nf-claw
Each pipeline is an unmodified git submodule pinned to a release, with a generated skill.md that says how to run it and a reference.md that lists every parameter. The nfclaw command checks a run before it starts, records what a replay needs, chains pipelines and serves all of this to agents over MCP. Scheduled workflows move the pins to new releases once the tests and each changed pipeline's own test run pass.
Every pipeline is an nf-core release pinned as a git submodule — wrapped, never forked.
skill.md and the full parameter reference are generated from the pinned schema, not written by hand.
CI regenerates the context from pinned schemas and checks for drift. This site builds from the same repository.
How an agent uses it
Three commands, straight from the repository's agent guide: the catalog narrows the library to one pipeline, its generated skill.md gives the exact command and inputs, and nfclaw runs the pinned release and records the run.
Grep the catalog for a keyword instead of reading it whole — one line per pipeline.
$ grep rnaseq catalog.md | `rnaseq` | 3.27.0 | samplesheet (sample, fastq_1, fastq_2, strandedness, seq_platform, seq_center, genome_bam, transcriptome_bam, percent_mapped) | --outdir/ (configured results); pipeline_info/ (run metadata when enabled); MultiQC report (conditional) | RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control. | | `scrnaseq` | 4.2.0 | samplesheet (sample, fastq_1, fastq_2, fastq_barcode, expected_cells, seq_center, sample_type, feature_type) | --outdir/ (configured results); pipeline_info/ (run metadata when enabled); MultiQC report (conditional) | Pipeline for processing 10x Genomics single cell rnaseq data | | `smrnaseq` | 2.4.1 | samplesheet (sample, fastq_1, fastq_2) | --outdir/ (configured results); pipeline_info/ (run metadata when enabled); MultiQC report (conditional) | Small RNA-Seq Best Practice Analysis Pipeline. |
skill.md is generated from the pinned schema: the exact command, inputs and required parameters.
$ cat pipelines/rnaseq/skill.md # rnaseq ## Run it ```bash git submodule update --init pipelines/rnaseq/upstream # first time only nfclaw run rnaseq --input samplesheet.csv --outdir results -profile docker # raw equivalent (the submodule is already pinned to this release, so no -r is needed): nextflow run pipelines/rnaseq/upstream -profile docker --input samplesheet.csv --outdir results ``` ## Inputs | column | type | required | allowed values | constraints | |---|---|---|---|---| | `sample` | string or integer | yes | | matches `^\S+$` | …
nfclaw validates first, runs the pinned release and records every run where status can read it.
# the bundled test profile, end to end $ nfclaw run rnaseq --demo --outdir results # or your own data $ nfclaw run rnaseq --input samplesheet.csv --outdir results -profile docker $ nfclaw status results status: success
The same three steps work for every pipeline in the library.See rnaseq in full
The collection
Every nf-core pipeline in the library, grouped by research domain. Search by name or tool, filter by domain, inspect any pipeline and compare up to four side by side.
95 pipelines across 9 domains
nf-core/rnaseq
RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.
Pinned release · Sep 23, 2026 · latest-release
What an agent reads
Each pipeline has one generated skill: the exact run command, inputs, required parameters and the complete parameter reference. Search the skills and every parameter they list.
95 skills
nf-core/rnaseq
RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.
nfclaw run rnaseq --input samplesheet.csv --outdir results -profile dockernfclaw run rnaseq --demo --outdir results # adds the upstream test profile (-profile test,docker)--inputstring (file path)Path to the sample sheet (CSV) containing metadata about the experimental samples.
--outdirstring (directory path)The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.
Results land in --outdir; the files and directory layout depend on the selected workflow, parameters and publication settings. Run metadata is normally placed in <outdir>/pipeline_info/ (execution report, software versions), when those outputs are enabled. The pinned tree includes MultiQC support; a report is produced only when its workflow step runs. --skip-multiqc true disables that report. nfclaw run also writes <outdir>/provenance/ with the exact params file and the run log, <outdir>/provenance/logs/run.log — the whole launch, whose last line states the outcome (Nextflow's own log is <outdir>/.nextflow.log); unless --no-provenance it adds a run manifest (pinned version, commit and exact command), input/output SHA-256 checksums, and a replayable commands.sh.
The exact output files and directory layout for this release are documented upstream: github.com/nf-core/rnaseq/blob/3.27.0/docs/output.md
Check a run — in the foreground or the background — with nfclaw status <outdir>: success, still running, how it ended (with the error), or stopped without an outcome; exit 0 success, 3 running, 1 otherwise.
Build snapshot
Commits and automation captured from git and GitHub Actions when this site was built. Rebuild the site to refresh this view.
Snapshot captured
Versioned history
Each pipeline is pinned to a specific nf-core release. This timeline tracks those pinned versions and the library's own milestones — newest first.
95 pinned releases spanning 2021–2026 · 1 library tags
9 entries
16 entries
From the repository
Every page here is rendered from the repository: the README, the agent guide, the guides in docs/ and the contributor notes. A change to one of those files appears here on the next build.