Medical Research Agent Skills
A library of agent skills for medical research: literature search and appraisal, study design, data analysis and academic writing
- 2,047 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Generates R and Python analysis code and runs scripts that work with data
- Some skills reach external databases, and the output is research assistance to be verified, not a clinical decision
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/medical-research-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Generates R and Python analysis code and runs scripts that work with data
- Some skills reach external databases, and the output is research assistance to be verified, not a clinical decision
This is third-party code. Review the repository files before installing.
What it does
The set gives an agent a large collection of SKILL.md skills for the work of a medical researcher. The skills are grouped by research stage: evidence discovery and appraisal (building queries for PubMed and other databases, screening papers, mapping the evidence base, finding gaps), study design (design selection, power calculation, validation plans), data analysis (generating R and Python code for bioinformatics, statistical models, data cleaning, visualization) and academic writing (drafts of paper sections, abstracts, cover letters). Each skill is a folder with a SKILL.md file describing activation conditions and methodology, and several skills ship Python scripts and reference material. The repository also includes a separate skill auditor that runs every entry through a domain audit framework before publication.
Who it is for. For medical and biomedical researchers, data analysts and authors of scientific papers who work with a SKILL.md agent.
Good fit when
- You need to build a search strategy across PubMed and other databases and screen the literature
- You need to plan a study design, calculate power or dissect a paper's methodology
- You need to generate R or Python analysis code and drafts of manuscript sections
Not a fit when
- You need clinical advice or a treatment decision: the set is for research work, not medical recommendations
- The task is not about medical research
Example request
Build a PubMed search strategy for a systematic review on this question and screen the results by study designLimitations
This is a reference and working tool for research, not a source of medical recommendations: conclusions, code and text must be verified by you and do not replace a clinician or a clinical decision. Skills and scripts target Python 3.10 and above and separate libraries, and some features are unavailable without them. The material is in English. Some skills reach external databases and generate code whose results need checking.
How to disable. Remove the copied skill folders from ~/.claude/skills/ or the project's .claude/skills/ directory.
FAQ
Is this a medical recommendation?
No. The set supports research work: literature search, design, analysis and writing papers. It gives no clinical advice and does not replace a clinician, and all conclusions must be verified.
Do I have to install the whole library?
No. You can copy only the folders you need from scientific-skills into the skills directory, for example academic writing or data analysis.
Discussion
No questions or reviews yet.
Related
Skills166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases
Around 200 skills for Claude Code on bioinformatics, chemistry and biostatistics, from RNA-seq analysis to molecular docking
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
37 skills for computational drug discovery: from target selection and docking to ADMET and the clinical record.
Skills for pharma R&D: clinical trial design, ADaM datasets with admiral, Kaplan–Meier digitizing and statistical review.
17 skills for computational biology: RNA-seq, single-cell, protein structure, docking, literature and figures
README in short
The README describes a library of hundreds of medical research skills built by the AIPOCH team and compatible with Claude Code, Codex and other SKILL.md platforms. The skills cover four areas: evidence work, study design, data analysis and academic writing, organized by research stage. Every skill passes a MedSkillAudit domain review before publication, and a separate auditor is included in the repository. A subset of the skills ships inside the AIPOCH Open-Science workbench. MIT licensed.
README badge
Original SKILL.md
--- name: abstract-summarizer description: Transform lengthy academic papers into concise, structured 250-word abstracts. license: MIT author: AIPOCH --- > **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills) # Abstract Summarizer ## When to Use - Use this skill when the task needs Transform lengthy academic papers into concise, structured 250-word abstracts. - Use this skill for academic writing tasks that require explicit assumptions, bounded scope, and a reproducible output format. - Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence. ## Key Features - Scope-focused workflow aligned to: Transform lengthy academic papers into concise, structured 250-word abstracts. - Packaged executable path(s): `scripts/main.py`. - Reference material available in `references/` for task-specific guidance. - Structured execution path designed to keep outputs consistent and reviewable.