nextflow

Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda, Wave), scale a workflow to HPC/SLURM or cloud (AWS Batch, Google Batch, Azure, Kubernetes), or debug a failed/-resume run. Make sure to use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word "Nextflow", and for authoring nf-core-compliant pipelines, modules, configs, and linting.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, well-structured skill body with executable examples, clear routing to real reference files, and useful best-practice habits. It is slightly long for a SKILL.md overview and could tighten its concept explanations and add an explicit failure-recovery loop for the run workflow.

Suggestions

Move or compress the 'Key ideas' and 'Core Concepts at a Glance' sections into references/language.md, keeping SKILL.md as a routing overview to improve token efficiency.

Add an explicit validate→fix→retry loop for failed pipeline runs (e.g. inspect `nextflow log`, fix config/inputs, re-run with `-resume`) to strengthen workflow_clarity for batch/destructive operations.

Dimension	Reasoning	Score
Conciseness	Efficient and well-organized with executable commands and tables rather than prose, but the Overview 'Key ideas' bullets and 'Core Concepts at a Glance' re-explain some domain concepts that could be trimmed or pushed into references.	4 / 5
Actionability	Copy-paste-ready commands throughout — a complete minimal SAYHELLO pipeline, exact `nextflow run` invocations with flags, and two dense CLI tables — covering the common run/develop/config cases concretely.	5 / 5
Workflow Clarity	The 'Two Modes of Work' table routes by goal and Quick Start gives numbered steps with a validation checkpoint ('Always smoke-test with the bundled test profile first'), but the main run path lacks an explicit validate→fix→retry feedback loop for failed runs.	4 / 5
Progressive Disclosure	A clear overview in SKILL.md points to seven well-signaled, one-level-deep references (language, configuration, containers, running-pipelines, nf-core-tools, developing, testing), all of which exist as real files, with content appropriately split and a routing table for navigation.	5 / 5
	Total	18 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally specific, trigger-rich description that clearly states both what the skill does and when to use it, with strong natural-language keywords and file extensions. The only weakness is a slight over-broadening toward generic bioinformatics-workflow work that could collide with neighboring pipeline skills.

Suggestions

Tighten the 'even if the user does not say the word Nextflow' clause to name Nextflow-family signals (e.g. DSL2, processes/channels, .nf) rather than 'any reproducible scientific/bioinformatics workflow work', to reduce overlap with Snakemake/WDL skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build, run, and debug', 'write or test a module/subworkflow with nf-test', 'configure executors/containers', 'scale a workflow to HPC/SLURM or cloud', 'authoring nf-core-compliant pipelines, modules, configs, and linting' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Build, run, and debug Nextflow data pipelines and nf-core workflows end to end') and 'when' with a concrete 'Use whenever the user mentions...' trigger clause enumerating specific phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms including the product names, file extensions, and synonyms: 'Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets', plus concrete pipeline names like 'nf-core/rnaseq, nf-core/sarek' and executor/container names.	5 / 5
Distinctiveness Conflict Risk	Mostly a clear niche (Nextflow/nf-core) with distinct triggers, but the clause 'use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word Nextflow' creates minor overlap risk with adjacent workflow tools (Snakemake, WDL).	4 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/nextflow/SKILL.md
Commit: 1e5eeff

Reviewed: ~17 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.