Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aipoch/medical-research-skillsnpx agentmods add skills/aipoch/medical-research-skills/external-model-validationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aipoch/medical-research-skills/external-model-validation)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/external-model-validation"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/external-model-validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/external-model-validation"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/external-model-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.03123 |
| Opus 5 | $0.00033 | $0.01562 |
| Sonnet 5 | $0.00013 | $0.00625 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade A, and why
external-model-validation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Model Validation
Input Validation
This 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.
If 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:
"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."
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need to run the analysis | scripts/main.R |
Execute: Rscript scripts/main.R --exp_file ... --cli_file ... --model_file ... |
| Need workflow order or output generation steps | scripts/run_analysis.R |
Review the 4-step orchestration of loading, scoring, plotting, and metadata export |
| Need risk score or sample matching logic | scripts/functions.R |
Inspect core data preparation and validation logic |
| Need output writing or metadata export details | scripts/io.R |
Inspect output directory creation and file-writing helpers |
| Need plotting implementation details | scripts/plotting.R |
Inspect Kaplan-Meier, risk, heatmap, and ROC plot generation |
| Need input validation, logging, timeout, or dependency logic | scripts/utils.R |
Review validation helpers, SKILL_* error handling, logging, and runtime safeguards |
| Need statistical assumptions or method details | references/algorithm.md |
Risk score formula, group cutoff, survival analysis, ROC, and heatmap assumptions |
| Need troubleshooting help | references/troubleshooting.md |
Common failures, warnings, and concrete fixes |
| Need CLI usage examples | references/cli-guide.md |
Parameter explanations, examples, and command patterns |
| Need expected outputs or benchmark run | references/baseline-run.md |
Real-data baseline command, runtime, memory checkpoints, and output inventory |
| Need test inputs | tests/data/ |
Example expression, clinical, and model files for validation |
| Need to refresh the retained example output | tests/refresh_example_output.R |
Rebuild tests/output/ with --overwrite using the bundled test data |
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- eval_report_external-model-validation_result.json 17 KB
- references/algorithm.md 3.7 KB
- references/baseline-run.md 2.5 KB
- references/cli-guide.md 2.8 KB
- references/project-structure.md 1.6 KB
- references/troubleshooting.md 5.2 KB
- scripts/functions.R 4.8 KB
- scripts/io.R 2.6 KB
- scripts/main.R 6.9 KB
- scripts/plotting.R 4.9 KB
- scripts/run_analysis.R 1.9 KB
- scripts/utils.R 4.0 KB
- tests/data/BRCA_clinic.csv 105 KB
- tests/data/BRCA_coef.csv 47 B
- tests/data/BRCA_data.csv 60 KB
- tests/refresh_example_output.R 980 B
- tests/testthat.R 729 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 309 lines · 66 tokens per session scan A 2ac5ed828786
external-model-validation is a skill published in the GitHub repository aipoch/medical-research-skills (1,855 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 3,123 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.
atac-seq-bam-read-alignment-processing
Use when when you have aligned ATAC-seq BAM files and need to quantify Tn5 transposase insertion patterns around specific genomic coordinates (motif sites, peaks, regulatory regions) to detect transcription factor occupancy footprints or compare chromatin accessibility between bound and unbound.
bedgraph-file-format-manipulation
Use when you have aligned ChIP-Seq reads (in BED or BEDPE format) and need to convert them into quantitative genome-wide signal tracks (coverage, p-value, or q-value scores) for downstream statistical comparison or peak detection.