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 xgboost-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/xgboost-analysis)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/xgboost-analysis"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/xgboost-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/xgboost-analysis"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/xgboost-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 | $0.00050 | $0.01920 |
| Opus 5.5 | $0.00020 | $0.00768 |
| Sonnet 5.5 | $0.00010 | $0.00384 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
xgboost-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 2mo 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XGBoost Modeling And Feature Importance Ranking
Use this skill to train an XGBoost model from a tabular dataset and export both feature importance ranking tables and feature importance plots.
Use This Skill When
- You need a command-line XGBoost workflow in R for tabular data.
- You need a reproducible train-test split, model training, and evaluation.
- You need feature importance ranking outputs as both a table and a figure.
- You need automatic one-hot encoding for categorical predictors.
- Your data may contain a first unnamed sample ID column such as
V1that should not enter the model.
Do Not Use This Skill When
- Your classification target has more than 2 classes.
- Your input is not tabular CSV, TXT, or TSV data.
- You need causal interpretation, mechanism claims, or policy, business, or clinical conclusions.
- You only need narrative interpretation or triage of an existing result rather than model training.
Primary Command
Rscript scripts/main.R \
--data_file <input_file> \
--target_var <target_column> \
--task_type <auto|classification|regression> \
--output_dir <output_dir>
Prerequisites
Rscriptis available in the shell.- Required R packages:
optparse,data.table,Matrix,xgboost. - Install missing packages with
Rscript -e 'install.packages(c("optparse", "data.table", "Matrix", "xgboost"), repos="https://cloud.r-project.org")'.
Core Arguments
| Argument | Required | Description |
|---|---|---|
--data_file |
Yes | Input CSV, TXT, or TSV file |
--target_var |
Yes | Target column used for modeling |
--task_type |
No | auto, classification, or regression. Default auto |
--output_dir |
No | Output directory, default ./XGBoost_Results |
--ignore_vars |
No | Comma-separated columns to exclude from predictors |
--positive_class |
No | Positive class label for binary classification |
--test_size |
No | Test set proportion between 0 and 1, default 0.2 |
--seed |
No | Random seed, default 123 |
--nrounds |
No | Maximum boosting rounds, default 300 |
--max_depth |
No | Tree depth, default 6 |
--eta |
No | Learning rate, default 0.1 |
--subsample |
No | Row sampling ratio, default 0.8 |
--colsample_bytree |
No | Column sampling ratio, default 0.8 |
--min_child_weight |
No | Minimum child weight, default 1 |
--gamma |
No | Minimum split loss reduction, default 0 |
--lambda |
No | L2 regularization, default 1 |
--alpha |
No | L1 regularization, default 0 |
--early_stopping_rounds |
No | Early stopping rounds, default 20 |
--importance_metric |
No | gain, cover, or frequency. Default gain |
--top_n |
No | Number of features to plot, default 20 |
--output_format |
No | Table format: csv or txt, default csv |
--output_prefix |
No | Output filename prefix, default xgboost |
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_xgboost-analysis_result.json 15 KB
- references/algorithm.md 3.4 KB
- references/cli-guide.md 3.8 KB
- references/troubleshooting.md 4.2 KB
- scripts/functions.R 11 KB
- scripts/main.R 5.4 KB
- scripts/run_analysis.R 3.9 KB
- scripts/utils.R 7.0 KB
- tests/data/dt_sample1.csv 13 KB
- tests/data/dt_sample2.csv 4.6 KB
- tests/data/dt_sample3.txt 71 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.
- 2mo ago First seen · 210 lines · 50 tokens per session scan A 82b2c924c184
xgboost-analysis is a skill published in the GitHub repository aipoch/medical-research-skills (2,024 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,920 once invoked, about $0.0002 per session on Opus 5.5. 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.
xgboost-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xgboost-analysisaipoch/medical-research-skills | Skill | 2.0k | 1mo ago | MIT | A | 50 | Claude Code, Codex |
| multimodal-single-cellinflexa-ai/inflexa | Skill | 36 | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| motif-annotation-correlation-analysisHolobiomicsLab/asb-skill-collections | Skill | 16 | 6d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| motif-enrichment-statistical-testingHolobiomicsLab/asb-skill-collections | Skill | 16 | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| multiome-data-ingestion-paired-modalitiesHolobiomicsLab/asb-skill-collections | Skill | 16 | 6d ago | Apache-2.0 | A | 67 | Claude Code, Codex |
| bedpe-format-handlingHolobiomicsLab/asb-skill-collections | Skill | 16 | 6d ago | Apache-2.0 | A | 73 | Claude Code, Codex |
| fragment-based-count-matrix-generationHolobiomicsLab/asb-skill-collections | Skill | 16 | 6d ago | Apache-2.0 | A | 33 | Claude Code, Codex |