Summary
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" /…
light0305/light-skills
light-data-engineering
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"。
Installation
$
npx skills add https://github.com/light0305/light-skills
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
ai-prompt-engineering-safety-review
Similar name
github/awesome-copilot
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for …
8 installs
eval-engineering
Similar name
langchain-ai/langchain-skills
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs,…
57 installs
langsmith-online-eval-engineering
Similar name
langchain-ai/langchain-skills
Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a…
3.3K installs
using-dbt-for-analytics-engineering
Similar name
dbt-labs/dbt-agent-skills
Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates te…
10 installs
harness-engineering
Similar name
github/awesome-copilot
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent …
9 installs
turning-engineering-analytics-into-insights
Similar name
posthog/ai-plugin
Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subs…
2 installsAlso in this package
Other skills from light0305/light-skills · top by installs.
npx skills add https://github.com/light0305/light-skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude Code
Not declared
Cursor
Not declared
Codex
Not declared
GitHub Copilot
Not declared
Windsurf
Not declared
Gemini CLI
Not declared
Cline
Not declared
OpenCode
Not declared
Repository health
Stars
609
License
LICENSE
Default branch
master
Open issues
1
Status
Active
History
- First seen on skills.sh
- First recorded snapshot · 35 installs