Update to Life Sciences NGS Analysis

{
  "name": "ngs-analysis-router",
  "description": "Route BCL, FASTQ, BAM/CRAM, count-matrix, or VCF sequencing requests to the right public NGS analysis skill and ask only the missing assay-specific setup questions.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 296
    }
  ],
  "skill_md_contents": "---\nname: ngs-analysis-router\ndescription: Route BCL, FASTQ, BAM/CRAM, count-matrix, or VCF sequencing requests to the right public NGS analysis skill and ask only the missing assay-specific setup questions.\n---\n\n# Life Sciences NGS Analysis Router\n\nUse this skill as the top-level entrypoint for ambiguous or broad sequencing-analysis requests.\n\n## Start Here\n\nInspect the available inputs before asking the user questions. Look for:\n\n- Illumina run-folder files: `RunInfo.xml`, `RunParameters.xml`, `SampleSheet.csv`, `Data/Intensities/BaseCalls`\n- FASTQs: `*.fastq`, `*.fq`, `*.fastq.gz`, `*.fq.gz`\n- BAM/CRAM/VCF: `*.bam`, `*.cram`, `*.vcf`, `*.vcf.gz`\n- count matrices: `matrix.mtx`, `features.tsv`, `barcodes.tsv`, `*.h5`, `*.h5ad`, `*.rds`\n- metadata: sample sheets, design files, target BEDs, reference FASTA/GTF, primer files\n\nRead `references/intake-schema.json` and `references/pipeline-registry.json` when forming the route.\n\n## Intake Rules\n\nAsk the smallest set of missing questions needed to choose a defensible pipeline. Do not ask the full questionnaire if file inspection already answers a field.\n\nAlways resolve:\n\n- input type\n- assay type\n- desired output\n- organism/reference\n- paired-end vs single-end when FASTQs are involved\n- any assay-specific design file or metadata required for the requested result\n- runtime constraints: local/HPC/cloud, container availability, and whether installs are allowed\n\nFor human data, ask whether cloud upload is allowed before suggesting BaseSpace, Terra, DNAnexus, or any cloud path.\n\n## Routing\n\nRoute to one leaf skill:\n\n- BCL run folder or demultiplexing: `ngs-bcl-to-fastq`\n- QC/trimming only: `ngs-fastq-qc`\n- WGS/WES/panel variants: `ngs-dna-variant-calling`, then a subtype skill when the analysis model is clear\n- germline WGS/WES/panel variants: `ngs-dna-germline-variants`\n- tumor-normal or tumor-only somatic variants: `ngs-dna-somatic-variants`\n- UMI, duplex, or low-frequency targeted panels: `ngs-dna-umi-panel-variants`\n- bulk RNA-seq kickoff: `ngs-bulk-rnaseq`\n- bulk RNA-seq FASTQ-to-count QC: `ngs-bulk-rnaseq-counts-qc`\n- bulk RNA-seq differential expression from counts: `ngs-bulk-rnaseq-differential-expression`\n- single-cell or single-nucleus FASTQ-to-matrix kickoff: `ngs-scrna-seq`\n- single-cell or single-nucleus post-count QC/annotation/UMAP: `scrna-seq-qc`\n- epigenomics kickoff: `ngs-epigenomics-peaks`\n- ATAC-seq QC/peaks/accessibility: `ngs-atacseq-peaks-qc`\n- ChIP-seq, CUT&RUN, or CUT&Tag QC/peaks: `ngs-chip-cutrun-peaks-qc`\n- 16S/18S/ITS/COI amplicons: `ngs-amplicon-microbiome`\n- shotgun metagenomics: `ngs-shotgun-metagenomics`\n- runtime/package setup only: `ngs-runtime-env`\n\nPrefer public, runtime-installable packages and nf-core workflows. Surface license/EULA/account boundaries before using proprietary or cloud tools.\n\n## Preflight\n\nBefore proposing installation or execution, run a preflight plan from the repo root:\n\n```bash\npython plugins/ngs-analysis/scripts/ngs_preflight.py --pipeline <pipeline_key> --emit-install-plan\n```\n\nWhen the user needs an approval-ready install handoff, write persistent install artifacts:\n\n```bash\npython plugins/ngs-analysis/scripts/ngs_preflight.py --pipeline <pipeline_key> --manager micromamba --install-plan-outdir runtime_readiness/<pipeline_key>_install\n```\n\nTreat `install_plan.json` as the canonical review artifact. `install_commands.sh` is generated from the same plan and stays review-only unless the user explicitly approves execution with `NGS_RUN_INSTALL_COMMANDS=1`.\n\nFor reference- or database-heavy pipelines, also create a resource plan before saying the workflow is runnable:\n\n```bash\npython plugins/ngs-analysis/scripts/ngs_reference_manager.py plan --pipeline <pipeline_key> --genome-build <build> --outdir resource_readiness/<pipeline_key>\n```\n\nUse `--include-optional` for shotgun, amplicon, or motif-enabled epigenomics runs when optional databases materially affect the requested output.\n\nUse `--network-checks` only when the user allows network checks. Use `--install-missing --yes` only when the user explicitly asks to install.\n\n## Output Contract\n\nReturn:\n\n1. the routed analysis type and confidence\n2. missing essential parameters, if any\n3. recommended public pipeline or package family\n4. local tool preflight summary\n5. preflight-first command or next concrete action\n6. caveats around licenses, cloud upload, database size, and reference data\n"
}