prophet
使用 Prophet 分解趋势季节性并预测（forecast 时间序列预测）
Source facts
- Repository
- Zafer-Liu/Data-Analysis-Agent
- Last source activity
- October 24, 2026 at 14:41
- Detected SKILL.md language
- Mixed languages
- Stars
- 2,620
- Forks
- 234
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- prophet
- description
- 使用 Prophet 分解趋势季节性并预测（forecast 时间序列预测）
- icon
- 🔮
- tags
- ["mode-business","mode-ml","forecasting"]
- allowedTools
- ["get_schema","query_data","run_analysis","generate_chart"]
# Prophet 预测
确认时间列、目标、频率、预测期及已知节假日。用时间切分验证，展示趋势、季节性、预测区间和误差；异常点或结构突变应单独提示。
## Tool routing
1. Use `get_schema` to identify the time column, target column, known holiday or event fields, and source table.
2. Use `query_data` only to verify frequency, gaps, outliers, and enough history for trend and seasonality.
3. Use `run_analysis` with `analysis_name="Time_Series_Prophet"` for the actual forecast computation.
4. Use `generate_chart` on forecast, trend, or seasonality result tables after `run_analysis` succeeds.
## Implementation reference
- Tool entry: `agent/tools/business/data.py::_tool_run_analysis`
- Analysis registry: `Function/Analyze/registry.py`
- Analysis implementation: `Function/Analyze/Time_Series_Prophet/analyze.py`
- Chart implementation: `Function/Charts_generation/chart_generate.py`
View on GitHub