model-validation

SKILLWorkflowcommunity
v0.0.0AperivueMITUpdated 1mo agoSource →

Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection) before the validation report or manuscript is written. Covers patient-level split disjointness and the data-leakage taxonomy, tuning-on-test, internal versus genuine

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
258Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorAperivue
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection) before the validation report or manuscript is written. Covers patient-level split disjointness and the data-leakage taxonomy, tuning-on-test, internal versus genuine external validation, comparator design, single-run versus multi-seed variance, task-correct metric

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.