Skip to content

nota-america/forgecat-agent-profiles / profiles/anthropics/knowledge-work-plugins/anthropics_knowledge-work-plugins_bio-research/for-claude/.claude/skills/nextflow-development

nextflow-development

Unverified

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

scripts/config/pipelines/rnaseq.yaml

View on GitHub
name: rnaseq
version: "3.22.2"
description: "Gene expression quantification and differential expression analysis"

# Documentation and source - NOTE: Update version in URLs when upgrading pipeline
urls:
  documentation: "https://nf-co.re/rnaseq/{version}/"
  parameters: "https://nf-co.re/rnaseq/{version}/parameters/"
  output_docs: "https://nf-co.re/rnaseq/{version}/docs/output/"
  github: "https://github.com/nf-core/rnaseq"
  releases: "https://github.com/nf-core/rnaseq/releases"

data_types:
  - RNA-seq
  - mRNA-seq
  - bulk RNA-seq

detection_hints:
  filename:
    - rna
    - rnaseq
    - mrna
    - expression
  directory:
    - rnaseq
    - rna
    - expression
    - transcriptome

samplesheet:
  input_types:
    - fastq

  columns:
    - name: sample
      required: true
      type: string
      inference: filename
      description: "Sample identifier"

    - name: fastq_1
      required: true
      type: path
      inference: auto
      description: "Absolute path to R1 FASTQ"

    - name: fastq_2
      required: false
      type: path
      inference: auto
      description: "Absolute path to R2 FASTQ (empty for single-end)"

    - name: strandedness
      required: true
      type: enum
      allowed:
        - auto
        - forward
        - reverse
        - unstranded
      default: "auto"
      inference: default
      description: "Library strandedness (auto recommended)"

decision_points:
  - parameter: genome
    prompt: "Which reference genome matches your organism?"
    options:
      - value: GRCh38
        label: "Human GRCh38/hg38 (recommended for human)"
        description: "Latest human reference assembly"
      - value: GRCh37
        label: "Human GRCh37/hg19 (legacy)"
        description: "Older human reference for compatibility"
      - value: mm10
        label: "Mouse mm10/GRCm38"
        description: "Mouse reference genome"
      - value: BDGP6
        label: "Drosophila BDGP6"
        description: "Fruit fly reference"
    default: GRCh38
    recommendation: "Default to GRCh38 for human samples"

  - parameter: aligner
    prompt: "Which alignment strategy would you prefer?"
    options:
      - value: star_salmon
        label: "STAR + Salmon (recommended)"
        description: "Most accurate, standard for differential expression"
      - value: star_rsem
        label: "STAR + RSEM"
        description: "Better for isoform-level quantification"
      - value: hisat2
        label: "HISAT2"
        description: "Lower memory requirements, faster"
    default: star_salmon
    recommendation: "Use star_salmon unless memory-constrained or need isoforms"

test_profile:
  command: "nextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq"
  duration: "15 minutes"
  success_indicators:
    - "test_rnaseq/multiqc/multiqc_report.html"
  log_pattern: "Pipeline completed successfully"

run_command:
  template: |
    nextflow run nf-core/rnaseq \
        -r 3.22.2 \
        -profile docker \
        --input {samplesheet} \
        --outdir {outdir} \
        --genome {genome} \
        --aligner {aligner} \
        -resume

outputs:
  primary:
    - path: "star_salmon/salmon.merged.gene_counts.tsv"
      description: "Raw gene counts for DESeq2/edgeR"
    - path: "star_salmon/salmon.merged.gene_tpm.tsv"
      description: "TPM normalized expression values"
    - path: "star_salmon/*.bam"
      description: "Aligned reads"

  validation:
    - file: "multiqc/multiqc_report.html"
      check: exists
      description: "QC report must exist"
    - file: "star_salmon/salmon.merged.gene_counts.tsv"
      check: non_empty
      description: "Count matrix must have data"

resources:
  min_memory: "8.GB"
  recommended_memory: "32.GB"
  min_cpus: 4
  recommended_cpus: 8
  disk_space: "100.GB"

troubleshooting:
  - error: "STAR index fails"
    fix: "Increase memory with --max_memory '64.GB' or provide pre-built --star_index"
  - error: "Low alignment rate"
    fix: "Verify genome matches species; check FastQC for adapter contamination"
  - error: "Strandedness detection fails"
    fix: "Specify explicitly with --strandedness reverse (or forward/unstranded)"
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall