Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xu-xiang/clickhouse-io
ClickHouse 数据库模式、查询优化、分析以及高性能分析负载的数据工程最佳实践。
Passed 18 of 23 test cases with the skill, and 16 of 23 without it.
3 fixed15 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a ClickHouse query to calculate Daily Active Users (DAU) over the past 30 days from raw user event logs.
| Checked | Without skill | With skill |
|---|---|---|
| Groups activity date using toDate on the event timestamp | Passed | Passed |
| Calculates unique active users using uniq aggregate function | Missed | Passed |
The instructions your model reads when the skill loads.
用於高效能分析和資料工程的 ClickHouse 特定模式。
ClickHouse 是一個列式資料庫管理系統(DBMS),用於線上分析處理(OLAP)。它針對大型資料集的快速分析查詢進行了優化。
關鍵特性:
CREATE TABLE markets_analytics (
date Date,
market_id String,
market_name String,
volume UInt64,
trades UInt32,
unique_traders UInt32,
avg_trade_size Float64,
created_at DateTime
) ENGINE = MergeTree()
PARTITION BY toYYYYMM(date)
ORDER BY (date, market_id)
SETTINGS index_granularity = 8192;
-- 用於可能有重複的資料(例如來自多個來源)
CREATE TABLE user_events (
test cases passed, vs 16 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.