ARIMA 预测

SkillAI & models

Lets your agent forecast future values from a single time series, like sales or trends, using ARIMA statistical models.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the ARIMA 预测 skill

About this capability

Univariate time series forecasting using ARIMA (forecast)

What this skill tells your AI

The instructions your AI receives, as published by zafer-liu/data-analysis-agent in skills/arima/SKILL.md and read by ahel’s review.

确认时间列、频率、目标和预测区间，按时间排序并处理缺口。检查平稳性，选择合理参数，使用时间切分验证，输出预测值、区间和误差，并说明外部冲击限制。

Use get_schema to identify the time column, target column, table name, and available covariates.
Use query_data only to verify ordering, missing timestamps, frequency, and enough rows for modeling.
Use run_analysis with analysis_name="Time_Series_ARIMA" for the actual forecast computation.
Use generate_chart on the returned forecast or diagnostic result tables after run_analysis succeeds.

Advanced