Nextflow Development

Name: Nextflow Development
Author: anthropics

Official

anthropics·vlatest·cloud·Apache-2.0

Develop Nextflow workflows for efficient bioinformatics pipelines – streamlining data processing and analysis for faster research.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

Run this in your project

terminal

$ npx skills add anthropics/knowledge-work-plugins --skill nextflow-development -a claude-code

Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

anthropics

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned 28 Sept 2026

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

No undeclared network calls: failed
Contacts 6 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: docs.docker.com, eutils.ncbi.nlm.nih.gov, ftp.ncbi.nlm.nih.gov, get.nextflow.io, nf-co.re….
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
get.nextflow.ioundeclareddocs.docker.comundeclaredhub.docker.compackage registrynf-co.reundeclaredeutils.ncbi.nlm.nih.govundeclaredftp.ncbi.nlm.nih.govundeclaredwww.ebi.ac.ukundeclared
What it found (3 of 22)
- bio-research/skills/nextflow-development/references/installation.md:15contacts get.nextflow.io
  curl -s https://get.nextflow.io | bash
- bio-research/skills/nextflow-development/scripts/check_environment.py:120contacts get.nextflow.io
  fix="curl -s https://get.nextflow.io | bash && mv nextflow ~/bin/ && export PATH=$HOME/bin:$PATH"
- bio-research/skills/nextflow-development/scripts/check_environment.py:54contacts docs.docker.com
  fix="Install Docker: https://docs.docker.com/get-docker/"
No pipe-to-shell installers: failed
Runs code fetched at install time in 3 places.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
What it found
- bio-research/skills/nextflow-development/references/installation.md:15remote script piped into a shell
  curl -s https://get.nextflow.io | bash
- bio-research/skills/nextflow-development/scripts/check_environment.py:120remote script piped into a shell
  fix="curl -s https://get.nextflow.io | bash && mv nextflow ~/bin/ && export PATH=$HOME/bin:$PATH"
- bio-research/skills/nextflow-development/SKILL.md:75tells the user to run: remote script piped into a shell(in the instructions, not code)
  | Not installed | `curl -s https://get.nextflow.io \| bash && mv nextflow ~/bin/` |
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
Pinned to a commit: passed
Scanned anthropics/knowledge-work-plugins at da38ec1ee8.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit: da38ec1ee8
Manifest: bio-research/skills/nextflow-development/SKILL.md
Scanned: 22 files, 5,994 lines

This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.

What each check looks for →

About this skill

The nextflow-development skill enables AI agents to create, modify, and manage Nextflow pipelines for scalable bioinformatics and data processing workflows. It allows agents to generate pipeline code, configure execution environments, and handle complex data dependencies automatically.

When to use it

Automating the creation of new bioinformatics analysis pipelines from scratch based on research requirements.
Modifying existing Nextflow scripts to incorporate new tools or update data processing logic.
Generating configuration files for specific cloud computing environments like AWS Batch or Google Cloud Life Sciences.
Debugging and optimizing pipeline performance by analyzing workflow graphs and resource usage patterns.

Key capabilities

Generates valid Nextflow DSL2 code for multi-step data processing workflows.
Configures process parameters, input/output channels, and task dependencies dynamically.
Integrates with external tools such as BWA, GATK, and SAMtools within pipeline definitions.
Manages execution profiles for different hardware environments (local, HPC, cloud).

Example prompts

"Create a Nextflow pipeline to align raw sequencing reads using BWA-MEM and sort the output with SAMtools."
"Modify this existing Nextflow script to add a quality control step using FastQC before alignment."
"Generate a Nextflow configuration file optimized for running on AWS Batch with specific instance types."

Tips & gotchas

Ensure you provide clear specifications for input data formats and desired output structures, as vague requirements may lead to incomplete pipeline logic. Always validate generated code against your target execution environment's version constraints before deployment.