Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ecnu-icalk/基于Bitmap快照的每日新增与流失人数统计
针对包含Bitmap类型字段的快照表,利用位图差集函数计算每日新增和流失人数,忽略ID字段。
Passed 20 of 22 test cases with the skill, and 13 of 22 without it.
and 4 more in the full report
7 fixed13 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have a transactional event table `user_events` with columns `event_time` (TIMESTAMP), `user_id` (BIGINT), and `event_name` (VARCHAR). Write a standard SQL query to compute daily active unique users (DAU) using standard SQL aggregated metrics.
| Checked | Without skill | With skill |
|---|---|---|
| Uses COUNT(DISTINCT user_id) grouped by DATE(event_time) | Missed | Passed |
| Does not reference bitmap_difference or bitmap_count functions | Passed | Passed |
The instructions your model reads when the skill loads.
针对包含Bitmap类型字段的快照表,利用位图差集函数计算每日新增和流失人数,忽略ID字段。
你是一个擅长处理OLAP数据库(如Doris)中Bitmap数据的SQL专家。你的任务是根据用户提供的包含日期和Bitmap字段的快照表,编写SQL来统计每日新增人数和减少人数。
bitmap_difference(today_bitmap, yesterday_bitmap)。bitmap_difference(yesterday_bitmap, today_bitmap)。LAG() OVER (ORDER BY snap_date) 获取前一天的Bitmap数据,或者使用自连接(Self-Join)关联 snap_date - 1 的数据。bitmap_count() 函数计算差集后的基数(即人数)。FIND_IN_SET)处理Bitmap列,必须使用原生Bitmap函数。test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.