mag

Run the nf-core/mag metagenomics pipeline from samplesheet to annotated outputs.

1|Updated Jun 19, 2026
One-click install
npx skills add https://github.com/danilomonge/nf-claw --skill mag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mag
Source: https://github.com/danilomonge/nf-claw/tree/main/pipelines/mag
Command: npx skills add https://github.com/danilomonge/nf-claw --skill mag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the complexity of running nf-core/mag by turning a large metagenomics workflow into a guided, validated run with the right inputs, parameters, and provenance captured automatically.

Core Features & Use Cases

  • End-to-End Metagenomics: Handles read preprocessing, assembly, binning, bin QC, taxonomic profiling, virus identification, and genome annotation in one workflow.
  • Strict Input Validation: Uses a required CSV samplesheet and schema-backed parameters so runs fail fast on invalid paths, flags, or values.
  • Reproducible Execution: Tracks the pinned pipeline release, commit, exact command, and run provenance for reliable reruns and auditing.
  • Use Case: A researcher can submit short-read, long-read, or hybrid metagenomic data and obtain assembled contigs, bins, QC reports, and MultiQC summaries without manually wiring pipeline modules together.

Quick Start

Ask the assistant to run the mag metagenomics pipeline with my samplesheet, output directory, and preferred profile, then generate the command and validate the required parameters.

Frequently Asked Questions about mag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I assemble and annotate metagenomes using nf-core/mag?

To assemble and annotate metagenomes, this Skill guides the nf-core/mag pipeline from validated samplesheet inputs to assembled contigs, binned genomes, and taxonomic profiles. It automates module wiring to produce MultiQC summaries and bin QC reports.

What do I need to run an nf-core/mag metagenomics pipeline?

Running an nf-core/mag metagenomics pipeline requires a strictly validated CSV samplesheet and schema-backed parameters. You must provide input read data, an output directory, and a preferred execution profile to generate the validated run command.

Can I use hybrid metagenomic data for binning and taxonomic profiling?

Yes, hybrid metagenomic data can be used for binning and taxonomic profiling. The workflow processes short-read, long-read, and hybrid inputs, applying bin refinement and virus detection to generate assembled contigs and annotated bins.

How is reproducible provenance tracked during metagenome assembly?

Reproducible provenance is tracked by recording the pinned pipeline release, exact commit, and run command. This ensures safe execution and allows researchers to reliably rerun or audit metagenomics workflows.

Why does my metagenomics pipeline fail fast on invalid inputs?

Metagenomics pipeline runs fail fast on invalid inputs due to strict schema-backed parameter validation. This mechanism checks provided CSV samplesheet paths, flags, and values before execution to prevent downstream processing errors.

What is the best way to handle bin refinement and virus detection in Nextflow?

The best way to handle bin refinement and virus detection in Nextflow is using a guided workflow that applies strict validation. This approach manages read preprocessing and genome annotation automatically within the nf-core framework.