github.com/aipoch/medical-research-skills
Skill | Added | Review |
|---|---|---|
interview-mock-partner Simulates behavioral interview questions for medical professionals. | 45 1.58x Agent success vs baseline Impact 98% 1.58xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
go-kegg-enrichment Performs GO (Gene Ontology) and KEGG pathway enrichment analysis on gene lists. Trigger when: - User provides a list of genes (symbols or IDs) and asks for enrichment analysis - User mentions "GO enrichment", "KEGG enrichment", "pathway analysis" - User wants to understand biological functions of gene sets - User provides differentially expressed genes (DEGs) and asks for interpretation - Input: gene list (file or inline), organism (human/mouse/rat), background gene set (optional) - Output: enriched terms, statistics, visualizations (barplot, dotplot, enrichment map) | 80 1.00x No change in agent success vs baseline Impact 72% 1.00xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
microscopy-scale-bar-adder Add scale bars to microscopy images | 53 1.95x Agent success vs baseline Impact 92% 1.95xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
competitor-trial-monitor Monitor competitor clinical trial progress and alert on market risks | 62 1.88x Agent success vs baseline Impact 98% 1.88xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: ca9aaa4 | |
response-tone-polisher Polishes response letters by transforming defensive or harsh language into professional, courteous academic prose. Converts phrases like "I will not correct this" into "We respectfully believe the original data sufficiently supports..." to avoid reviewer conflict. | 67 2.13x Agent success vs baseline Impact 96% 2.13xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
volcano-plot-labeler Automatically label top significant genes in volcano plots using a force-directed repulsion algorithm to prevent label overlap. | 72 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
rebuttal-letter-strategist Strategic response drafting for sharp reviewer criticisms | 51 1.04x Agent success vs baseline Impact 99% 1.04xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
eln-template-creator Generate standardized experiment templates for Electronic Laboratory Notebooks | 62 1.00x No change in agent success vs baseline Impact 100% 1.00xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
heatmap-beautifier Professional beautification tool for gene expression heatmaps, automatically adds clustering trees, color annotation tracks, and intelligently optimizes label layout. | 65 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
dicom-anonymizer Batch anonymize DICOM medical images by removing patient sensitive information (name, ID, birth date) while preserving image data for research use. Trigger when users need to de-identify medical imaging data, prepare DICOM files for research sharing, or remove PHI from radiology/scanned images. | 90 1.51x Agent success vs baseline Impact 100% 1.51xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
figure-legend-gen Generate standardized figure legends for scientific charts and graphs. Trigger when user uploads/requesting legend for research figures, academic papers, or data charts. Supports bar charts, line graphs, scatter plots, box plots, heatmaps, and microscopy images. This tool generates text legends only, not visualizations. | 82 1.14x Agent success vs baseline Impact 96% 1.14xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
presentation-hook Creates engaging opening statements and powerful closings for medical presentations. | 52 2.22x Agent success vs baseline Impact 100% 2.22xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
unstructured-medical-text-miner Mine unstructured clinical text from MIMIC-IV to extract diagnostic logic and treatment details | 50 2.00x Agent success vs baseline Impact 76% 2.00xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
automated-soap-note-generator Transform unstructured clinical input (dictation, transcripts, or rough notes) into standardized SOAP (Subjective, Objective, Assessment, Plan) medical documentation. Use ONLY for initial documentation draft generation; ALL output requires physician review before entering patient records. Not for complex cases requiring nuanced clinical reasoning. | 16 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
motif-logo-generator Generate publication-quality sequence logos for DNA or protein motifs from FASTA files or raw sequence lists. | 78 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
variant-pathogenicity-predictor Integrate REVEL, CADD, PolyPhen-2, SIFT, and MutationTaster scores to predict variant pathogenicity with ACMG guideline interpretation. | 72 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
metagenomic-krona-chart Generate interactive Krona charts (sunburst plots) for metagenomic samples from Kraken2, Bracken, or custom TSV taxonomy abundance data. | 78 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
spatial-transcriptomics-mapper Map spatial transcriptomics data from 10x Genomics Visium or Xenium onto tissue section images, visualizing gene expression and spatial clustering distributions. | 86 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
single-cell-rnaseq-pipeline Generate single-cell RNA-seq analysis code templates for Seurat and Scanpy, supporting QC, clustering, visualization, and downstream analysis. Trigger when users need scRNA-seq analysis pipelines, preprocessing workflows, or batch correction code. | 88 1.28x Agent success vs baseline Impact 90% 1.28xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
journal-cover-prompter Use when creating journal cover images, generating scientific artwork prompts, or designing graphical abstracts. Creates detailed prompts for AI image generators to produce publication-quality scientific visuals. | 84 4.00x Agent success vs baseline Impact 96% 4.00xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
digital-twin-discharge-drafter Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissions, or optimizing care transitions. Generates AI-enhanced discharge documentation with digital twin predictions for improved patient safety. | 83 2.55x Agent success vs baseline Impact 92% 2.55xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
discussion-section-architect Structures and writes discussion sections for academic papers and research reports. Use when writing a discussion section, interpreting research results, connecting findings to existing literature, addressing study limitations, synthesizing conclusions, or drafting any part of an academic discussion. Helps researchers organize arguments, contextualize data, and produce clear, publication-ready discussion prose. | 99 0.99x Agent success vs baseline Impact 99% 0.99xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
graphical-abstract-wizard Generate graphical abstract layout recommendations based on paper abstracts | 68 2.28x Agent success vs baseline Impact 96% 2.28xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
code-refactor-for-reproducibility Transforms research code into publication-ready, reproducible workflows. Adds documentation, implements error handling, creates environment specifications, and ensures computational reproducibility for scientific publications. | 74 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 | |
adverse-event-narrative Generate CIOMS-compliant adverse event narratives for Individual Case Safety Reports (ICSR). Creates structured pharmacovigilance documents following CIOMS I and ICH E2B standards from case data for regulatory submission to health authorities. | 17 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: ca9aaa4 |