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

pacsomatic Run Assistant

Operator toolkit that validates inputs, builds samplesheets and launch artifacts, and submits nf-core/pacsomatic tumor-normal runs to local or HPC schedulers.

AutomationAdvanced★ 33,030⑂ 3,248AI score 7/10Last updated: Aug 9, 2026

What it does

A reproducible execution wrapper for the nf-core/pacsomatic matched tumor-normal pipeline, built around a single entrypoint (scripts/run_pacsomatic.py):

  • Validates required IDs (patient, tumor sample, normal sample) and the existence of BAM/PBI/FASTA paths
  • Writes a pacsomatic-compliant samplesheet (patient,sample,status,bam,pbi)
  • Generates a params YAML plus a launch script so runs can be reproduced
  • Runs locally or submits to LSF/Slurm/PBS/SGE and reports the detected job ID
  • On failure, reports the first failure point and where to look next (.nextflow.log, pipeline_info, failing task logs)

It defaults to --dry-run for validation-only requests, which is a nice safety net before burning cluster time.

Who it's for

  • Genomics analysts routinely running matched tumor-normal somatic calling
  • Core facility / HPC operators managing Nextflow submissions
  • Researchers who want durable, reproducible launch artifacts instead of ad-hoc nextflow run commands

Example uses

  1. Pre-flight check: "Do a dry run on this tumor/normal BAM pair and tell me what's missing" — validates paths and reference mode (--fasta or --genome), then emits samplesheet and launch script only.
  2. Slurm submission: "Submit to the compute queue with 16 CPUs, 64GB RAM, 48h walltime" — generates the script, submits it, and returns the job ID.
  3. Failure triage: "Why did the pacsomatic submission fail?" — summarizes the first failure point and points to the relevant logs.

· · · 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/pacsomatic folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pacsomatic/.
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/pacsomatic ~/.claude/skills/

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

  1. Open a terminal and confirm you have Python 3, git, and Nextflow (plus Singularity or Docker) available.
  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/pacsomatic ~/.claude/skills/
  5. Restart Claude Code and verify pacsomatic appears in your skill list.
  6. Start with a dry run — ask something like "dry run pacsomatic for this BAM pair" and review the validation output and generated artifact paths.
  7. Optionally edit config.yaml so the default profile, executor, and resource settings match your cluster.
View source on GitHub ↗License: MIT