Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-sql-reporting-7aa335e491d5 ,按照其中的说明把「sql-reporting」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
Apply this skill before writing or running any analytics SQL so reports stay consistent and safe.
Use this skill when the task involves:
SELECT explicit column names, never SELECT *.order_count, not count(*)).LIMIT unless an aggregate already collapses
the result set.COUNT(DISTINCT ...) over a sub-query when de-duplicating.SELECT *.Return the final SQL in a fenced ```sql block, then one sentence describing what the query returns.