Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Bulk RNA-seq Orchestrator

Orchestrates a reproducible bulk RNA-seq workflow from raw FASTQ through QC, quantification, differential expression, pathway enrichment and publication figures.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

This skill is a router that chains every stage of a bulk RNA-seq differential-expression study in the right order:

  • QC & trimming: FastQC/MultiQC, then fastp or Trim Galore
  • Align/quantify: choose Path A (nf-core/rnaseq via Nextflow) or Path B (standalone STAR, Salmon, featureCounts)
  • Counts bridge: scripts/build_counts_matrix.py converts Salmon/STAR/featureCounts output into an integer counts.csv plus metadata_template.csv that PyDESeq2 accepts directly
  • Handoffs: DE to the pydeseq2 skill, ORA/GSEA to pathway-enrichment, plots to scientific-visualization
  • Quality gates: replication, batch confounding, strandedness, PCA and sample-distance checks before you trust any result

Four self-contained reference docs cover design & QC thresholds, nf-core parameters, manual pipeline recipes, and the counts→DE handoff nuances (length-scaled TPM, integer rounding, Ensembl→symbol mapping).

Who it's for

  • Students and researchers holding FASTQ files and unsure where to start
  • Anyone who needs a clean counts matrix for DESeq2/PyDESeq2
  • Teams running nf-core/rnaseq with pinned revisions and containers for reproducibility
  • Authors who need a defensible pipeline and accurate Methods text

For single-cell data use the scanpy skill instead.

Examples

  1. "Analyze my 12-sample RNA-seq from FASTQ to DESeq2" → validate samplesheet → nf-core test profile smoke run → real run pinned at -r 3.26.0 → DE on the merged gene counts file
  2. "I have a Salmon quant directory; build a PyDESeq2-ready counts matrix" → build_counts_matrix.py --from salmon with length-scaled TPM aggregation and integer rounding
  3. "Sanity-check my design: treated samples sequenced in March, controls in May" → flags batch/condition confounding and recommends ~batch + condition or re-sequencing

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/bulk-rnaseq folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/bulk-rnaseq/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/bulk-rnaseq ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and create the skills folder: mkdir -p ~/.claude/skills
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy this skill: cp -r scientific-agent-skills/skills/bulk-rnaseq ~/.claude/skills/
  4. (Recommended) copy the companion skills: cp -r scientific-agent-skills/skills/{pydeseq2,pathway-enrichment,scientific-visualization,nextflow} ~/.claude/skills/
  5. Install the glue Python packages: uv pip install pytximport pandas (or pip install pytximport pandas)
  6. For Path A install Nextflow plus Docker/Singularity; for Path B create the bioconda env: conda create -n rnaseq -c bioconda -c conda-forge fastqc fastp trim-galore "star=2.7.11b" "salmon=1.10.3" subread multiqc
  7. Restart Claude Code and prompt something like "take my RNA-seq reads to differentially expressed genes and enriched pathways".
View source on GitHub ↗License: MIT