Orchestrate BioMaster’s multi-agent pipelines (RNA-seq, ChIP-seq, single-cell, Hi-C) using the provided configs and repos to deliver reproducible outputs.
Workflow
Config prep: Populate YAML with tool paths, reference genomes, and workflow selection (rnaseq, chipseq, singlecell, hic).
Launch:python repo/run.py --config repo/config.yaml (or chosen config) and monitor progress.
Error recovery: Let BioMaster agents retry failing stages; review logs for missing reference/index files.
Output packaging: Collect BAMs/counts/peaks + QC + narrative summary of parameters and runtimes.
Guardrails
Fail fast when reference files or indices are absent to avoid wasted compute.
Record tool versions for every stage (alignment, quantification, etc.).
Require confirmation before deleting intermediates or rerunning destructive steps.
References
Full workflow descriptions, supported modalities, and repo links reside in README.md.
1---2name: biomaster-workflows3description: Pipeline maestro4license: MIT5---67<!--8# COPYRIGHT NOTICE9# This file is part of the "Universal Biomedical Skills" project.10# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>11# All Rights Reserved.12#13# This code is proprietary and confidential.14# Unauthorized copying of this file, via any medium is strictly prohibited.15#16# Provenance: Authenticated by MD BABU MIA1718-->192021# BioMaster Workflows2223Orchestrate BioMaster’s multi-agent pipelines (RNA-seq, ChIP-seq, single-cell, Hi-C) using the provided configs and repos to deliver reproducible outputs.2425## Workflow261. **Config prep:** Populate YAML with tool paths, reference genomes, and workflow selection (`rnaseq`, `chipseq`, `singlecell`, `hic`).272. **Environment:** `cd repo && pip install -r requirements.txt` (or container) prior to running.283. **Launch:** `python repo/run.py --config repo/config.yaml` (or chosen config) and monitor progress.294. **Error recovery:** Let BioMaster agents retry failing stages; review logs for missing reference/index files.305. **Output packaging:** Collect BAMs/counts/peaks + QC + narrative summary of parameters and runtimes.3132## Guardrails33- Fail fast when reference files or indices are absent to avoid wasted compute.34- Record tool versions for every stage (alignment, quantification, etc.).35- Require confirmation before deleting intermediates or rerunning destructive steps.3637## References38- Full workflow descriptions, supported modalities, and repo links reside in `README.md`.394041<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
Run npx skillmds@latest add fridrichmethod/biomaster-workflows in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Pipeline maestro It is listed under DevOps & Infra on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.
FridrichMethod (@fridrichmethod) published this skill. Their other Agent Skills are listed on their SkillMD profile.
FridrichMethod