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/roc-diagnostic-performanceWrote 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/roc-diagnostic-performance)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/roc-diagnostic-performance"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/roc-diagnostic-performance/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/roc-diagnostic-performance"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/roc-diagnostic-performance.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 | $0.00064 | $0.02690 |
| Opus 5 | $0.00032 | $0.01345 |
| Sonnet 5 | $0.00013 | $0.00538 |
| Haiku 4.5 | $0.00006 | $0.00269 |
Grade A, and why
roc-diagnostic-performance 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 13d 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.
ROC Diagnostic Performance
When to Use
Use this skill when you need to:
- evaluate one or more diagnostic marker genes in a case-control cohort;
- build a multivariable logistic regression diagnostic model from marker expression values;
- compare the ROC performance of the full model against individual markers.
Typical user requests:
- "Use these genes to build a diagnostic ROC model for case vs control samples."
- "Evaluate the AUC of FOXP3, CD45, and CD3E and plot all ROC curves together."
- "Run logistic regression on biomarker expression and export ROC results."
When Not to Use
Do not use this skill for:
- survival or prognostic analysis with time-to-event outcomes;
- multiclass classification tasks;
- calibration plots, nomograms, or decision-curve analysis;
- non-expression diagnostic inputs such as imaging, clinical scores, or mutation-only tables.
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need algorithm details | references/algorithm.md |
Logistic regression, ROC, AUC, and modeling assumptions |
| Need to run analysis | scripts/main.R |
Execute Rscript scripts/main.R --expression_file ... --group_file ... |
| Encounter errors | references/troubleshooting.md |
Common SKILL_* errors and solutions |
| Need CLI examples | references/cli-guide.md |
Detailed command-line examples |
| Need test data | tests/data/ |
Example expression matrix and group file |
Usage
Rscript scripts/main.R \
--expression_file ./expression_matrix.csv \
--group_file ./group_info.csv \
--marker_genes FOXP3,CD45,CD3E \
--case_group Disease \
--output_dir ./output/ \
--seed 42
Arguments
| Short | Long | Type | Default | Description |
|---|---|---|---|---|
-e |
--expression_file |
character | required | Expression matrix file in CSV/TSV format |
-g |
--group_file |
character | required | Group file with sample IDs and labels |
-m |
--marker_genes |
character | required | Comma-separated marker genes |
-c |
--case_group |
character | required | Case group label in the group file |
--group_col |
character | NULL |
Optional group column name; auto-detected if omitted | |
-o |
--output_dir |
character | ./output/ |
Output directory |
--overwrite |
flag | FALSE |
Allow writing into a non-empty output directory | |
-s |
--seed |
integer | 42 |
Random seed for reproducibility |
-T |
--timeout_seconds |
integer | 0 |
Elapsed time limit in seconds; 0 disables timeout |
--plot_width |
double | 6 |
ROC plot width in inches | |
--plot_height |
double | 6 |
ROC plot height in inches | |
--font_family |
character | sans |
PDF font family | |
--line_colors |
character | #E64B35,#4DBBD5,#00A087,#3C5488,#F39B7F |
Comma-separated ROC line colors | |
--line_width |
double | 1.2 |
ROC curve line width | |
--show_diagonal |
character | true |
Show diagonal reference line: true or false |
|
--diagonal_color |
character | #7F7F7F |
Diagonal line color | |
--diagonal_lty |
integer | 2 |
Diagonal line type | |
--plot_title |
character | ROC Diagnostic Performance |
ROC plot title | |
--x_label |
character | 1 - Specificity |
X-axis label | |
--y_label |
character | Sensitivity |
Y-axis label | |
--base_cex |
double | 0.9 |
Base text-size multiplier | |
--legend_position |
character | bottomright |
Legend position | |
--legend_cex |
double | 0.8 |
Legend text size |
What ships with it
21 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_roc-diagnostic-performance_result.json 12 KB
- references/algorithm.md 2.8 KB
- references/cli-guide.md 2.7 KB
- references/troubleshooting.md 2.8 KB
- scripts/cli.R 3.7 KB
- scripts/functions.R 5.9 KB
- scripts/io.R 1.3 KB
- scripts/main.R 1.8 KB
- scripts/plotting.R 2.4 KB
- scripts/run_analysis.R 2.8 KB
- scripts/utils.R 2.5 KB
- scripts/validation.R 2.3 KB
- tests/data/sample_expression_matrix.csv 7.6 KB
- tests/data/sample_group_info.csv 2.2 KB
- tests/expected_output/data/analysis_data.rds 2.8 KB
- tests/expected_output/data/roc_model.rds 17 KB
- tests/expected_output/session_info.txt 1.8 KB
- tests/expected_output/table/model_coefficients.csv 568 B
- tests/expected_output/table/roc_auc_summary.csv 76 B
- tests/run_smoke_test.R 2.1 KB
- tests/run_smoke_test.sh 127 B runs code
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.
- 13d ago First seen · 309 lines · 64 tokens per session scan A 95efa3295572
roc-diagnostic-performance is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,690 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.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
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.