light-data-engineering
bylight0305· 23 skills
Light 科研主线第 2 步·数据工程：找得到且用得起的数据（来源/许可/版本/大小/split）+ 提 idea 前先判数据可行性 （数据够不够支撑研究/统计功效）+ 防数据泄漏（顶会拒稿高频雷）。何时用：用户要找/选/下载公开数据集，或给了数据问 "能不能做研究/够不够/质量行不行" / 要清洗·处理缺失异常·特征工程·划分数据集·数据增强 / 自建数据集（采集·标注规范· 隐私合规·发布） / 怀疑训练测试串了数据(泄漏) / 提 idea 前评数据基础。 触发词：数据够不够 / 数据可行性 / 数据质量 / 数据泄漏 / 防穿越 / train test 重叠 / 怎么划分 / 交叉验证 / 标注规范 / 一致性 IAA / 自建数据集 / 样本量够吗 / 统计功效 / 找数据集 / 数据许可 / dataset search / data leakage / feasibility / data split / annotation。核心纪律： 数据泄漏 = critical 一票否决（标准化早于划分/时序穿越/实体重叠/目标编码穿越）；数据不足以支撑 idea = 拦在 idea 前（回边 2⊣3，补数据/改 idea）；功效是经验阈值非 power analysis；泄漏检测是启发式有边界，不吹"查全了"。
How to install light-data-engineering?
light0305/light-skills/light-data-engineering
$npx -y skills add light0305/light-skills --skill light-data-engineeringInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/light0305/light-skills" --skill "light0305/light-skills/light-data-engineering"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/light0305/light-skills" that are relevant to the current task. Run `npx skills add "https://github.com/light0305/light-skills"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- azure-kustoQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis.Jul 2026
- analyticsWhen the user wants to set up, improve, or audit analytics tracking and measurement.Jul 2026
- firecrawl-dashboard-reportingPull metrics from analytics dashboards and internal web tools with Firecrawl browser.Jun 2026
- data-storytellingTransform data into compelling narratives using visualization, context, and persuasive structure.Jul 2026
- data-visualizationCreate effective data visualizations with Python (matplotlib, seaborn, plotly).Jul 2026
- extension-oqlMake a canister's data queryable by the Caffeine Data Intelligence agent.Jul 2026
