Skill Tracer
Skills › Knowledge Work Plugins › nextflow-development

nextflow-development

skill · 290 lines · Apache-2.0 · bio-research/skills/nextflow-development/SKILL.md

The facts

Its description

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.

The description the agent reads to decide when to use it.

From its settingsline 3

When it starts

The agent would pick this skill when someone asks to run an nf-core/Nextflow bioinformatics pipeline on sequencing data — local FASTQ files or public GEO/SRA datasets — for RNA-seq, WGS/WES, or ATAC-seq analysis, including samplesheet creation and variant calling.

Things a person might say (the model's guesses)

  • “I have paired-end RNA-seq FASTQ files from my yeast experiment — can you run the nf-core rnaseq pipeline and give me gene counts?”
  • “Reanalyze GSE110004 and find the differentially expressed genes between the treated and control samples.”
  • “I need to call variants on my WGS samples; can you set up and run nf-core sarek?”

A model's summary of when it is used.

A model's reading

Runs scripts

python scripts/sra_geo_fetch.py, python scripts/check_environment.py, python scripts/detect_data_type.py (first 5 of 9 lines)

Scripts the text names. Found by matching words, so treat them as pointers.

Found by matching wordsline 36 line 39 line 42 line 58 line 100

Files it mentions

references/geo-sra-acquisition.md, references/troubleshooting.md, references/pipelines/rnaseq.md, references/pipelines/sarek.md, references/pipelines/atacseq.md (first 5 of 13 lines)

Files the text names, such as ones to read or write. Found by matching words, so treat them as pointers.

Found by matching wordsline 30 line 84 line 104 line 105 line 106

What leads to it

  • start hands off to this when the researcher wants to set up a sequencing pipeline start, line 74

Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.

A model's reading

Licence

Apache-2.0, from bio-research/skills/nextflow-development/LICENSE.txt

The terms its author shares it under, which let it be shown here.

From the repositoryLICENSE.txt, line 1 licence text
Other files in this skill (21) Close

The text

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1---
2name: nextflow-development
3description: 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.
4---
5
6# nf-core Pipeline Deployment
7
8Run nf-core bioinformatics pipelines on local or public sequencing data.
9
10**Target users:** Bench scientists and researchers without specialized bioinformatics training who need to run large-scale omics analyses—differential expression, variant calling, or chromatin accessibility analysis.

nf-core Pipeline Deployment

Run nf-core bioinformatics pipelines on local or public sequencing data.

Target users: Bench scientists and researchers without specialized bioinformatics training who need to run large-scale omics analyses—differential expression, variant calling, or chromatin accessibility analysis.

Raw lines 1 to 11
12## Workflow Checklist
14```
15- [ ] Step 0: Acquire data (if from GEO/SRA)
16- [ ] Step 1: Environment check (MUST pass)
17- [ ] Step 2: Select pipeline (confirm with user)
18- [ ] Step 3: Run test profile (MUST pass)
19- [ ] Step 4: Create samplesheet
20- [ ] Step 5: Configure & run (confirm genome with user)
21- [ ] Step 6: Verify outputs
22```
24---

Workflow Checklist

- [ ] Step 0: Acquire data (if from GEO/SRA)
- [ ] Step 1: Environment check (MUST pass)
- [ ] Step 2: Select pipeline (confirm with user)
- [ ] Step 3: Run test profile (MUST pass)
- [ ] Step 4: Create samplesheet
- [ ] Step 5: Configure & run (confirm genome with user)
- [ ] Step 6: Verify outputs
Raw lines 12 to 25
26## Step 0: Acquire Data (GEO/SRA Only)
28**Skip this step if user has local FASTQ files.**
30For public datasets, fetch from GEO/SRA first. See [references/geo-sra-acquisition.md](references/geo-sra-acquisition.md) for the full workflow.
32**Quick start:**
34```bash
35# 1. Get study info
36python scripts/sra_geo_fetch.py info GSE110004
38# 2. Download (interactive mode)
39python scripts/sra_geo_fetch.py download GSE110004 -o ./fastq -i
41# 3. Generate samplesheet
42python scripts/sra_geo_fetch.py samplesheet GSE110004 --fastq-dir ./fastq -o samplesheet.csv
43```
45**DECISION POINT:** After fetching study info, confirm with user:
46- Which sample subset to download (if multiple data types)
47- Suggested genome and pipeline
49Then continue to Step 1.
51---

Step 0: Acquire Data (GEO/SRA Only)

Skip this step if user has local FASTQ files.

For public datasets, fetch from GEO/SRA first. See references/geo-sra-acquisition.md for the full workflow.

Quick start:

# 1. Get study info
python scripts/sra_geo_fetch.py info GSE110004

# 2. Download (interactive mode)
python scripts/sra_geo_fetch.py download GSE110004 -o ./fastq -i

# 3. Generate samplesheet
python scripts/sra_geo_fetch.py samplesheet GSE110004 --fastq-dir ./fastq -o samplesheet.csv

DECISION POINT: After fetching study info, confirm with user:

  • Which sample subset to download (if multiple data types)
  • Suggested genome and pipeline

Then continue to Step 1.

Raw lines 26 to 52
Reads a file references/geo-sra-acquisition.md :30
Runs code python scripts/sra_geo_fetch.py :36
53## Step 1: Environment Check
55**Run first. Pipeline will fail without passing environment.**
57```bash
58python scripts/check_environment.py
59```
61All critical checks must pass. If any fail, provide fix instructions:

Step 1: Environment Check

Run first. Pipeline will fail without passing environment.

python scripts/check_environment.py

All critical checks must pass. If any fail, provide fix instructions:

Raw lines 53 to 62
Runs code python scripts/check_environment.py :58
63### Docker issues
65| Problem | Fix |
66|---------|-----|
67| Not installed | Install from https://docs.docker.com/get-docker/ |
68| Permission denied | `sudo usermod -aG docker $USER` then re-login |
69| Daemon not running | `sudo systemctl start docker` |

Docker issues

ProblemFix
Not installedInstall from https://docs.docker.com/get-docker/
Permission deniedsudo usermod -aG docker $USER then re-login
Daemon not runningsudo systemctl start docker
Raw lines 63 to 70
71### Nextflow issues
73| Problem | Fix |
74|---------|-----|
75| Not installed | `curl -s https://get.nextflow.io \| bash && mv nextflow ~/bin/` |
76| Version < 23.04 | `nextflow self-update` |

Nextflow issues

ProblemFix
Not installed`curl -s https://get.nextflow.io \bash && mv nextflow ~/bin/`
Version < 23.04nextflow self-update
Raw lines 71 to 77
78### Java issues
80| Problem | Fix |
81|---------|-----|
82| Not installed / < 11 | `sudo apt install openjdk-11-jdk` |
84**Do not proceed until all checks pass.** For HPC/Singularity, see [references/troubleshooting.md](references/troubleshooting.md).
86---

Java issues

ProblemFix
Not installed / < 11sudo apt install openjdk-11-jdk

Do not proceed until all checks pass. For HPC/Singularity, see references/troubleshooting.md.

Raw lines 78 to 87
Reads a file references/troubleshooting.md :84
88## Step 2: Select Pipeline
90**DECISION POINT: Confirm with user before proceeding.**
92| Data Type | Pipeline | Version | Goal |
93|-----------|----------|---------|------|
94| RNA-seq | `rnaseq` | 3.22.2 | Gene expression |
95| WGS/WES | `sarek` | 3.7.1 | Variant calling |
96| ATAC-seq | `atacseq` | 2.1.2 | Chromatin accessibility |
98Auto-detect from data:
99```bash
100python scripts/detect_data_type.py /path/to/data
101```
103For pipeline-specific details:
104- [references/pipelines/rnaseq.md](references/pipelines/rnaseq.md)
105- [references/pipelines/sarek.md](references/pipelines/sarek.md)
106- [references/pipelines/atacseq.md](references/pipelines/atacseq.md)
108---

Step 2: Select Pipeline

DECISION POINT: Confirm with user before proceeding.

Data TypePipelineVersionGoal
RNA-seqrnaseq3.22.2Gene expression
WGS/WESsarek3.7.1Variant calling
ATAC-seqatacseq2.1.2Chromatin accessibility

Auto-detect from data:

python scripts/detect_data_type.py /path/to/data

For pipeline-specific details:

  • references/pipelines/rnaseq.md
  • references/pipelines/sarek.md
  • references/pipelines/atacseq.md
Raw lines 88 to 109
Runs code python scripts/detect_data_type.py :100
Reads a file references/pipelines/rnaseq.md :104
Reads a file references/pipelines/sarek.md :105
Reads a file references/pipelines/atacseq.md :106
110## Step 3: Run Test Profile
112**Validates environment with small data. MUST pass before real data.**
114```bash
115nextflow run nf-core/<pipeline> -r <version> -profile test,docker --outdir test_output
116```
118| Pipeline | Command |
119|----------|---------|
120| rnaseq | `nextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq` |
121| sarek | `nextflow run nf-core/sarek -r 3.7.1 -profile test,docker --outdir test_sarek` |
122| atacseq | `nextflow run nf-core/atacseq -r 2.1.2 -profile test,docker --outdir test_atacseq` |
124Verify:
125```bash
126ls test_output/multiqc/multiqc_report.html
127grep "Pipeline completed successfully" .nextflow.log
128```
130If test fails, see [references/troubleshooting.md](references/troubleshooting.md).
132---

Step 3: Run Test Profile

Validates environment with small data. MUST pass before real data.

nextflow run nf-core/<pipeline> -r <version> -profile test,docker --outdir test_output
PipelineCommand
rnaseqnextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq
sareknextflow run nf-core/sarek -r 3.7.1 -profile test,docker --outdir test_sarek
atacseqnextflow run nf-core/atacseq -r 2.1.2 -profile test,docker --outdir test_atacseq

Verify:

ls test_output/multiqc/multiqc_report.html
grep "Pipeline completed successfully" .nextflow.log

If test fails, see references/troubleshooting.md.

Raw lines 110 to 133
Reads a file references/troubleshooting.md :130
134## Step 4: Create Samplesheet

Step 4: Create Samplesheet

Raw lines 134 to 135
136### Generate automatically
138```bash
139python scripts/generate_samplesheet.py /path/to/data <pipeline> -o samplesheet.csv
140```
142The script:
143- Discovers FASTQ/BAM/CRAM files
144- Pairs R1/R2 reads
145- Infers sample metadata
146- Validates before writing
148**For sarek:** Script prompts for tumor/normal status if not auto-detected.

Generate automatically

python scripts/generate_samplesheet.py /path/to/data <pipeline> -o samplesheet.csv

The script:

  • Discovers FASTQ/BAM/CRAM files
  • Pairs R1/R2 reads
  • Infers sample metadata
  • Validates before writing

For sarek: Script prompts for tumor/normal status if not auto-detected.

Raw lines 136 to 149
Runs code python scripts/generate_samplesheet.py :139
150### Validate existing samplesheet
152```bash
153python scripts/generate_samplesheet.py --validate samplesheet.csv <pipeline>
154```

Validate existing samplesheet

python scripts/generate_samplesheet.py --validate samplesheet.csv <pipeline>
Raw lines 150 to 155
Runs code python scripts/generate_samplesheet.py :153
156### Samplesheet formats
158**rnaseq:**
159```csv
160sample,fastq_1,fastq_2,strandedness
161SAMPLE1,/abs/path/R1.fq.gz,/abs/path/R2.fq.gz,auto
162```
164**sarek:**
165```csv
166patient,sample,lane,fastq_1,fastq_2,status
167patient1,tumor,L001,/abs/path/tumor_R1.fq.gz,/abs/path/tumor_R2.fq.gz,1
168patient1,normal,L001,/abs/path/normal_R1.fq.gz,/abs/path/normal_R2.fq.gz,0
169```
171**atacseq:**
172```csv
173sample,fastq_1,fastq_2,replicate
174CONTROL,/abs/path/ctrl_R1.fq.gz,/abs/path/ctrl_R2.fq.gz,1
175```
177---

Samplesheet formats

rnaseq:

sample,fastq_1,fastq_2,strandedness
SAMPLE1,/abs/path/R1.fq.gz,/abs/path/R2.fq.gz,auto

sarek:

patient,sample,lane,fastq_1,fastq_2,status
patient1,tumor,L001,/abs/path/tumor_R1.fq.gz,/abs/path/tumor_R2.fq.gz,1
patient1,normal,L001,/abs/path/normal_R1.fq.gz,/abs/path/normal_R2.fq.gz,0

atacseq:

sample,fastq_1,fastq_2,replicate
CONTROL,/abs/path/ctrl_R1.fq.gz,/abs/path/ctrl_R2.fq.gz,1
Raw lines 156 to 178
179## Step 5: Configure & Run

Step 5: Configure & Run

Raw lines 179 to 180
181### 5a. Check genome availability
183```bash
184python scripts/manage_genomes.py check <genome>
185# If not installed:
186python scripts/manage_genomes.py download <genome>
187```
189Common genomes: GRCh38 (human), GRCh37 (legacy), GRCm39 (mouse), R64-1-1 (yeast), BDGP6 (fly)

5a. Check genome availability

python scripts/manage_genomes.py check <genome>
# If not installed:
python scripts/manage_genomes.py download <genome>

Common genomes: GRCh38 (human), GRCh37 (legacy), GRCm39 (mouse), R64-1-1 (yeast), BDGP6 (fly)

Raw lines 181 to 190
Runs code python scripts/manage_genomes.py :184
191### 5b. Decision points
193**DECISION POINT: Confirm with user:**
1951. **Genome:** Which reference to use
1962. **Pipeline-specific options:**
197 - **rnaseq:** aligner (star_salmon recommended, hisat2 for low memory)
198 - **sarek:** tools (haplotypecaller for germline, mutect2 for somatic)
199 - **atacseq:** read_length (50, 75, 100, or 150)

5b. Decision points

DECISION POINT: Confirm with user:

  1. Genome: Which reference to use
  2. Pipeline-specific options:
  3. rnaseq: aligner (star_salmon recommended, hisat2 for low memory)
  4. sarek: tools (haplotypecaller for germline, mutect2 for somatic)
  5. atacseq: read_length (50, 75, 100, or 150)
Raw lines 191 to 200
201### 5c. Run pipeline
203```bash
204nextflow run nf-core/<pipeline> \
205 -r <version> \
206 -profile docker \
207 --input samplesheet.csv \
208 --outdir results \
209 --genome <genome> \
210 -resume
211```
213**Key flags:**
214- `-r`: Pin version
215- `-profile docker`: Use Docker (or `singularity` for HPC)
216- `--genome`: iGenomes key
217- `-resume`: Continue from checkpoint
219**Resource limits (if needed):**
220```bash
221--max_cpus 8 --max_memory '32.GB' --max_time '24.h'
222```
224---

5c. Run pipeline

nextflow run nf-core/<pipeline> \
    -r <version> \
    -profile docker \
    --input samplesheet.csv \
    --outdir results \
    --genome <genome> \
    -resume

Key flags:

  • -r: Pin version
  • -profile docker: Use Docker (or singularity for HPC)
  • --genome: iGenomes key
  • -resume: Continue from checkpoint

Resource limits (if needed):

--max_cpus 8 --max_memory '32.GB' --max_time '24.h'
Raw lines 201 to 225
226## Step 6: Verify Outputs

Step 6: Verify Outputs

Raw lines 226 to 227
228### Check completion
230```bash
231ls results/multiqc/multiqc_report.html
232grep "Pipeline completed successfully" .nextflow.log
233```

Check completion

ls results/multiqc/multiqc_report.html
grep "Pipeline completed successfully" .nextflow.log
Raw lines 228 to 234
235### Key outputs by pipeline
237**rnaseq:**
238- `results/star_salmon/salmon.merged.gene_counts.tsv` - Gene counts
239- `results/star_salmon/salmon.merged.gene_tpm.tsv` - TPM values
241**sarek:**
242- `results/variant_calling/*/` - VCF files
243- `results/preprocessing/recalibrated/` - BAM files
245**atacseq:**
246- `results/macs2/narrowPeak/` - Peak calls
247- `results/bwa/mergedLibrary/bigwig/` - Coverage tracks
249---

Key outputs by pipeline

rnaseq:

  • results/star_salmon/salmon.merged.gene_counts.tsv - Gene counts
  • results/star_salmon/salmon.merged.gene_tpm.tsv - TPM values

sarek:

  • results/variant_calling/*/ - VCF files
  • results/preprocessing/recalibrated/ - BAM files

atacseq:

  • results/macs2/narrowPeak/ - Peak calls
  • results/bwa/mergedLibrary/bigwig/ - Coverage tracks
Raw lines 235 to 250
251## Quick Reference
253For common exit codes and fixes, see [references/troubleshooting.md](references/troubleshooting.md).

Quick Reference

For common exit codes and fixes, see references/troubleshooting.md.

Raw lines 251 to 254
Reads a file references/troubleshooting.md :253
255### Resume failed run
257```bash
258nextflow run nf-core/<pipeline> -resume
259```
261---

Resume failed run

nextflow run nf-core/<pipeline> -resume
Raw lines 255 to 262
263## References
265- [references/geo-sra-acquisition.md](references/geo-sra-acquisition.md) - Downloading public GEO/SRA data
266- [references/troubleshooting.md](references/troubleshooting.md) - Common issues and fixes
267- [references/installation.md](references/installation.md) - Environment setup
268- [references/pipelines/rnaseq.md](references/pipelines/rnaseq.md) - RNA-seq pipeline details
269- [references/pipelines/sarek.md](references/pipelines/sarek.md) - Variant calling details
270- [references/pipelines/atacseq.md](references/pipelines/atacseq.md) - ATAC-seq details
272---

References

  • references/geo-sra-acquisition.md - Downloading public GEO/SRA data
  • references/troubleshooting.md - Common issues and fixes
  • references/installation.md - Environment setup
  • references/pipelines/rnaseq.md - RNA-seq pipeline details
  • references/pipelines/sarek.md - Variant calling details
  • references/pipelines/atacseq.md - ATAC-seq details
Raw lines 263 to 273
Reads a file references/geo-sra-acquisition.md :265
Reads a file references/troubleshooting.md :266
Reads a file references/installation.md :267
Reads a file references/pipelines/rnaseq.md :268
Reads a file references/pipelines/sarek.md :269
Reads a file references/pipelines/atacseq.md :270
274## Disclaimer
276This skill is provided as a prototype example demonstrating how to integrate nf-core bioinformatics pipelines into Claude Code for automated analysis workflows. The current implementation supports three pipelines (rnaseq, sarek, and atacseq), serving as a foundation that enables the community to expand support to the full set of nf-core pipelines.
278It is intended for educational and research purposes and should not be considered production-ready without appropriate validation for your specific use case. Users are responsible for ensuring their computing environment meets pipeline requirements and for verifying analysis results.
280Anthropic does not guarantee the accuracy of bioinformatics outputs, and users should follow standard practices for validating computational analyses. This integration is not officially endorsed by or affiliated with the nf-core community.

Disclaimer

This skill is provided as a prototype example demonstrating how to integrate nf-core bioinformatics pipelines into Claude Code for automated analysis workflows. The current implementation supports three pipelines (rnaseq, sarek, and atacseq), serving as a foundation that enables the community to expand support to the full set of nf-core pipelines.

It is intended for educational and research purposes and should not be considered production-ready without appropriate validation for your specific use case. Users are responsible for ensuring their computing environment meets pipeline requirements and for verifying analysis results.

Anthropic does not guarantee the accuracy of bioinformatics outputs, and users should follow standard practices for validating computational analyses. This integration is not officially endorsed by or affiliated with the nf-core community.

Raw lines 274 to 281
282## Attribution
284When publishing results, cite the appropriate pipeline. Citations are available in each nf-core repository's CITATIONS.md file (e.g., https://github.com/nf-core/rnaseq/blob/3.22.2/CITATIONS.md).

Attribution

When publishing results, cite the appropriate pipeline. Citations are available in each nf-core repository's CITATIONS.md file (e.g., https://github.com/nf-core/rnaseq/blob/3.22.2/CITATIONS.md).

Raw lines 282 to 285
286## Licenses
288- **nf-core pipelines:** MIT License (https://nf-co.re/about)
289- **Nextflow:** Apache License, Version 2.0 (https://www.nextflow.io/about-us.html)
290- **NCBI SRA Toolkit:** Public Domain (https://github.com/ncbi/sra-tools/blob/master/LICENSE)

Licenses

  • nf-core pipelines: MIT License (https://nf-co.re/about)
  • Nextflow: Apache License, Version 2.0 (https://www.nextflow.io/about-us.html)
  • NCBI SRA Toolkit: Public Domain (https://github.com/ncbi/sra-tools/blob/master/LICENSE)
Raw lines 286 to 290

From anthropics/knowledge-work-plugins at 2574e29, 2026-10-27. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.