Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.
This repository also configures its own agents. See what OmicsClaw tells them →
Skill Claude CodeCodex
Load when attaching cell-barcode → sgRNA assignments from a mapping TSV/CSV onto a Perturb-seq expression AnnData, producing standardised perturbation / sgRNA / target-gene obs columns. Skip when the AnnData already has perturbation labels (use sc-perturb); raw guide-calling from FASTQ (use upstream demuxlet /…
Skill Claude CodeCodex
Load when classifying perturbed vs non-perturbed cells in a Perturb-seq / CRISPR-screen scRNA AnnData via the pertpy Mixscape workflow. Skip when guide labels are not yet attached to the expression object (use sc-perturb-prep); in-silico KO predictions on unperturbed data (use sc-in-silico-perturbation).
Skill Claude CodeCodex
Load when normalising QC'd scRNA into a PCA-ready AnnData via scanpy / Seurat / SCTransform / Pearson residuals. Skip when QC thresholds are still undecided (use sc-qc); batch correction across samples (use sc-batch-integration).
Skill Claude CodeCodex
Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R). Skip when ranking marker genes per cluster (use sc-markers); RNA velocity vector fields (use sc-velocity).
Skill Claude CodeCodex
Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering. Skip when reads are still raw FASTQ (use sc-fastq-qc); you want to filter cells now (use sc-filter).
Skill Claude CodeCodex
Load when an external single-cell h5ad/h5/loom/mtx needs to be canonicalised onto the OmicsClaw AnnData contract before downstream scRNA skills run. Skip when data already came from sc-count (already canonical); bulk RNA-seq (use bulkrna-qc); spatial (use spatial-preprocess).
Skill Claude CodeCodex
Load when generating spliced / unspliced layers from Cell Ranger BAM, FASTQ, STARsolo output, or velocyto loom — the prerequisite for sc-velocity. Skip when AnnData already has spliced+unspliced layers (use sc-velocity); any non-velocity preprocessing (use sc-preprocessing).
Skill Claude CodeCodex
Load when computing RNA velocity vectors on a scRNA AnnData with spliced / unspliced layers via scVelo (stochastic / dynamical / steady-state); dynamical mode additionally exports latent time. Skip when input lacks spliced+unspliced layers (use sc-velocity-prep); trajectory pseudotime ordering (use sc-pseudotime).
Skill Claude CodeCodex
Load when you want a verified multi-method consensus over spatial tissue domains on a preprocessed spatial AnnData — fanning out N domain methods, ranking base clusterings, and emitting a typed consensus with cross-method disagreement. Skip when one method suffices (use spatial-domains); the data is single-cell (use…
Skill Claude CodeCodex
Load when biologically interpreting a finished verified consensus run (consensus-domains / sc-consensus-clustering) — inline DE, marker-DB lookup, and LLM cell-type naming with mandatory marker citations + evidence-bound next-step recommendations. Skip when the consensus run failed (fix it first); forward query→skill…
Skill Claude CodeCodex
Load when assigning per-spot cell-type labels on a spatial AnnData via marker-gene scoring or scRNA-reference mapping (Tangram / scANVI / CellAssign). Skip when computing spot-level cell-type proportions for multi-cell-per-spot platforms (use spatial-deconv); tissue-domain detection (use spatial-domains).
Skill Claude CodeCodex
Load when inferring copy-number variation per spot on a preprocessed spatial AnnData with chromosome-annotated genes via infercnvpy (default — log-ratio sliding-window) or Numbat (R, allele-aware clone deconvolution). Skip when var["chromosome"] / var["start"] / var["end"] gene-coord metadata is missing; no…
Skill Claude CodeCodex
Load when computing ligand-receptor cell-cell communication on a preprocessed spatial AnnData with obs[celltypekey] (default leiden) via LIANA (default), CellPhoneDB, FastCCC, or CellChat (R). Skip when running scRNA-only L-R inference (use sc-cell-communication); no cell-type labels exist (use spatial-annotate).
Skill Claude CodeCodex
Load when comparing two or more experimental conditions (treatment vs control) on a multi-sample preprocessed spatial AnnData via PyDESeq2 pseudobulk or Wilcoxon DE — needs obs[conditionkey], obs[samplekey], and cluster labels. Skip when running per-cluster DE on one condition (use spatial-de); comparing two slices…
Skill Claude CodeCodex
Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics. Skip when the data is single-cell (use sc-de); bulk (use bulkrna-de); spatially variable expression discovery (use spatial-genes).
Skill Claude CodeCodex
Load when deconvolving spot-level cell-type proportions on a Visium-style spatial AnnData using a labelled scRNA reference (FlashDeconv / Cell2location / RCTD / DestVI / Tangram / others). Skip when each spot is a single cell already (Xenium / MERFISH) (use spatial-annotate); tissue-domain detection (use…
Skill Claude CodeCodex
Load when detecting tissue domains / niches on a preprocessed spatial AnnData via Leiden / Louvain (spatial-weighted) or graph-neural backends (SpaGCN / STAGATE / GraphST / BANKSY / CellCharter). Skip when ranking spatially variable genes (use spatial-genes); spot-level cell-type annotation (use spatial-annotate).
Skill Claude CodeCodex
Load when running pathway / gene-set enrichment per cluster on a preprocessed spatial AnnData via Enrichr (over-representation), GSEA (preranked), or ssGSEA (per-cell scores). Skip when ranking spatially variable genes (use spatial-genes); comparing pathways across conditions (use spatial-condition).
Skill Claude CodeCodex
Load when ranking spatially variable genes (SVGs) on a preprocessed spatial AnnData via Moran's I, SpatialDE, SPARK-X, or FlashS. Skip when detecting tissue domains (use spatial-domains); differential expression between groups (use spatial-de).
Skill Claude CodeCodex
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); single-batch data (no integration needed) (use spatial-domains).
Skill Claude CodeCodex
Load when extracting a niche / microenvironment subset around a center cell-type by spatial radius from a labelled spatial AnnData, producing a smaller AnnData of centers + their within-radius neighbours. Skip when running global tissue-domain detection (use spatial-domains); cross-condition comparison (use…
Skill Claude CodeCodex
Load when running the foundational spatial transcriptomics QC + filtering + normalisation + HVG + PCA + neighbour-graph + Leiden pipeline on a Visium / Xenium / generic spatial AnnData. Skip when raw FASTQs need converting first (use spatial-raw-processing); tissue-domain detection on already-preprocessed data (use…
Skill Claude CodeCodex
Load when converting spatial transcriptomics raw FASTQ pairs through ST-Pipeline into a rawcounts.h5ad ready for spatial-preprocess. Skip when input is already a count-matrix AnnData (use spatial-preprocess); non-spatial bulk / scRNA FASTQ (use bulkrna-read-qc).
Skill Claude CodeCodex
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); cross-sample integration in the gene-expression space (use spatial-integrate).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: