mcpField
P
parabricks

parabricks

github.com/nvidia-bionemoData & databases502218 installsUpdated 2d ago
Repository

About parabricks

parabricks is an agent skill for selecting and preparing NVIDIA Parabricks `pbrun` commands. It guides tool choice, version-aware options, runtime readiness checks, and STAR argument translation without running workloads by default.

Key features

  1. 01Route requests to a suitable `pbrun` tool
  2. 02Check GPU and container readiness
  3. 03Draft version-aware commands
  4. 04Translate STAR arguments
  5. 05Validate commands against references

Use cases

  1. 01Choose a tool for an assay and input type
  2. 02Check host readiness before execution
  3. 03Translate STAR options into a command draft

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nvidia-bionemo/bionemo-agent-toolkit --skill parabricks

After installing, type/parabricksin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

BENCHMARK.md
evals/
evals.json
evals/files/
rna-batch.json
rna-contracts.json
references/
command-conventions.md
pbrun-applybqsr.md
pbrun-bam2fq.md
pbrun-bammetrics.md
pbrun-bamsort.md
pbrun-bqsr.md
pbrun-collectmultiplemetrics.md
pbrun-dbsnp.md
pbrun-deepsomatic.md
pbrun-deepvariant_germline.md
pbrun-deepvariant.md
pbrun-fq2bam_meth.md
pbrun-fq2bam.md
pbrun-genotypegvcf.md
pbrun-germline.md
pbrun-giraffe.md
pbrun-haplotypecaller.md
pbrun-indexgvcf.md
pbrun-markdup.md
pbrun-minimap2.md
pbrun-mutectcaller.md
pbrun-ont_germline.md
pbrun-pacbio_germline.md
pbrun-pangenome_aware_deepvariant.md
pbrun-pangenome_germline.md
pbrun-postpon.md

Details

From the project README

Parabricks

Purpose

Use this skill to discover the right NVIDIA Parabricks pbrun command, assess runtime readiness, and generate version-aware command guidance for individual tools.

Do not use this skill for whole-workflow inspection, acceleration planning, or wiring optional GPU branches. For pipeline-level work, use genomics-workflow-acceleration.

When to Use This Skill

  • Which pbrun tool fits the user's data and goal
  • GPU, driver, Docker, container, storage, or installation readiness
  • Command shape, flags, and validation for a specific Parabricks tool
  • Reference/index compatibility and CPU-to-Parabricks option translation
  • Troubleshooting a single Parabricks command or tool family
  • Planning-only or "do not run" questions about a named pbrun tool (for example reference/index compatibility, output naming, or flag validity). Use this skill's references to answer; do not skip it because nothing will be executed.

Prerequisites

  • Command guidance: No Parabricks/NGC credential or local GPU/container runtime is required to read references or generate commands.
  • Readiness helper: Requires Bash and GNU coreutils timeout (or gtimeout) on the host being inspected. Missing runtime components are reported as readiness gaps; without a timeout utility it exits before running probes.
  • STAR translation helper: Requires Python 3.7 or newer, using only the standard library. It does not require a GPU or a Parabricks installation.
  • Execution: The documented Docker commands require a supported Linux host, an NVIDIA GPU with sufficient memory, a compatible NVIDIA driver, Docker, NVIDIA Container Toolkit, and access to the selected Parabricks image. Pulling the image may require an NGC API key for authentication to nvcr.io. See runtime-environment.md for version-specific requirements and checks.

Tool scope: read this skill's references and user-supplied manifests; write only requested command artifacts. Use the bundled helpers for translation or an authorized host inspection. Documentation lookups use docs.nvidia.com; image access uses the selected registry only for authorized container execution. These instructions do not grant tool permissions; the host's permission policy still applies to shell, file, network and optional documentation MCP access.

Inputs

Use the user's explicit arguments and supplied manifests as the source of truth; use prior context only where it does not conflict. Read a named manifest before translating it. For command guidance, identify the assay, input paths, reference/index provenance, outputs and target release. Ask only for missing facts that change the answer; label unresolved template values as placeholders. Required inputs are the selected tool's read/reference and output arguments. Optional inputs include intervals, resource bundles, logs and tuning parameters when supported by that tool; do not invent them to fill a template. Runtime-only questions do not need sample metadata. Supplied deployment paths are not permission to probe local data or hardware.

If the user is unsure which tool applies, scan the Tool Reference Index below, then load the matching references/pbrun-<tool>.md file.

Limitations

This skill routes and guides Parabricks commands. It does not install Parabricks, infer missing sample metadata, guarantee output parity, provide clinical interpretation, or promise exact runtime without benchmark data.

Instructions

  1. Identify the requested release. The option references cover v4.7.1; examples from another release are labeled. A software version and image tag can differ: NVIDIA's 4.7.1 image is tagged 4.7.1-1. Preserve the user's verified image selection; use command-conventions.md for the shared launch and validation contract.
  2. Classify the request:
    • Runtime → runtime-environment.md
    • Tool discovery → Tool Reference Index (below)
    • Specific command → matching references/pbrun-<tool>.md. Read it before any web search or MCP lookup; use those only to verify version-sensitive details the reference does not settle.
  3. Combine the tool-specific mapping with shared-options.md rows whose Tools column names the selected command. For STAR argument arrays or multi-lane batches, use the local translation helper; it preserves tokens and reports unmapped semantics without executing a workload.
  4. Collect missing biological and filesystem context before generating commands.
  5. Return the requested command or artifact with unresolved assumptions. For planning-only work, check command text against the references and supplied facts. Filesystem, container and output checks apply only to an authorized execution. Do not turn command preparation into a readiness inspection.

Available Scripts

Run these from the skill directory containing this file; paths are relative to that directory. See the helper prerequisites above.

ScriptPurposeArguments
scripts/check_parabricks_runtime.shInspect the execution host; report gaps without installing anything--path DIR (repeatable), --format text|json, --timeout SECONDS; container probes require --run-container-check or --run-parabricks-check with --parabricks-version TAG / --parabricks-image IMAGE
scripts/translate_star_to_parabricks.pyConvert explicit STAR argument arrays to reviewed command drafts--input FILE or --input -; request and output schema

Output Format

For explanations, give the decision, complete command, and remaining checks. For file requests, write the specified path and schema, then read back and validate the artifact against the input manifest. Report all job IDs, omitted options and unresolved output contracts. Do not replace supplied values with illustrative examples. The runtime helper's JSON has schema_version, checks and readiness results; the translator emits status, draft_argv, command, notes, issues and untranslated for each request.

Tool Reference Index

If the command is named, open references/pbrun-<command>.md directly. For tool selection and official manual links, use tool-index.md. Common routes:

RequestReference
DNA FASTQ alignment / RNA STAR translationfq2bam / rna_fq2bam
Existing BAM germline calls / tumor-normal callshaplotypecaller / mutectcaller
Giraffe graph alignmentgiraffe
STAR-Fusion migrationstarfusion
Recalibration / apply a recalibration reportbqsr / applybqsr
BAM metrics / multiple metric familiesbammetrics / collectmultiplemetrics
GVCF indexing / joint genotypingindexgvcf / genotypegvcf
Panel-of-normals preparation / annotationprepon / postpon
BWA performance optionsperformance

Examples

Runtime Readiness

For GPU, driver, Docker, container, storage, or installation questions, read runtime-environment.md and prefer:

bash scripts/check_parabricks_runtime.sh --format json

Add --path <dir> for known input/output/tmp paths. Run container probes only with user consent.

STAR Translation
python3 scripts/translate_star_to_parabricks.py --input requests.json

Prepare the request using the translation schema. Review issues and untranslated before using the draft. Tool references show the pbrun portion; the shared container envelope is documented once in command-conventions.md.

Troubleshooting

ErrorCauseSolution
Multiple plausible toolsData type or goal underspecifiedAsk for assay, inputs, caller preference, desired output; use Tool Reference Index
Exact flag requestedOptions are version-sensitiveCheck the selected tool reference, NVIDIA docs, or pbrun <tool> --help
Runtime questionGPU, Docker, drivers, or storageUse runtime-environment reference and diagnostic script
Wrong tool familyAssay or input type unclearConfirm DNA/RNA/methylation/long-read/pangenome before routing
CUDA or memory failureRuntime not ready or GPU memory constrainedAssess runtime before tuning command flags
Documentation MCP unavailableConnection, timeout or server errorUse the bundled release reference first; for an unresolved fact, fall back to the official versioned manual and mark any remaining uncertainty

Guardrails

  • Treat command availability and options as version-sensitive.
  • Do not infer exact flags from command names alone.
  • Do not collapse standalone tools and full pipelines when explaining tradeoffs.
  • Do not substitute DNA fq2bam for RNA, or germline for somatic callers.
  • Do not invent sample names, read groups, reference builds, known-sites files, model files, graph resources, container tags, or output paths.
  • Do not install, upgrade, or modify packages. Label setup commands as user-run.
  • Do not claim CPU execution of Parabricks tools.
  • Do not claim biological or VCF parity without a comparison run.
  • Use the optional documentation MCP server only for details the bundled references do not settle. If its connection fails, avoid repeated discovery or lookup loops; use the official manual. Never claim a failed lookup verified an option. Documentation access does not require genomic data or credentials.

Key References

Comments

Markdown supported