Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fmschulz/omics-skills --skill bio-prefect-dask-nextflowgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fmschulz/omics-skills/bio-prefect-dask-nextflow)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/bio-prefect-dask-nextflow"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/bio-prefect-dask-nextflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fmschulz/omics-skills/bio-prefect-dask-nextflow"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/bio-prefect-dask-nextflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00974 |
| Opus 5.5 | $0.00014 | $0.00390 |
| Sonnet 5.5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
bio-prefect-dask-nextflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bio Prefect + Dask + Nextflow
Choose a workflow engine for a local, distributed, or HPC bioinformatics pipeline and scaffold it.
Supplementary docs last verified: 2026-10-01 against Prefect 3.8.7, prefect-dask 0.3.7 (maintained in the Prefect repository; install with prefect[dask]), Dask/distributed 2026.8.0, and Nextflow v26.04.6.
Instructions
- Collect requirements: scheduler, container policy, data location, scale, and whether steps are CLI tools or Python functions.
- Choose the engine with decision-matrix.md: Nextflow for file-based CLI tools on a scheduler, Prefect+Dask for Python-heavy or dynamic work, or a hybrid with Prefect as the control plane and Nextflow as the compute plane.
- Generate a runnable scaffold with a clear data layout, per-step resources, and explicit thread counts (
task.cpusin Nextflow,threads_per_workerin Dask). - Pin the software: pixi for tool stacks or Apptainer images on HPC, uv for Python (
uv add "prefect[dask]"). Nextflow v26.04+ parses scripts and configs with the strict syntax by default; write code that passesnextflow lint. - Run heavy work through the scheduler, never on a login node. Submit the Nextflow launcher with
scripts/submit_nextflow.sh; it runs from the current directory, so call it from the project root. - Validate with a small test dataset, then check resume (
-resume, or Prefect retries plus idempotent outputs) before scaling.
Quick Reference
| Task | Action |
|---|---|
| Engine choice | decision-matrix.md |
| Prefect+Dask scaffold | prefect-dask.md |
| Prefect on Slurm | prefect-hpc-slurm.md |
| Nextflow on HPC | nextflow-hpc.md |
| Submit Nextflow through Slurm | SLURM_ACCOUNT=... scripts/submit_nextflow.sh main.nf 'data/*.fastq.gz' results |
| Multi-cluster sites | Export SBATCH_CLUSTERS, SBATCH_PARTITION, and SBATCH_QOS before the wrapper; --parsable then prints jobid;cluster, so strip the suffix and pass the cluster to squeue -M and sacct -M |
| Examples | examples.md |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago Changed · +6 lines · -1 tokens per session 04b1a471e15b
- 1mo ago First seen · 66 lines · 37 tokens per session scan A 9692b1a7168f
bio-prefect-dask-nextflow is a skill published in the GitHub repository fmschulz/omics-skills (11 stars, last pushed 23d ago), licensed MIT. It adds 36 tokens to every session and 974 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
genomic-intelligence
Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
torch-geometric
Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.
bulk-rnaseq
Prepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq…
geniml
Supports audited local Geniml genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.
waypoint-bio
Supports work with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the waypoint CLI from the waypoint-bio package. Covers embedding microbiome samples, fine-tuning on taxonomic…
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…