data-pipeline — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited data-pipeline (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.
Run a complete analysis workflow from connection through profiling, analysis, and structured reporting.
$ARGUMENTS. The first argument is the file path or connection string. The second argument is the analysis type: one of regression, clustering, forecast, correlation, or ab-test.connect_database with the source path. Then call describe_database to get the schema and get_data_quality_report to assess data quality. Summarize table structure, row counts, and quality scores.regression -- Call analyze_regression with the target column and feature columns. Then call execute_query if needed to inspect residuals. Report model coefficients, R-squared, and feature importance.
clustering -- Call analyze_clusters with numeric feature columns and algorithm "kmeans". Try k=2 through k=5 and compare silhouette scores. Call reduce_dimensions with PCA for a 2D summary. Report cluster profiles and quality.
forecast -- Call analyze_time_series to decompose the series and test stationarity. Then call forecast_time_series with the target column and desired horizon. Report trend, seasonality, and forecast values with confidence intervals.
correlation -- Call analyze_hypothesis_test with test type "correlation" for each numeric column pair. Call analyze_effect_sizes for the strongest relationships. Report a ranked correlation matrix with significance levels.
ab-test -- Call analyze_ab_test with the metric and group columns. Call analyze_effect_sizes to quantify practical significance. Report group comparison, p-value, effect size, and ship/iterate/no-ship recommendation.
export_schema to capture the data structure. If the analysis produced structured output suitable for downstream use, call export_structured to save it in a portable format./localdata-mcp:analyze-correlations to validate predictor selection/localdata-mcp:regression using cluster labels as features/localdata-mcp:analyze-correlations to find external predictors/localdata-mcp:regression with the strongest predictors/localdata-mcp:cluster-analysis to find segment-level effects~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.