Causal inference

Skill Alim430/bioresearch-agent/skills/biomedical/causal-inference

Executable biomedical workflows for AI assistants — literature analysis, biomarker discovery, and Mendelian randomization through reproducible agent skills.

Install

npx -y skills add Alim430/bioresearch-agent --skill causal-inference

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run two-sample Mendelian randomization via the BioResearch Agent causal workflow (IVW estimation, leave-one-out sensitivity, scatter / funnel plots). Use when the user asks to test a causal effect between an exposure and an outcome (e.g., BMI → Type 2 Diabetes) using genetic instruments.

SKILL.md

1.3 KB, as published. Nobody here has run it

BioResearch Agent — Causal Inference (MR) Skill

Capability

Runs a reproducible two-sample Mendelian randomization: GWAS summary statistics (simulated by default) → genome-wide significant SNP instruments → IVW causal estimate → leave-one-out sensitivity → scatter / funnel plots. Returns a quantitative causal estimate, not a claim.

Run

bioresearch run causal --exposure BMI --outcome "Type 2 Diabetes"

Outputs (in `outputs/causal/`)

causal_ivw_results.csv — IVW estimate, SE, p-value
causal_loo_results.csv — leave-one-out sensitivity
causal_mr_scatter.png — MR scatter plot (IVW slope labeled)
causal_mr_funnel.png — funnel plot
causal_interpretation.txt — interpretation notes

Note

This skill dispatches to the framework's causal workflow. It adds no analysis of its own; all MR statistics run in the workflow modules. By default uses simulated GWAS data (no external credentials required).