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/batch-effect-correctionWrote 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/batch-effect-correction)<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/batch-effect-correction"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/batch-effect-correction/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/batch-effect-correction"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/batch-effect-correction.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 | $0.00057 | $0.02604 |
| Opus 5 | $0.00028 | $0.01302 |
| Sonnet 5 | $0.00011 | $0.00521 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
batch-effect-correction 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 10d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Effect Correction
Prerequisites
Run the following before the first analysis to install all required R packages:
Rscript -e "if (!require('BiocManager', quietly=TRUE)) install.packages('BiocManager'); BiocManager::install(c('sva', 'limma')); install.packages('ggplot2', repos='https://cloud.r-project.org')"
Note:
svaandlimmaare Bioconductor packages and requireBiocManagerfor installation.ggplot2is a standard CRAN package.
The skill cannot run until these packages are installed. In new or bare R environments, always run the prerequisite step first.
When to Read External Files
| Situation | File to Read | Purpose |
|---|---|---|
| Need algorithm details | references/algorithm.md |
ComBat workflow, assumptions, and QC logic |
| Need to run analysis | scripts/main.R |
Execute: Rscript scripts/main.R --input_file ... --group_file ... |
| Encounter errors | references/troubleshooting.md |
Common errors and solutions |
| Need CLI examples | references/cli-guide.md |
Detailed CLI usage examples and baseline run record |
| Need test data | tests/data/ |
Sample input files for testing |
Usage
Rscript scripts/main.R \
--input_file ./expression_matrix.csv \
--group_file ./sample_info.csv \
--output_dir ./output/ \
--batch_column batch \
--group_column group \
--sample_column sample \
--log_transform auto \
--timeout_seconds 600 \
--seed 42
Arguments
| Short | Long | Type | Default | Description |
|---|---|---|---|---|
-i |
--input_file |
character | required | Expression matrix file (genes as rows, samples as columns) |
-g |
--group_file |
character | required | Sample metadata file (sample ID, group, and batch columns) |
-o |
--output_dir |
character | ./output/ |
Output directory |
-b |
--batch_column |
character | batch |
Batch column name in metadata |
-c |
--group_column |
character | group |
Biological group column name in metadata |
-n |
--sample_column |
character | sample |
Sample ID column name in metadata |
-l |
--log_transform |
character | auto |
Log transform mode: auto, yes, no |
-t |
--timeout_seconds |
integer | 600 |
Elapsed time limit in seconds; use 0 to disable |
-s |
--seed |
integer | 42 |
Random seed for reproducibility |
What ships with it
17 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_batch-effect-correction_result.json 12 KB
- references/algorithm.md 3.7 KB
- references/cli-guide.md 4.8 KB
- references/troubleshooting.md 5.2 KB
- scripts/functions.R 1.2 KB
- scripts/input_functions.R 4.7 KB
- scripts/main.R 4.3 KB
- scripts/output_utils.R 1.8 KB
- scripts/plotting.R 4.3 KB
- scripts/run_analysis.R 1.2 KB
- scripts/utils.R 3.8 KB
- tests/data/expression_matrix_merged.csv 105 KB
- tests/data/sample_info.csv 2.5 KB
- tests/run_tests.R 894 B
- tests/testthat/helper-load-scripts.R 459 B
- tests/testthat/setup.R 247 B
- tests/testthat/test-batch-correction.R 6.4 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.
- 10d ago First seen · 292 lines · 57 tokens per session scan A a2512af0a086
batch-effect-correction is a skill published in the GitHub repository aipoch/medical-research-skills (1,848 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,604 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.
conda-environment-creation-and-management
Use when you need to deploy a complex multi-language pipeline (e.g., HiC-Pro) that requires Python >3.7 libraries (pysam, bx-python, numpy, scipy), R packages (ggplot2, RColorBrewer), and compiled tool binaries (bowtie2, samtools >=1.
450k-array-data-processing
Use when you have raw .idat files or beta-valued matrices from HumanMethylation450 (450k) arrays and need to remove low-quality probes, correct for technical artifacts (batch effects, type-2 probe bias), and normalize the data before performing differential methylation analysis or DMR detection.