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/model-calibration-curveWrote 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/model-calibration-curve)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/model-calibration-curve"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/model-calibration-curve/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/model-calibration-curve"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/model-calibration-curve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 173 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.02633 |
| Opus 5 | $0.00032 | $0.01316 |
| Sonnet 5 | $0.00013 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
model-calibration-curve 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Calibration Curve
When to Use
Use this skill when you need to:
- validate a survival model with bootstrap calibration curves;
- compare predicted and observed survival probabilities at multiple horizons;
- export calibration statistics together with a PDF visualization.
Typical user requests:
- "Generate 1-, 2-, and 3-year calibration curves for this prognosis model."
- "Check whether the Cox model built from age, gender, and risk is well calibrated."
- "Export calibration statistics and a calibration PDF from this clinical cohort."
When Not to Use
Do not use this skill for:
- nomogram construction;
- univariate or multivariable Cox feature screening;
- ROC, calibration-free discrimination, or decision-curve analysis;
- non-survival endpoints or multiclass classification tasks.
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need algorithm details | references/algorithm.md |
Statistical method and formulas |
| Need to run analysis | scripts/main.R |
Get the complete command |
| Encounter errors | references/troubleshooting.md |
Find solutions |
| Need CLI examples | references/cli-guide.md |
Parameter usage examples |
Input Validation
This skill accepts:
- A clinical CSV file with sample IDs as row names, survival time, event indicator, and pre-selected prognostic features
- Requests to assess calibration of a survival (Cox) model via bootstrap resampling at one or more prediction horizons
If the user's request does not involve survival model calibration from a clinical CSV file — for example, asking to construct a nomogram, screen Cox features, generate an ROC curve, analyze a decision curve, or work with non-survival outcomes — do not proceed with this workflow. Instead respond:
"model-calibration-curve is designed to validate survival model calibration by generating bootstrap calibration curves from a clinical CSV file. Your request appears to be outside this scope. Please use a nomogram-construction skill for nomogram building, a roc-diagnostic-performance skill for ROC analysis, or a decision-curve-analysis skill for DCA."
What ships with it
11 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_model-calibration-curve_result.json 13 KB
- references/algorithm.md 3.0 KB
- references/cli-guide.md 2.1 KB
- references/troubleshooting.md 2.7 KB
- scripts/functions.R 5.4 KB
- scripts/main.R 4.6 KB
- scripts/run_analysis.R 4.5 KB
- scripts/utils.R 4.4 KB
- tests/data/sample_clinical_survival_data.csv 42 KB
- tests/run_smoke_test.R 1.9 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 · 306 lines · 64 tokens per session scan A 1dbdf02a16d4
model-calibration-curve 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 2,633 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.