forecast — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited forecast (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Decompose a time series, test for stationarity, and generate forecasts with confidence intervals.
$ARGUMENTS. The first argument is the database name, the second is the column to forecast.execute_query to select the datetime column and the target column, ordered by time ascending. If the table is not obvious, query the schema first. Ensure no gaps in the time index. Limit to the most recent 10,000 observations if the series is very long.analyze_time_series with the database name and column. Review the decomposition results:forecast_time_series with the database name, column, and desired forecast horizon. The tool will select an appropriate model (ARIMA, ETS, or SARIMA) based on the series characteristics. Request confidence intervals at the 80% and 95% levels./localdata-mcp:analyze-correlations to find external predictors that could improve the model.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.