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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aipoch/medical-research-skills --skill svm-model-importance-analysisgit clone --depth 1 https://github.com/aipoch/medical-research-skillsWrote 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/svm-model-importance-analysis)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/svm-model-importance-analysis"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/svm-model-importance-analysis/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/svm-model-importance-analysis"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/svm-model-importance-analysis.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 | $0.00070 | $0.01942 |
| Opus 5 | $0.00035 | $0.00971 |
| Sonnet 5 | $0.00014 | $0.00388 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
svm-model-importance-analysis 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 9d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SVM Model Importance Analysis
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need algorithm details | references/algorithm.md |
Explain SVM-RFE ranking, cross-validation logic, assumptions, and interpretation |
| Need to execute the analysis | scripts/main.R |
Run the CLI entry point with a complete Rscript command |
| Encounter an error | references/troubleshooting.md |
Map standardized error codes to causes and fixes |
| Need CLI examples | references/cli-guide.md |
Review installation steps and runnable CLI examples |
| Need a runnable smoke test | tests/data/ |
Use the bundled small dataset for verification |
Usage
Rscript scripts/main.R \
--input_file ./input/expression_matrix.csv \
--group_file ./input/group_info.csv \
--case_group Case \
--control_group Control \
--output_dir output/basic-run \
--seed 42 \
--timeout_seconds 600
Arguments
| Short | Long | Type | Default | Required | Description |
|---|---|---|---|---|---|
-i |
--input_file |
character | none | yes, unless --plot_only TRUE |
Expression matrix file with samples in rows and features in columns |
-g |
--group_file |
character | none | yes, unless --plot_only TRUE |
Group file with sample IDs in the first column |
-c |
--case_group |
character | none | yes, unless --plot_only TRUE |
Case group label |
-r |
--control_group |
character | none | yes, unless --plot_only TRUE |
Control group label |
-o |
--output_dir |
character | output |
yes | Output directory inside the skill root |
-p |
--plot_only |
logical | FALSE |
no | Reuse output_dir/data/svm_result.rds and regenerate plots without rerunning SVM-RFE |
-s |
--seed |
integer | 42 |
no | Random seed for reproducibility |
-t |
--timeout_seconds |
integer | 600 |
no | Elapsed time limit for the run |
--svm_k |
integer | 10 |
no | Number of stratified outer folds used for SVM-RFE and validation | |
--svm_halve_above |
integer | 50 |
no | If surviving features exceed this count, remove half per iteration | |
--svm_max_features_cap |
integer | 30 |
no | Maximum feature count evaluated on the error curve | |
--svm_select_rule |
character | min |
no | Feature-count rule: min or tolerance |
|
--svm_tol |
numeric | 0.01 |
no | Tolerance used when --svm_select_rule tolerance is selected |
|
--svm_error_height |
numeric | 5 |
no | SVM error plot height in inches | |
--svm_error_width |
numeric | 6 |
no | SVM error plot width in inches | |
--svm_error_xlab |
character | Number of Features |
no | X-axis label for the SVM error plot | |
--svm_error_ylab |
character | Classification Error Rate |
no | Y-axis label for the SVM error plot | |
--svm_error_main_line_color |
character | black |
no | Main line color for the SVM error plot | |
--svm_error_second_line_color |
character | #2BA2DE |
no | Baseline line color for the SVM error plot | |
--svm_error_best_point_color |
character | red |
no | Highlight color for the best feature-count point | |
--svm_error_noinfo_lty |
integer | 3 |
no | Line type for the no-information baseline | |
--svm_error_label_cex |
numeric | 0.75 |
no | Label size for the best-point annotation | |
--svm_error_label_pos |
integer | 4 |
no | Label position for the best-point annotation | |
--svm_rank_top_n |
integer | 20 |
no | Maximum number of ranked features shown in the ranking plot | |
--svm_rank_width |
numeric | 7 |
no | Ranking plot width in inches | |
--svm_rank_height |
numeric | 6 |
no | Ranking plot height in inches | |
--svm_rank_color |
character | #2BA2DE |
no | Bar color for the ranking plot | |
--svm_rank_title |
character | SVM-RFE Feature Ranking |
no | Title for the ranking plot |
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_svm-model-importance-analysis_result.json 15 KB
- references/algorithm.md 3.3 KB
- references/cli-guide.md 6.1 KB
- references/troubleshooting.md 2.8 KB
- scripts/cli_options.R 179 B
- scripts/core_option_groups.R 2.5 KB
- scripts/functions.R 3.2 KB
- scripts/io.R 4.4 KB
- scripts/main.R 1.9 KB
- scripts/option_validation.R 2.1 KB
- scripts/path_utils.R 2.4 KB
- scripts/plot_option_groups.R 2.6 KB
- scripts/recording.R 182 B
- scripts/run_analysis.R 3.6 KB
- scripts/svm_helpers.R 2.9 KB
- scripts/utils.R 1.0 KB
- scripts/validation_utils.R 658 B
- scripts/visualization.R 1.9 KB
- tests/data/expression_matrix.csv 9.1 KB
- tests/data/group_info.csv 648 B
- tests/run_tests.R 347 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.
- 9d ago First seen · 163 lines · 70 tokens per session scan A 5e1c6edc97a9
svm-model-importance-analysis is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,942 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 2026-09-03.
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.