external-model-validation

1# External Model Validation
2 
3## Input Validation
4 
5This skill accepts: an existing prognostic gene signature (model coefficient file with `Gene` and `Coef` columns), a bulk expression matrix in CSV format (genes as rows, samples as columns), and a clinical file with `OS` and `OS.time` survival columns.
6 
7If the user's request does not involve validating a pre-existing prognostic model on an external cohort — for example, asking to train a new model, perform feature selection, build a nomogram, run calibration curves, analyze single-cell data, or process data without survival endpoints — do not proceed with the workflow. Instead respond:
8 
9> "external-model-validation is designed to validate an existing prognostic risk signature on an external bulk expression cohort with survival outcomes. Your request appears to be outside this scope. Please provide a fixed model coefficient file plus expression and clinical data with OS/OS.time columns, or use a more appropriate tool for model training, nomogram construction, or single-cell analysis."
10 
11## When to Read External Files
12 
13| Situation | File to Read | Purpose |
14|-----------|--------------|---------|
15| **Need to run the analysis** | `scripts/main.R` | Execute: `Rscript scripts/main.R --exp_file ... --cli_file ... --model_file ...` |
16| **Need workflow order or output generation steps** | `scripts/run_analysis.R` | Review the 4-step orchestration of loading, scoring, plotting, and metadata export |
17…