What problem does it solve? Running production bioinformatics pipelines requires environment setup, samplesheet formatting, genome reference management, and public data acquisition—steps that block researchers without specialized bioinformatics training from analyzing RNA-seq, WGS/WES, or ATAC-seq data. ## Core Features & Use Cases - Guided nf-core Execution: Step-by-step workflow for nf-core/rnaseq, nf-core/sarek, and nf-core/atacseq with environment pre-flight checks, test profile validation, and output verification. - GEO/SRA Data Acquisition: Fetch study metadata, download FASTQ files from ENA with parallel transfers, and auto-generate samplesheets from public datasets using GSE/GSM/SRR accessions. - Automated Samplesheet & Genome Management: Detect data types, pair R1/R2 reads, infer tumor/normal status for sarek, and manage iGenomes references (GRCh38, GRCm39, R64-1-1, and more). - Use Case: A researcher wants to reanalyze a published yeast RNA-seq study (GSE110004). The skill fetches study info, downloads the FASTQs, generates a samplesheet, validates the Docker/Nextflow environment, and launches nf-core/rnaseq with the correct genome. ## Quick Start Ask the agent to run the nf-core rnaseq pipeline on your FASTQ directory or a GEO accession, and it will check the environment, build the samplesheet, and launch the analysis.
