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

Nextflow Pipeline Assistant

Helps you build, run, debug and scale Nextflow/nf-core data pipelines from laptop to HPC and cloud.

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

What it does

  • Runs pipelines: builds correct commands from a -profile test,docker smoke test to production runs with pinned revisions (-r), samplesheet CSV inputs and -resume.
  • Develops pipelines: covers DSL2 syntax (processes, channels, operators, take/emit), modules and subworkflows, the nf-core template, meta.yml, meta maps and ext.args conventions.
  • Configures and scales: nextflow.config, profiles, withName/withLabel selectors, Docker/Singularity/Conda/Wave containers, and SLURM, AWS Batch, Google Batch, Azure or Kubernetes executors.
  • Tests and lints: nf-test snapshot testing, nf-core pipelines lint, and nextflow lint to stay forward-compatible with the strict parser landing in 26.04.
  • Ships topic reference files (language, configuration, containers, running-pipelines, nf-core-tools, developing, testing) that are loaded only when depth is needed.

Who it's for

  • Bioinformaticians running reproducible RNA-seq, variant calling or similar analyses.
  • Data engineers moving heavy pipelines from local runs to HPC or cloud batch services.
  • Developers contributing nf-core-compliant modules, subworkflows and pipelines.

Examples

  1. "Give me the command to run nf-core/rnaseq 3.14.0 with my samplesheet on GRCh38" → a complete command with profile combos, params and -resume guidance.
  2. "My process_high tasks keep dying with OOM on SLURM" → dynamic resource scaling via task.attempt, errorStrategy 'retry', and a custom config layered with -c.
  3. "Write an nf-core style samtools sort module with tests" → scaffolded main.nf, meta.yml, a stub: block and an nf-test snapshot test.

· · · 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/nextflow folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/nextflow/.
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 && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/nextflow ~/.claude/skills/

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

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/nextflow ~/.claude/skills/
  5. Confirm the references/ folder came along: ls ~/.claude/skills/nextflow
  6. Prepare the runtime: check java -version (Java 17+ required), then curl -s https://get.nextflow.io | bash and sudo mv nextflow /usr/local/bin/
  7. Optional: install the nf-core CLI with conda install -c bioconda nf-core or uv pip install nf-core
  8. Restart Claude Code and ask something like "help me run an nf-core pipeline" to trigger the skill.
View source on GitHub ↗License: MIT