ghchinoy/mizan-results
Turn stored Mizan eval results into a self-contained, standalone HTML report from an agent: query results via the mizan CLI over -o json, aggregate client-side, and render a single offline report.html. Use when you need to review, summarize, or visualize past evaluation results as an HTML report.
Turn stored Mizan eval results into a single self-contained, standalone HTML report (summary table, score distribution, per-metric trend) by querying the mizan CLI over -o json, aggregating client-side, and rendering an offline report.html. Use when a user asks to review, summarize, visualize, chart, or report on past evaluation results, generate an HTML results report/dashboard, or see score trends over time.
Explain and triage a single past Mizan evaluation run — pull its full record with mizan results show <run-id> -o json (or find it with mizan results list -o json), lay out the provenance (template, autorater, inputs, build), explain the verdict, and suggest concrete next steps. Use when a user asks why an eval scored the way it did, wants to debug or understand a past run, or needs to know what to change and re-run.