Introduction Download Documentation BAAM About
BAAM

BioRouter AI Agent Marketplace

One-click downloads for BioRouter extensions, community workflows, and reusable skills.

BioRouter extensions

.brxt · One-click install

Download a .brxt bundle and drag it into BioRouter, Extensions, Add Extension. BioRouter installs the virtual environment, configures the tool, and adds it to your session. No terminal needed.

CDW Agent

BaranziniLab · UCSF · v0.4.3

SQL access to the UCSF Clinical Data Warehouse through natural language. Read-only queries, schema discovery, and structured results. Requires UCSF network credentials (CAMPUS\username and password).

UCSF OMOP Agent

BaranziniLab · UCSF · v0.1.0

Natural language SQL on the UCSF OMOP de-identified clinical database. Read-only access to standardized EHR data under the OMOP Common Data Model. Requires UCSF credentials.

Playwright Agent

BaranziniLab · UCSF · v0.1.0

Browser automation via Microsoft's @playwright/mcp. Navigate websites, extract data, fill forms, and run web research workflows using structured accessibility snapshots. No vision model required. Requires Node.js on the host.

SPOKE Agent

BaranziniLab · UCSF · v0.2.0

Cypher queries on the SPOKE biomedical knowledge graph linking diseases, genes, proteins, drugs, and pathways. Includes a bundled spoke-knowledge-graph skill. Requires a SPOKEAGENT_PASSCODE (see credentials page).

CodeGraph Agent

Broccolito · UCSF · v0.1.0

Pre-indexed code knowledge graph. Ask "who calls X?", "what does Y call?", or "what breaks if I change Z?" across 23 languages including R, Julia, MATLAB, Perl. Vendored fork of CodeGraph on tree-sitter.

Community workflows

All on GitHub →
Federated collaboration: Workflows let researchers share analytical pipelines without sharing sensitive data. A workflow is a portable YAML file that carries the instructions, not the underlying patient records or proprietary datasets. A colleague imports your workflow and runs it against their own institutional data to replicate and extend your research.

EHR Diabetes Demographics & Reporting Dashboard

Federated OMOP CDM EHR R Shiny Demographics

Query an OMOP-based EHR to identify a Type 2 Diabetes cohort, compute demographic summaries (gender, age, race, ethnicity), and auto-generate a shareable HTML report and interactive R Shiny dashboard. Runs at any OMOP-compatible institution without moving patient data.

version: 1.0.0
title: EHR Diabetes Demographics and Reporting Dashboard
description: A workflow for querying an OMOP-based EHR to derive a disease cohort
  (e.g., T2D), summarize demographics, and produce sharable visual outputs.
instructions: |
  Use an OMOP CDM clinical database to identify a patient cohort via diagnosis
  concepts. Join to person to obtain demographics and compute counts/percentages.
  Present results as an HTML report and optional R Shiny dashboard.
activities:
  - Count disease cohort
  - Demographic breakdowns
  - Generate HTML report
  - Build Shiny dashboard
extensions: []

Skills

70 collections · 460+ skills All on GitHub →
Skills are reusable instruction bundles that shape how BioRouter writes code, drafts documents, and reasons about a problem. To install: download a .zip below, then in BioRouter open Skills → Add Skill and drag the .zip (or a single SKILL.md) into the drop zone — BioRouter unpacks the bundle into ~/.config/biorouter/skills/ and registers every SKILL.md inside. You can also unzip manually and copy the folder into ~/.config/biorouter/skills/. Skills appear under BioRouter → Skills automatically; auto-applied skills activate when relevant files are touched.
Core BioRouter skills 8 skills

Anti-AI Writing

User-invocable · /anti-ai-writing

A pass/fail checklist for spotting AI writing patterns before generating prose, articles, or essays.

ggplot2 Visualization

Auto-applied · R plotting

Applies ggplot2 best-practice style when writing R plotting code.

R Scripting

Auto-applied · R code

Applies tidyverse conventions and documentation standards when writing or reviewing R code.

Python Scripting

Auto-applied · Python code

Applies Python naming, typing, error handling, and project structure conventions when writing Python code.

RALPH

User-invocable · /ralph

End-to-end planning for the Ralph autonomous agent loop. Drafts a markdown PRD from a feature idea, then converts it to prd.json. Each story is sized for one hands-off iteration.

Build a BioRouter Extension

User-invocable · /develop-biorouter-extension

A guide for building a .brxt extension: directory layout, manifest.json, Python MCP server, and bundled skills.

Superpowers Collection

13 skills · TDD, debugging, planning, more

Engineering discipline skills: brainstorming, TDD, systematic debugging, parallel agents, plan writing, code review, git worktrees. Workflows tested on long-running engineering tasks.

UCSF HPC

User-invocable · /ucsf-hpc

SSH setup, SLURM job templates (CPU/GPU/H200), file transfer, module management, and common pitfalls for the UCSF CHPC cluster.

Biomedical analysis skills 63 categories · 456 skills

Alignment

7 skills · auto-applied

Multiple sequence alignment and pairwise alignment.

Alignment Files

10 skills · auto-applied

SAM/BAM/CRAM manipulation, sorting, indexing, dedup, and stats.

Alternative Splicing

9 skills · auto-applied

RNA isoform and splice-junction analysis from short- and long-read data.

ATAC-seq

12 skills · auto-applied

Chromatin accessibility, peak calling, footprinting, and deep-learning ATAC.

Causal Genomics

11 skills · auto-applied

Mendelian randomization, colocalization, fine-mapping, and TWAS.

Chemoinformatics

7 skills · auto-applied

Molecular structure handling, descriptors, and drug-discovery utilities.

ChIP-seq

7 skills · auto-applied

Transcription-factor and histone-mark peak calling and differential binding.

Clinical Biostatistics

6 skills · auto-applied

Survival, mixed models, and clinical-trial statistical analysis.

Clinical Databases

10 skills · auto-applied

ClinVar, OMIM, COSMIC, gnomAD, and phenotype DB queries.

CLIP-seq

5 skills · auto-applied

Protein–RNA interaction mapping from iCLIP/eCLIP/PAR-CLIP data.

Comparative Genomics

5 skills · auto-applied

Cross-species synteny, orthology, and selection scans.

Copy Number

4 skills · auto-applied

CNV detection, visualization, and segmentation.

CRISPR Screens

8 skills · auto-applied

Pooled screen counting, MAGeCK analysis, and hit prioritization.

Data Visualization

12 skills · auto-applied

Publication-quality plots: heatmaps, volcano, Manhattan, dimplots.

Database Access

11 skills · auto-applied

NCBI, UniProt, Ensembl, and biological database APIs.

Differential Expression

6 skills · auto-applied

RNA-seq DE testing with DESeq2, edgeR, and limma-voom.

Ecological Genomics

6 skills · auto-applied

Environmental DNA, ecological population genomics, and biodiversity.

Epidemiological Genomics

5 skills · auto-applied

Pathogen typing, outbreak phylogeography, and surveillance.

Epitranscriptomics

5 skills · auto-applied

m6A and other RNA modification detection from sequencing.

Experimental Design

4 skills · auto-applied

Power analysis and sample-size calculation for omics studies.

Expression Matrix

5 skills · auto-applied

Count normalization, gene ID mapping, and matrix QC.

Flow Cytometry

8 skills · auto-applied

FCS parsing, gating, and high-dimensional cytometry analysis.

Gene Regulatory Networks

5 skills · auto-applied

TF–target network inference from expression and chromatin data.

Genome Annotation

6 skills · auto-applied

Gene prediction, repeat masking, and functional annotation.

Genome Assembly

8 skills · auto-applied

De novo assembly, polishing, and assembly QC.

Genome Engineering

5 skills · auto-applied

CRISPR guide design, off-target prediction, and editing analysis.

Genome Intervals

7 skills · auto-applied

BED/GTF arithmetic, overlap, and feature manipulation.

Hi-C Analysis

8 skills · auto-applied

3D chromatin contacts, TAD calling, and loop detection.

Imaging Mass Cytometry

6 skills · auto-applied

Single-cell spatial proteomics from IMC and MIBI data.

Immunoinformatics

5 skills · auto-applied

MHC binding, neoantigen prediction, and HLA typing.

Liquid Biopsy

6 skills · auto-applied

Cell-free DNA fragmentomics, tumor fraction, and methylation cfDNA.

Long-read Sequencing

8 skills · auto-applied

ONT and PacBio basecalling, alignment, and structural-variant workflows.

Machine Learning

6 skills · auto-applied

Biomarker discovery, model training, and cross-validation pipelines.

Metabolomics

8 skills · auto-applied

Mass-spec metabolite identification, alignment, and quantification.

Metagenomics

7 skills · auto-applied

Shotgun microbial profiling, assembly, and binning.

Methylation Analysis

5 skills · auto-applied

Bisulfite alignment and differential methylation testing.

Microbiome

6 skills · auto-applied

16S rRNA amplicon and microbiota community profiling.

Multi-omics Integration

4 skills · auto-applied

Cross-modality fusion: MOFA, DIABLO, WNN, totalVI.

Pathway Analysis

6 skills · auto-applied

GO, KEGG, Reactome, and GSEA enrichment testing.

Phasing & Imputation

4 skills · auto-applied

Haplotype phasing and genotype imputation with SHAPEIT and Beagle.

Phylogenetics

8 skills · auto-applied

Tree construction with IQ-TREE, RAxML, BEAST, and ancestral state.

Population Genetics

6 skills · auto-applied

GWAS, population structure, LD, and selection scans.

Primer Design

3 skills · auto-applied

PCR and qPCR primer generation with Primer3 and primerBLAST.

Proteomics

9 skills · auto-applied

Mass-spec quantification and protein abundance pipelines.

Read Alignment

4 skills · auto-applied

Short-read mapping with BWA-MEM2, Bowtie2, STAR, HISAT2.

Read QC

7 skills · auto-applied

FastQC, fastp, trimming, and contamination screening.

Reporting

5 skills · auto-applied

Reproducible HTML, Quarto, and R Markdown reports.

Restriction Analysis

4 skills · auto-applied

Restriction-enzyme mapping and digestion prediction.

Ribo-seq

5 skills · auto-applied

Ribosome profiling and translation-efficiency analysis.

RNA Quantification

4 skills · auto-applied

Gene and transcript abundance with Salmon, kallisto, RSEM.

RNA Structure

3 skills · auto-applied

Secondary-structure prediction with RNAfold, IPknot.

Sequence I/O

9 skills · auto-applied

FASTA/FASTQ parsing, conversion, and indexing.

Sequence Manipulation

7 skills · auto-applied

Transcription, translation, ORF finding, and motif search.

Single-cell

14 skills · auto-applied

scRNA-seq clustering, annotation, trajectory, and integration.

Small RNA-seq

5 skills · auto-applied

miRNA, piRNA, and small-RNA quantification.

Spatial Transcriptomics

11 skills · auto-applied

Visium, Slide-seq, and high-resolution tissue expression.

Structural Biology

6 skills · auto-applied

PDB parsing, AlphaFold, ESMFold, and structure analysis.

Systems Biology

5 skills · auto-applied

Metabolic flux balance, kinetic modelling, network analysis.

TCR/BCR Analysis

5 skills · auto-applied

Immune-receptor repertoire profiling and clonal-family analysis.

Temporal Genomics

5 skills · auto-applied

Time-series and circadian expression analysis.

Variant Calling

13 skills · auto-applied

SNPs, indels, SVs with GATK, DeepVariant, Manta, Delly.

Workflow Management

4 skills · auto-applied

Snakemake, Nextflow, CWL, WDL pipeline scaffolding.

End-to-end Workflows

41 skills · auto-applied

Ready-to-run analysis pipelines combining multiple skills.

Have an agent, workflow, or skill to share with the BioRouter community?

Contribute on GitHub