菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | time-series-diagnostics |
| description | 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. |
| compatibility | Best with the ts-agents repo + CLI (`ts-agents`). |
| metadata | {"domain":"time-series","tasks":["eda","diagnostics","statistics","periodicity","autocorrelation"],"ts_agents":{"tool_categories":["statistics","spectral"],"prefers_with_data_tools":true,"preferred_workflow":"inspect-series","preferred_tools":["describe_series_with_data","detect_periodicity_with_data","compute_autocorrelation_with_data"],"artifact_checklist":["summary.json","report.md"]}} |
Produce a fast, decision-useful snapshot of a time series so later steps (decomposition, forecasting, anomaly detection) can be configured correctly.
Use when the user asks for a quick understanding of a series (seasonality, period, persistence) or before selecting decomposition/forecasting parameters.
If the user hasn’t pinned down run_id + variable, discover candidates with:
uv run ts-agents data list --runs
uv run ts-agents data vars
Then proceed with the selected run_id + variable.
Run:
uv run ts-agents tool run describe_series_with_data --run <RUN_ID> --var <VARIABLE>
Report at least: length, mean, std, min/max, skew/kurtosis (if available), and whether NaNs appear.
Run:
uv run ts-agents tool run compute_autocorrelation_with_data --run <RUN_ID> --var <VARIABLE> --param max_lag=200
Interpretation heuristics:
Run:
uv run ts-agents tool run detect_periodicity_with_data --run <RUN_ID> --var <VARIABLE> --param n_top=5
Use the top detected period(s) to:
period for STL/Holt-WintersRun:
uv run ts-agents tool run compute_psd_with_data --run <RUN_ID> --var <VARIABLE> --param sampling_rate=1.0
Use PSD when:
If tools change or new diagnostics are added, list what’s available:
uv run ts-agents tool list --category statistics --json
uv run ts-agents tool list --category spectral --json
Return a concise diagnostic summary:
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.
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.