Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Load when removing batch effects across multiple spatial samples on a multi-batch spatial AnnData via Harmony, BBKNN, or Scanorama before downstream analysis. Skip when aligning physical slice coordinates (use spatial-register) or for single-batch data (no integration needed — go straight to spatial-domains).
Load when converting spatial transcriptomics raw FASTQ pairs through ST-Pipeline into a `raw_counts.h5ad` ready for spatial-preprocess. Skip when input is already a count-matrix AnnData (go straight to spatial-preprocess) or for non-spatial bulk / scRNA FASTQ (use bulkrna-read-qc / sc-fastq-qc).
Load when aligning multiple spatial slices into a common coordinate frame on a multi-slice spatial AnnData via PASTE optimal transport or STalign image-aware registration. Skip when data is single-slice (no registration needed) or for cross-sample integration in the gene-expression space (use spatial-integrate).
Load when calling CNV segments via CBS-style segmentation on a bin-level log2-ratio CSV from exome / WGS coverage — emits per-segment 5-class CN state (`amplification` / `gain` / `neutral` / `loss` / `deep_deletion`), per-chromosome summary, genome-fraction-altered. Skip when working with single-cell / spatial CNV (use `spatial-cnv`).
Load when summarising structural variants from an SV VCF (DEL / DUP / INV / TRA) — BND-notation parsing, size classification, per-type counts. Skip when working with small SNVs / indels (use `genomics-variant-calling`) or calling SVs from BAM (run Manta / Delly / Sniffles first).
Load when summarising functional impact of an annotated variant CSV — per-IMPACT counts (HIGH / MODERATE / LOW / MODIFIER), top consequences, gene-affected count. Skip when input is a raw VCF (convert with `bcftools +split-vep` first), when calling raw variants (use `genomics-variant-calling`), or filtering VCFs (use `genomics-vcf-operations`).
Load when summarising / filtering a VCF — variant classification (SNP / MNP / INS / DEL / COMPLEX), Ti/Tv ratio, QUAL / DP threshold filtering, INFO-field parsing. Skip when the input is a BAM (use `genomics-variant-calling` upstream first) or when adding functional annotations (use `genomics-variant-annotation`).
Reverse-engineer missing or incomplete OpenFastTrace system requirements and arc42-style design documentation from a project's user guide, existing documentation, tests, and code. Use when the agent must draft or repair `doc/system_requirements.md`, `doc/design.md`, and `doc/design/` chapters; infer features, requirements, scenarios, and design items; align design coverage with requirements; and report contradictions or open issues found during reverse engineering.
Inspect and print USD scene hierarchy using the wu CLI. Use when the user wants to examine a USD file structure, list prims, show prim types, variants, API schemas, collections, custom token attributes, query a specific prim, limit traversal depth, or get scene statistics for .usd/.usda/.usdc/.usdz files.
Load when summarising PTM sites (phosphorylation, acetylation, ubiquitination, etc.) from a per-site CSV — site-class assignment (Olsen et al. Class I/II/III by `localization_probability`), per-PTM-type counts, amino-acid distribution, sites-per-protein. Skip when raw spectra are the input or when you only need protein-level abundance (use `proteomics-quantification`).