domains / families / science / robustness-checker

robustness-checker

authentic

Design and run risk-targeted robustness, sensitivity, error, and baseline checks for an approved mathematical model, emitting compact machine evidence in lean mode and a final report in submission mode.

When to use

• Test the claims most likely to fail. Choose checks from the model's assumptions and decision risks rather than filling a generic checklist.

When not to use

• irrelevant checks merely to reach a count
• inventing a threshold after seeing the result without labeling it exploratory
• converting stability metrics into the human confidence verdict
• creating robustness-checker_modeler_decision.md

Skill page

Source