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/elastic-net-feature-selectionWrote 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/elastic-net-feature-selection)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/elastic-net-feature-selection"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/elastic-net-feature-selection/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/elastic-net-feature-selection"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/elastic-net-feature-selection.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 156 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 | $0.00083 | $0.02790 |
| Opus 5 | $0.00042 | $0.01395 |
| Sonnet 5 | $0.00017 | $0.00558 |
| Haiku 4.5 | $0.00008 | $0.00279 |
Grade A, and why
elastic-net-feature-selection 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 12d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elastic Net Feature Selection
When to Use
- Use this skill for binary case-vs-control classification on bulk expression matrices.
- Use it when you need elastic net logistic regression feature selection, coefficient paths, and
cv.glmnet-based lambda selection. - Use custom labels such as
TumorandNormalonly when the group file still contains exactly two outcome levels.
Out of Scope
- Survival or Cox modeling
- Multiclass outcomes
- Single-cell data
- Non-expression tables
Out-of-scope enforcement:
- If the group file contains any label outside the requested
case_groupandcontrol_group, the command stops withSKILL_INVALID_DATAinstead of silently dropping samples. - If either requested class is missing after validation, the command stops with
SKILL_INVALID_DATA.
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need to understand alpha, lambda choice, or feature-selection behavior | references/algorithm.md |
Elastic net logistic regression, penalty mixing, cross-validation, and coefficient selection assumptions |
| Need the authoritative executable entrypoint | scripts/main.R |
Run: Rscript scripts/main.R --input_file ... --group_file ... --output_dir ... |
| Need parameter examples, smoke-test commands, or recorded local runs | references/cli-guide.md |
Verified CLI examples for normal runs, conservative runs, and test-data runs |
| Need bundled sample inputs for a first run or regression test | tests/data/ |
Sample expression matrix, group file, and feature list |
| Encounter errors, warnings, or timeout issues | references/troubleshooting.md |
Common failures, console warning interpretation, and recovery steps |
Usage
Rscript scripts/main.R \
--input_file ./expression_matrix.csv \
--group_file ./groups.csv \
--feature_file ./genes.csv \
--case_group case \
--control_group control \
--alpha auto \
--alpha_grid 0,0.25,0.5,0.75,1 \
--nfolds 5 \
--lambda_choice lambda.min \
--standardize TRUE \
--timeout_seconds 600 \
--output_dir ./output/ \
--seed 42
What ships with it
20 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_elastic-net-feature-selection_result.json 12 KB
- references/algorithm.md 3.5 KB
- references/cli-guide.md 5.1 KB
- references/troubleshooting.md 4.4 KB
- scripts/functions.R 3.7 KB
- scripts/io.R 3.2 KB
- scripts/main.R 4.3 KB
- scripts/modeling.R 2.9 KB
- scripts/output.R 2.2 KB
- scripts/run_analysis.R 2.4 KB
- scripts/utils.R 3.5 KB
- scripts/validation.R 2.3 KB
- tests/data/expression_matrix.csv 2.5 KB
- tests/data/genes.csv 44 B
- tests/data/groups.csv 326 B
- tests/run_tests.R 771 B
- tests/testthat.R 887 B
- tests/testthat/helper-load-scripts.R 519 B
- tests/testthat/setup.R 249 B
- tests/testthat/test-elastic-net.R 9.8 KB
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.
- 12d ago First seen · 288 lines · 83 tokens per session scan A 92da5bde835b
elastic-net-feature-selection is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,790 once invoked, about $0.0004 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.