
bi-clustering
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。
packages/qwenpaw-data-skills/skills/atomic/bi-clustering/SKILL.md on GitHub (opens in a new tab) -
bi-comparison-analysis
对不同时间、群体、地区、渠道、版本之间的指标差异性的定量分析。触发条件：当分析任务需要通过定量比较多个对象来进行分析时触发，例如，对话包含“分析差异”、“衡量增长/下降”、“评估优劣/一致性“、“对比“等相似词语时触发。
packages/qwenpaw-data-skills/skills/atomic/bi-comparison-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-conversion-rate
从接触目标行为到完成目标行为的转化率计算。触发条件：需计算转化率时触发，如对话包含“转化率”、“转化情况”等词时触发。
packages/qwenpaw-data-skills/skills/atomic/bi-conversion-rate/SKILL.md on GitHub (opens in a new tab) -
bi-dashboard-generation
将 BI 数据分析结果构建为可筛选的交互式 HTML 看板。触发条件：① 用户显式要求「给我看板」时无条件触发；② 取数结果满足以下任一时自动触发——结果集行数>10行、存在可筛选维度（产品线/地域/时间粒度等）、涉及多张表数据、时序跨度长。
packages/qwenpaw-data-skills/skills/atomic/bi-dashboard-generation/SKILL.md on GitHub (opens in a new tab) -
bi-dimension-drilldown
对指标按维度逐层下拆，通过单维度扫描、交叉分析和层级下钻定位关键维度（组）值。当需要知道"从哪些维度拆解、按什么顺序拆解来定位指标变动来源"时调用。
packages/qwenpaw-data-skills/skills/atomic/bi-dimension-drilldown/SKILL.md on GitHub (opens in a new tab) -
bi-distribution-analysis
分析观测数据在不同区间维度上的分布特征。触发条件：当任务强调数据分布特征分析时调用，如出现“数据分布”、“分布情况”等词时触发。
packages/qwenpaw-data-skills/skills/atomic/bi-distribution-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-funnel-analysis
转化漏斗分析，构建产品链路转化漏斗、计算每步转化率、识别卡点、对比行业基准。触发条件：当需要分析多段行为的转化情况时触发，如对话涉及“漏斗”、“转化漏斗”、“阶段A-阶段B-阶段C转化情况”等相近词语时触发。
packages/qwenpaw-data-skills/skills/atomic/bi-funnel-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-ltv-analysis
评估单个用户或用户群体在生命周期内创造的收益。触发条件：当需要用户生命周期价值计算与分析时触发，如对话中涉及“LTV”、“LTV 分析”、“用户生命周期价值”、“人均收益测算”等等相近词语时调用。
packages/qwenpaw-data-skills/skills/atomic/bi-ltv-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-metric-observation
获取并计算指标的基础观测数据，包括时间周期确定、指标聚合、衍生指标计算和维度交叉展示表构建。当需要对指标进行基础数据观测、获取当期值与变动幅度时调用。
packages/qwenpaw-data-skills/skills/atomic/bi-metric-observation/SKILL.md on GitHub (opens in a new tab) -
bi-new-dimension-analysis
识别新增维度值并评估其在北极星指标上的表现。当归因维度出现新增值（如新渠道、新品类、新功能）需要评估效果时调用。
packages/qwenpaw-data-skills/skills/atomic/bi-new-dimension-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-report-generation
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。
packages/qwenpaw-data-skills/skills/atomic/bi-report-generation/SKILL.md on GitHub (opens in a new tab) -
bi-retention-rate
用户留存率计算，计算用户首次进入产品或首次完成关键行为后，后续回访或持续活跃的比例。触发条件：需计算用户留存率时触发，如观测次日留存率、观测第七日留存率等。
packages/qwenpaw-data-skills/skills/atomic/bi-retention-rate/SKILL.md on GitHub (opens in a new tab) -
bi-time-impact-attribution
将累加型量值指标的周期波动拆解为结构变动、趋势变动和事件影响。当需要量化时间因素对指标变动的影响时调用。
packages/qwenpaw-data-skills/skills/atomic/bi-time-impact-attribution/SKILL.md on GitHub (opens in a new tab) -
query-odps
MaxCompute（ODPS）只读 SELECT 写法与执行纪律。**以下场景必须立即加载**：生成、改写或提交任何 ODPS / MaxCompute SQL（SELECT、WITH、JOIN、子查询、nl2sql）；覆盖方言、分区、结构纪律、优化、字面量取值、执行纪律与失败回退。
packages/qwenpaw-data-skills/skills/domains/query-odps/SKILL.md on GitHub (opens in a new tab) -
skill-hub-guide
Data Skill-Hub 技能仓库使用指南。在执行任何数据分析任务前，必须优先加载此技能以了解可用技能体系和调用规范。
packages/qwenpaw-data-skills/skills/meta/skill-hub-guide/SKILL.md on GitHub (opens in a new tab) -
analysis-plan-builder
将用户的数据分析需求转化为结构化的分析计划并与用户确认。用户提出 BI 业务分析、数据探索、统计建模等需要规划的分析任务时使用。简单数据查询、公式明确的定量计算等流程简单、无需规划的任务不使用。
packages/qwenpaw-data-skills/skills/planning/analysis-plan-builder/SKILL.md on GitHub (opens in a new tab) -
data-intent-router
将用户的数据相关请求路由至对应的处理链路。当用户发起数据相关任务时调用。
packages/qwenpaw-data-skills/skills/routing/data-intent-router/SKILL.md on GitHub (opens in a new tab) -
bi-semantic-layer-guide
语义层工具使用规范。在发现语义层工具可用、需要查询指标定义/维度信息、验证业务口径、处理指标歧义时，必须优先调用此技能。无语义层工具时不调用。
packages/qwenpaw-data-skills/skills/runtime/bi-semantic-layer-guide/SKILL.md on GitHub (opens in a new tab) -
interaction-strategy
定义与用户之间的交互策略：何时反问、何时直接执行、何时交付结果。在任何需要判断"是否该停下来和用户沟通"的场景中参考本 skill。
packages/qwenpaw-data-skills/skills/runtime/interaction-strategy/SKILL.md on GitHub (opens in a new tab) -
runtime-guide
提供数据分析任务执行的强制性通用规范。在计划完成准备执行数据分析任务、或执行过程中涉及产物落盘、数据复用、异常处理、计划调整、质量自检时，必须优先调用此技能。
packages/qwenpaw-data-skills/skills/runtime/runtime-guide/SKILL.md on GitHub (opens in a new tab) -
bi-cohort-analysis
把用户按同一批/同一类分组，比较各群体后续表现。触发条件：对话涉及同期群分析、分群后表现对比、用户生命周期分群跟踪等任务时触发，如出现「同期群」「cohort」「按起始特征分群后表现如何」「不同客群后续转化/留存对比」「注册周/获客渠道分群跟踪」等相似问题时触发。
packages/qwenpaw-data-skills/skills/workflows/bi-cohort-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-conversion-analysis
对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。
packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-metric-analysis
对单个分析条目执行完整的指标观测、异常检测、维度下拆归因和新增维度分析。当分析条目、指标及角色已明确时调用。
packages/qwenpaw-data-skills/skills/workflows/bi-metric-analysis/SKILL.md on GitHub (opens in a new tab) -
bi-retention-analysis
对留存执行完整的分析流程，算清楚用户留不留、留多少、有没有变化，含口径定义、取数、留存率计算，及可选的维度拆分与对比/归因。触发条件：对话涉及留存率分析、留存表现评估、留存变化归因等任务时触发，如出现「留存表现情况如何」「访问留存和使用留存对比怎么样」「不同国家的访问留存是否存在差异」「分维度后留存情况」「次日/第七日留存率变化」等相似问题时触发。
packages/qwenpaw-data-skills/skills/workflows/bi-retention-analysis/SKILL.md on GitHub (opens in a new tab) -
data-modeling
Builds end-to-end predictive modeling pipelines on tabular datasets—data exploration, preprocessing, baseline modeling, and mandatory optimization—producing valid saved predictions in the required output format. Use for any supervised machine learning or data modeling task, including classification and regression on tabular data, Kaggle-style competitions or submission-file challenges, training a…
packages/qwenpaw-data-skills/skills/workflows/data-modeling/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
SenseNova-Skillsby OpenSenseNova Modular SenseNova skills for building AI-powered office assistants and productivity workflows
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs…
-
cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.