mcpbeat Sign in

Bio Workflow Management Cwl Workflows Agent Skill

by BioTender-max

Create portable, standards-based bioinformatics pipelines with Common Workflow Language (CWL). Use when building workflows that need maximum portability across execution platforms, sharing pipelines with collaborators using different systems, or contributing to community workflow registries.

4k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
132
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/BioTender-max/awesome-bio-agent-skills --skill bio-workflow-management-cwl-workflows

What comes with it

6 471 bytes besides the instruction
examples/rnaseq.cwl
usage-guide.md

The instruction itself

20 sections, as written by the author

Version Compatibility

Reference examples tested with: FastQC 0.12+, Nextflow 23.10+, Salmon 1.10+, Snakemake 8.0+, fastp 0.23+

Before using code patterns, verify installed versions match. If versions differ:

  • CLI: <tool> --version then <tool> --help to confirm flags

If code throws ImportError, AttributeError, or TypeError, introspect the installed

package and adapt the example to match the actual API rather than retrying.

CWL Workflows

"Write a portable CWL workflow for my analysis" → Define tools and workflows in YAML using the Common Workflow Language standard for maximum cross-platform portability and sharing through workflow registries.

  • CLI: cwltool for local execution of CWL documents
  • YAML: CWL v1.2 CommandLineTool and Workflow class definitions

Basic Tool Definition

# fastqc.cwl
cwlVersion: v1.2
class: CommandLineTool
baseCommand: fastqc

inputs:
  fastq:
    type: File
    inputBinding:
      position: 1

outputs:
  html:
    type: File
    outputBinding:
      glob: "*_fastqc.html"
  zip:
    type: File
    outputBinding:
      glob: "*_fastqc.zip"

Tool with Parameters

# bwa_mem.cwl
cwlVersion: v1.2
class: CommandLineTool
baseCommand: [bwa, mem]

requirements:
  DockerRequirement:
    dockerPull: biocontainers/bwa:v0.7.17
  ResourceRequirement:
    coresMin: 8
    ramMin: 16000

inputs:
  threads:
    type: int
    default: 8
    inputBinding:
      prefix: -t
      position: 1
  reference:
    type: File
    secondaryFiles:
      - .amb
      - .ann
      - .bwt
      - .pac
      - .sa
    inputBinding:
      position: 2
  reads_1:
    type: File
    inputBinding:
      position: 3
  reads_2:
    type: File?
    inputBinding:
      position: 4

stdout: aligned.sam

outputs:
  sam:
    type: stdout

Basic Workflow

# rnaseq.cwl
cwlVersion: v1.2
class: Workflow

inputs:
  fastq_1: File
  fastq_2: File
  salmon_index: Directory

outputs:
  quant_results:
    type: Directory
    outputSource: salmon/quant_dir

steps:
  fastp:
    run: fastp.cwl
    in:
      reads_1: fastq_1
      reads_2: fastq_2
    out: [trimmed_1, trimmed_2, json_report]

  salmon:
    run: salmon_quant.cwl
    in:
      index: salmon_index
      reads_1: fastp/trimmed_1
      reads_2: fastp/trimmed_2
    out: [quant_dir]

Scatter (Parallel Execution)

cwlVersion: v1.2
class: Workflow

requirements:
  ScatterFeatureRequirement: {}

inputs:
  fastq_files:
    type: File[]
  reference: File

outputs:
  bam_files:
    type: File[]
    outputSource: align/bam

steps:
  align:
    run: bwa_mem.cwl
    scatter: fastq
    in:
      fastq: fastq_files
      reference: reference
    out: [bam]

Multi-Scatter

requirements:
  ScatterFeatureRequirement: {}
  MultipleInputFeatureRequirement: {}

steps:
  align:
    run: bwa_mem.cwl
    scatter: [reads_1, reads_2]
    scatterMethod: dotproduct
    in:
      reads_1: fastq_1_array
      reads_2: fastq_2_array
      reference: reference
    out: [bam]

Input File (Job)

# job.yaml
fastq_1:
  class: File
  path: data/sample1_R1.fq.gz
fastq_2:
  class: File
  path: data/sample1_R2.fq.gz
salmon_index:
  class: Directory
  path: ref/salmon_index
threads: 8

Secondary Files

inputs:
  bam:
    type: File
    secondaryFiles:
      - .bai
  reference:
    type: File
    secondaryFiles:
      - pattern: .fai
        required: true
      - pattern: .dict
        required: false

Docker and Singularity

requirements:
  DockerRequirement:
    dockerPull: quay.io/biocontainers/salmon:1.10.0--h7e5ed60_0

hints:
  SoftwareRequirement:
    packages:
      salmon:
        version: ["1.10.0"]

# Run with Docker
cwltool --docker workflow.cwl job.yaml

# Run with Singularity
cwltool --singularity workflow.cwl job.yaml

Resource Requirements

requirements:
  ResourceRequirement:
    coresMin: 4
    coresMax: 16
    ramMin: 8000
    ramMax: 32000
    outdirMin: 10000
    tmpdirMin: 10000

Conditional Steps

cwlVersion: v1.2
class: Workflow

requirements:
  InlineJavascriptRequirement: {}

inputs:
  run_qc: boolean
  fastq: File

steps:
  fastqc:
    run: fastqc.cwl
    when: $(inputs.run_qc)
    in:
      run_qc: run_qc
      fastq: fastq
    out: [html]

Subworkflows

# main.cwl
steps:
  qc_workflow:
    run: subworkflows/qc.cwl
    in:
      reads_1: fastq_1
      reads_2: fastq_2
    out: [qc_report, trimmed_1, trimmed_2]

  alignment_workflow:
    run: subworkflows/align.cwl
    in:
      reads_1: qc_workflow/trimmed_1
      reads_2: qc_workflow/trimmed_2
    out: [bam]

File Arrays and Directories

inputs:
  bam_files:
    type: File[]
  output_dir:
    type: string
    default: "results"

outputs:
  results:
    type: Directory
    outputBinding:
      glob: $(inputs.output_dir)

JavaScript Expressions

requirements:
  InlineJavascriptRequirement: {}

inputs:
  sample_name: string

outputs:
  output_bam:
    type: File
    outputBinding:
      glob: $(inputs.sample_name + ".sorted.bam")

arguments:
  - prefix: -o
    valueFrom: $(inputs.sample_name).sorted.bam

InitialWorkDirRequirement

requirements:
  InitialWorkDirRequirement:
    listing:
      - entry: $(inputs.reference)
        writable: false
      - entryname: config.txt
        entry: |
          threads=$(inputs.threads)
          memory=$(inputs.memory)

Complete RNA-seq Tool

# salmon_quant.cwl
cwlVersion: v1.2
class: CommandLineTool
baseCommand: [salmon, quant]

requirements:
  DockerRequirement:
    dockerPull: quay.io/biocontainers/salmon:1.10.0--h7e5ed60_0
  ResourceRequirement:
    coresMin: 8
    ramMin: 16000

inputs:
  index:
    type: Directory
    inputBinding:
      prefix: -i
  reads_1:
    type: File
    inputBinding:
      prefix: "-1"
  reads_2:
    type: File
    inputBinding:
      prefix: "-2"
  lib_type:
    type: string
    default: A
    inputBinding:
      prefix: -l
  threads:
    type: int
    default: 8
    inputBinding:
      prefix: --threads
  output_dir:
    type: string
    default: quant_output
    inputBinding:
      prefix: -o

outputs:
  quant_dir:
    type: Directory
    outputBinding:
      glob: $(inputs.output_dir)

Run Commands

# Validate CWL file
cwltool --validate workflow.cwl

# Run workflow
cwltool workflow.cwl job.yaml

# Run with Docker
cwltool --docker workflow.cwl job.yaml

# Run with Singularity
cwltool --singularity workflow.cwl job.yaml

# Run with caching
cwltool --cachedir ./cache workflow.cwl job.yaml

# Run on Toil
toil-cwl-runner workflow.cwl job.yaml

Execution Engines

| Engine | Use Case |

|--------|----------|

| cwltool | Reference implementation, local execution |

| Toil | HPC clusters, cloud (AWS, Google, Azure) |

| Arvados | Enterprise workflow management |

| CWL-Airflow | Airflow integration |

Related Skills

  • workflow-management/wdl-workflows - WDL alternative
  • workflow-management/snakemake-workflows - Python-based alternative
  • workflow-management/nextflow-pipelines - Groovy-based alternative

Other skills for the same job

different authors, same section of the catalogue
Doc Coauthoring
by anthropics
vendor ×10

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

4k tokens
File Organizer
by frostant
×10

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

3k tokens
Domain Name Brainstormer
by frostant
×8

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

1k tokens
Brainstorming
by ZhanlinCui
×4

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

626 tokens
Planning With Files
by ZhanlinCui
×3

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

9k tokens scripts
Scientific Brainstorming
by christophacham
×3

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

5k tokens
GitHub Project Management
by ComeOnOliver
×3

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

14k tokens
Grill Me
by ComeOnOliver
×3

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

3k tokens

How to use it

Copy the folder

Take biotender-max/bio-workflow-management-cwl-workflows from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.