Agent Skills › Zafer-Liu/Data-Analysis-Agent › gru

gru

GitHub

使用 GRU 深度学习模型对时间序列数据进行预测，包含数据验证、模型计算及结果可视化。

skills/gru/SKILL.md Zafer-Liu/Data-Analysis-Agent

Trigger Scenarios

需要对足够样本量的时间序列进行深度学习预测需要执行 GRU 时序分析并生成图表

Install

npx skills add Zafer-Liu/Data-Analysis-Agent --skill gru -g -y

More Options

Use without installing

npx skills use Zafer-Liu/Data-Analysis-Agent@gru

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill gru -a claude-code -g -y

安装 repo 全部 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --all -g -y

预览 repo 内 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --list

SKILL.md

Frontmatter

{
    "icon": "🧠",
    "name": "gru",
    "tags": [
        "mode-ml",
        "forecasting",
        "modeling"
    ],
    "description": "使用 GRU 对足量时间序列进行预测（forecast deep learning）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

GRU 预测

仅在样本量和序列长度足够时使用。确认窗口、特征和预测期，严格按时间划分训练验证，避免泄漏，报告基线对比、误差和不确定性；小数据优先建议传统时序模型。

Tool routing

Use get_schema to identify the time column, target column, feature columns, and source table.
Use query_data only to verify sorted sequence length, missingness, and whether the sample size is sufficient.
Use run_analysis with analysis_name="Time_Series_GRU" for the actual model computation.
Use generate_chart on forecast or validation result tables after run_analysis succeeds.