ngs-analysis-router

Routes sequencing inputs to the appropriate public NGS analysis pipeline with preflight checks.

5.3k|765|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/openai/plugins --skill ngs-analysis-router
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ngs-analysis-router
Source: https://github.com/openai/plugins/tree/main/plugins/ngs-analysis/skills/ngs-analysis-router
Command: npx skills add https://github.com/openai/plugins --skill ngs-analysis-router

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Choosing the correct bioinformatics pipeline for sequencing data is error-prone: BCL run folders, FASTQs, BAM/CRAM files, count matrices, and VCFs each imply different assays and workflows. This Skill inspects available inputs, asks only the missing essential questions, and routes the request to the right public NGS analysis skill with a preflight-first plan.

Core Features & Use Cases

  • Input Inspection: Detects Illumina run folders, FASTQ, BAM/CRAM/VCF, count matrices, and metadata files before asking questions.
  • Pipeline Routing: Directs requests to leaf skills covering demultiplexing, QC, germline/somatic/UMI variant calling, bulk and single-cell RNA-seq, ATAC/ChIP-seq, amplicon, and shotgun metagenomics.
  • Preflight Planning: Generates install plans and reference-resource plans via ngs_preflight.py and ngs_reference_manager.py before any execution.
  • Use Case: A researcher drops a folder of paired-end FASTQs and a sample sheet into the workspace; the Skill identifies a bulk RNA-seq experiment, asks only for the organism and reference build, routes to ngs-bulk-rnaseq, and emits a reviewable install plan.

Quick Start

Inspect my sequencing data folder, ask only the missing essential questions, and route me to the right public NGS pipeline with a preflight plan.

Frequently Asked Questions about ngs-analysis-router

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

FAQPage Schema
How do I choose the right NGS analysis pipeline for my sequencing data?

Inspect the input files first: BCL run folders route to demultiplexing, FASTQs to QC or alignment workflows, and count matrices to differential expression. The router asks only for missing fields like assay type, organism, and desired output before selecting a public pipeline.

What file types indicate which sequencing assay I have?

RunInfo.xml and SampleSheet.csv indicate an Illumina BCL run folder, .fastq.gz files indicate raw reads, .bam/.cram indicate aligned reads, .vcf indicates called variants, and matrix.mtx or .h5ad files indicate single-cell count matrices.

Can I run NGS pipelines locally without cloud upload?

Yes, the router prefers public, runtime-installable packages and nf-core workflows that run locally or on HPC. For human data, it explicitly asks whether cloud upload is allowed before suggesting BaseSpace, Terra, or DNAnexus.

How do I check tool and reference genome readiness before running a pipeline?

Run ngs_preflight.py with the pipeline key to emit an install plan, and ngs_reference_manager.py to create a resource plan for the target genome build. The install_plan.json artifact is review-only unless execution is explicitly approved.

When should I use a UMI-aware variant calling pipeline?

Use UMI or duplex-aware variant calling for low-frequency targeted panel data where standard callers cannot distinguish true rare variants from sequencing errors. The router directs these requests to the UMI panel variants skill.