Claude Skills by lilinji

Load when running two-group metabolomics DE (t-test + log2FC + BH-FDR + PCA) on a feature

Load when normalising a feature × sample metabolomics CSV via median, quantile, total (sum),

Load when running over-representation analysis (ORA) on a metabolite list via Fisher's exact

Load when running per-sample peak picking on a feature × intensity table via `scipy.signal.find_peaks`

Load when imputing missing values (min / median / KNN) and normalising (TIC / median / log)

Load when running univariate two-group testing (t-test / Wilcoxon / ANOVA / Kruskal-Wallis)

Load when running an XCMS-style preprocessing summary on LC-MS metabolomics raw / vendor-converted

Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant

**Skill ID**: `nutrigx-advisor` **Version**: 0.1.0 **Status**: MVP **Author**: David de Lorenzo (ClawBio Community) **Requires**: Python 3.11+, pandas, numpy, matplotlib, seaborn, reportlab (optional) ---

Load when scaffolding a NEW OmicsClaw skill from a natural-language request — generates the

Load when routing a natural-language omics query to the correct domain skill across spatial

Patiently AI simplifies medical documents for patients. Takes doctor's letters, test results, prescriptions, discharge summaries, and clinical notes and explains them in clear, personalised language. Built by PharmaTools.AI.

Identify and handle PHI in software to enforce minimum necessary use, encryption, access control, and retention/deletion policies.

Define regulated-friendly CI/CD pipelines with compliance checks, artifact management, and auditability for medical device software.

Define safe power management patterns: sleep modes, wake sources, power budget, battery monitoring, graceful shutdown, and data preservation.

Load when ingesting a MaxQuant `proteinGroups.txt`, FragPipe `combined_protein.tsv`, DIA-NN

Load when computing two-group differential protein abundance (group2 vs group1, log2FC +

Load when running over-representation analysis (ORA) on a list of proteins via Fisher's exact

Load when summarising peptide identifications (PSM count, unique peptide count, distinct

Load when computing protein-table QC — proteins × samples count, missing-value rate, intensity

Load when summarising PTM sites (phosphorylation, acetylation, ubiquitination, etc.) from

Load when computing per-protein abundance from a peptide / PSM table via LFQ (intensity summation),

Load when summarising cross-linking MS (XL-MS) results — intra/inter-protein link split,

Search PubMed biomedical literature with natural language queries powered by Valyu semantic search. Full-text access, integrate into your AI projects.

Define controlled release process for medical device software: versioning, branching, verification, approvals, documentation, and post-release monitoring.

Provide safe RTOS usage patterns: task design, priorities, IPC, deadlines, priority inversion avoidance, and timing analysis for medical devices.

Define how safety classification (IEC 62304 Class A/B/C) influences architecture, segregation, documentation, and testing, ensuring controls scale with risk.

Load when removing ambient RNA contamination from droplet-based scRNA-seq using a simple

Load when integrating multi-sample scRNA-seq with Harmony, scVI, scANVI, BBKNN, Scanorama,

Load when assigning cell-type labels to a clustered scRNA AnnData via marker dictionaries,

Load when computing cell-cell ligand-receptor communication on an annotated scRNA AnnData

Load when building the neighbour graph, embedding (UMAP/t-SNE/diffmap/PHATE), and clustering

Load when you want resolution-robust single-cell clusters on a preprocessed scRNA AnnData

Load when you want a multi-sample single-cell (scRNA) clustering robust to the choice of

Load when you want a single-cell pseudotime ordering robust to the choice of trajectory method

Load when turning scRNA FASTQ (or existing CellRanger/STARsolo/SimpleAF/kb-python output)

Load when computing per-cell differentiation potency / stemness scores from gene-expression

Load when finding marker genes per cluster or comparing condition expression in single-cell

Load when testing whether cell-type / cluster proportions or neighbourhood densities differ

Load when annotating putative doublets in single-cell RNA-seq using Scrublet, DoubletDetection,

Load when scoring drug sensitivity per cluster on an annotated scRNA AnnData via simple-correlation

Load when running bulk-style pathway enrichment (ORA / GSEA / GSEA-R / GSVA-R) on a per-group

Load when checking raw single-cell FASTQ read quality (Phred / GC / adapter / length) before

Load when removing low-quality cells and lowly-detected genes from a single-cell AnnData

Load when extracting gene programs (NMF / cNMF factorisation) and per-cell program usage

Load when inferring TF → target gene regulatory networks on a normalised scRNA AnnData via

Load when predicting in-silico gene knockout effects on a normalised scRNA AnnData via GRN-based

Load when running a single batch-correction representation (none/Harmony/Scanorama/scVI)

Load when ranking cluster-level marker genes from a clustered single-cell AnnData via Scanpy

Load when aggregating single cells into metacells (sample-aware coarse-grained pseudo-cells)