Claude Skills by lilinji

Load when merging multiple single-sample scRNA-seq count matrices (one per sample-from-sc-count)

Load when computing per-cell pathway / gene-set scores on a normalised scRNA AnnData via

Load when attaching cell-barcode → sgRNA assignments from a mapping TSV/CSV onto a Perturb-seq

Load when classifying perturbed vs non-perturbed cells in a Perturb-seq / CRISPR-screen scRNA

Load when normalising QC'd scRNA into a PCA-ready AnnData via scanpy / Seurat / SCTransform

Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via

Load when computing per-cell QC metrics (n_genes, total counts, mt%, ribo%) on a single-cell

Load when an external single-cell h5ad/h5/loom/mtx needs to be canonicalised onto the OmicsClaw

Load when generating spliced / unspliced layers from Cell Ranger BAM, FASTQ, STARsolo output,

Load when computing RNA velocity vectors on a scRNA AnnData with spliced / unspliced layers

Load when preprocessing a single-cell ATAC peak × cell AnnData via Signac-style TF-IDF +

Establish a root of trust and verify firmware integrity/authenticity from reset through handoff, including anti-rollback and recovery.

Ensure OTA updates are authenticated, integrity-checked, atomic, and safely recoverable, with regulatory considerations for software changes.

Define architectural partitioning to contain failures, simplify verification, and align safety classes with appropriate isolation.

Load when assigning per-spot cell-type labels on a spatial AnnData via marker-gene scoring

Load when inferring copy-number variation per spot on a preprocessed spatial AnnData with

Load when computing ligand-receptor cell-cell communication on a preprocessed spatial AnnData

Load when comparing two or more experimental conditions (treatment vs control) on a multi-sample

Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics.

Load when deconvolving spot-level cell-type proportions on a Visium-style spatial AnnData

Load when detecting tissue domains / niches on a preprocessed spatial AnnData via Leiden

Load when running pathway / gene-set enrichment per cluster on a preprocessed spatial AnnData

Load when ranking spatially variable genes (SVGs) on a preprocessed spatial AnnData via Moran's

Load when removing batch effects across multiple spatial samples on a multi-batch spatial

Load when extracting a niche / microenvironment subset around a center cell-type by spatial

Load when running the foundational spatial transcriptomics QC + filtering + normalisation

Load when converting spatial transcriptomics raw FASTQ pairs through ST-Pipeline into a `raw_counts.h5ad`

Load when aligning multiple spatial slices into a common coordinate frame on a multi-slice

Load when running spatial autocorrelation / hotspot / co-occurrence / neighbourhood-enrichment

Load when inferring pseudotime / lineage trajectories on a preprocessed spatial AnnData via

Load when estimating RNA velocity on a spatial AnnData with `layers["spliced"]` + `layers["unspliced"]`

Define explicit, testable state machines with safe states, controlled transitions, and error handling suited to medical device safety classes.

Use static analysis (SAST) to detect defects and nonconformities (MISRA, CERT) early, with triage and traceability appropriate to safety class.

Define structure and content for test plans, protocols, and reports that support regulatory submissions and internal verification.

Identify, prioritize, and mitigate security threats for medical devices, integrating with risk management and informing control selection.

Analyze protein-protein interaction networks using STRING, BioGRID, and SASBDB databases. Maps protein identifiers, retrieves interaction networks with confidence scores, performs functional enrichment analysis (GO/KEGG/Reactome), and optionally includes structural data. No API key required for core functionality (STRING). Use when analyzing protein networks, discovering interaction partners, identifying functional modules, or studying protein complexes.

Ensure bidirectional traceability between requirements, hazards/risks, design, code, tests, and anomalies for medical device software.

Establish patterns for unit tests that verify software units against requirements with safety-class-appropriate rigor.

Implement safe USB device connectivity: class selection, enumeration handling, data validation, electrical and safety considerations.

Prepare for US medical licensing exams with progress tracking, weak area analysis, question bank management, and residency match planning.

Annotate VCF variants with Ensembl VEP, ClinVar, and gnomAD. Ranks variants by impact (HIGH/MODERATE/LOW/MODIFIER) and generates a reproducible report.

Secure and robust WiFi connectivity for medical devices: WPA3/enterprise auth, certificate management, coexistence, resilience, and hospital network integration.

Search and fetch structured content from Wikipedia using the MediaWiki API for reliable, encyclopedic information