メニュー
Decompose a time series into trend/seasonal/residual components (STL, MSTL, Holt-Winters). Use when the user asks about trend, seasonality, detrending, or wants residuals for anomaly detection/forecasting.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Convert ts-agents workflow outputs, run manifests, plots, JSON, CSV files, and short Markdown reports into stakeholder-facing Markdown, Quarto, HTML, or PDF reports. Use when the user asks for a report, executive summary, research appendix, or reusable analysis deliverable from existing ts-agents artifacts.
End-to-end workflow for labeled-stream activity recognition: prepare or download data, run window-size selection, evaluate a windowed classifier, and produce plots + a short report. Use when you need a reproducible CLI workflow artifact or evaluation bundle.
Forecast/predict future values of a time series, choose reasonable baselines, and compare forecasting methods on arbitrary series loaded from ts-agents data.
Supervised time series classification: choose and run classifiers (KNN/DTW, ROCKET variants, HIVE-COTE), compare models, and report accuracy. Use when the user asks to classify/categorize time series, build a classifier, or compare time series classification algorithms.
Quick EDA and diagnostics for a time series: descriptive stats, autocorrelation, and periodicity. Use when the user asks "what does this series look like?", "is there seasonality?", "what's the period?", or before choosing decomposition/forecasting parameters.
| name | time-series-decomposition |
| description | Decompose a time series into trend/seasonal/residual components (STL, MSTL, Holt-Winters). Use when the user asks about trend, seasonality, detrending, or wants residuals for anomaly detection/forecasting. |
| compatibility | Best with the ts-agents repo + CLI (`ts-agents`). |
| metadata | {"domain":"time-series","tasks":["decomposition","trend","seasonality","detrending"],"ts_agents":{"tool_category":"decomposition","prefers_with_data_tools":true,"preferred_tools":["detect_periodicity_with_data","stl_decompose_with_data","mstl_decompose_with_data","holt_winters_decompose_with_data"]},"claude_code":{"allowed-tools":["Bash","Read","Write","Edit","Glob","Grep"],"disable-model-invocation":false}} |
Use decomposition when you need to:
stl_decompose_with_data): best default for a single dominant seasonality.mstl_decompose_with_data): when there are multiple seasonalities (e.g., daily + weekly).holt_winters_decompose_with_data): forecasting-oriented decomposition; supports additive/multiplicative components.If the user didn’t specify a period:
uv run ts-agents tool run detect_periodicity_with_data --run <RUN_ID> --var <VARIABLE> --param n_top=3
Use the most plausible period as period for STL/Holt-Winters.
uv run ts-agents tool run stl_decompose_with_data --run <RUN_ID> --var <VARIABLE> --param period=<PERIOD> --param robust=true
Notes:
robust=true is usually safer with outliers.If you have multiple periods (e.g., [24, 168]):
uv run ts-agents tool run mstl_decompose_with_data --run <RUN_ID> --var <VARIABLE> --param periods=[24,168]
uv run ts-agents tool run holt_winters_decompose_with_data --run <RUN_ID> --var <VARIABLE> --param period=<PERIOD> --param trend=add --param seasonal=add
List current decomposition tools and parameters:
uv run ts-agents tool list --category decomposition --json
Summarize: