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 integrating multi-sample scRNA-seq with Harmony, scVI, scANVI, BBKNN, Scanorama, SIMBA, or supported R-backed methods to remove batch effects. Skip when the data is one sample (no batch effect to integrate); upstream merging only (use sc-multi-count).
Skill Claude CodeCodex
Load when assigning cell-type labels to a clustered scRNA AnnData via marker dictionaries, CellTypist, PopV, KNNPredict, SingleR, scmap, SCSA, or a manual cluster-to-label map. Skip when ranking marker genes per cluster (use sc-markers); condition-vs-control DE (use sc-de).
Skill Claude CodeCodex
Load when computing cell-cell ligand-receptor communication on an annotated scRNA AnnData via builtin scorer, LIANA, CellPhoneDB, CellChat (R), or NicheNet (R). Skip when assigning cell-type labels (use sc-cell-annotation); transcription factor → target regulatory networks (use sc-grn).
Skill Claude CodeCodex
Load when building the neighbour graph, embedding (UMAP/t-SNE/diffmap/PHATE), and clustering (Leiden/Louvain) on a normalised single-cell AnnData. Skip when QC/normalisation/HVG/PCA have not run yet (use sc-preprocessing); marker ranking after clustering (use sc-markers).
Skill Claude CodeCodex
Load when you want resolution-robust single-cell clusters on a preprocessed scRNA AnnData — fanning out leiden/louvain across a resolution sweep, scoring members by silhouette + cross-method NMI, and voting a typed consensus. Skip when one resolution suffices (use sc-clustering); spatial domains (use…
Skill Claude CodeCodex
Load when you want a multi-sample single-cell (scRNA) clustering robust to the choice of integration method — fanning out Harmony/Scanorama/scVI + an unintegrated baseline, scoring each by a batch-mixing intrinsic panel, and voting a consensus. Skip when single-batch (use sc-consensus-clustering); one integration…
Skill Claude CodeCodex
Load when you want a single-cell pseudotime ordering robust to the choice of trajectory method — fanning out DPT/Palantir/VIA from a shared root, rank-aligning them, and voting a consensus pseudotime with per-cell uncertainty. Skip when you have branching multi-lineage trajectories; no defined root.
Skill Claude CodeCodex
Load when turning scRNA FASTQ (or existing CellRanger/STARsolo/SimpleAF/kb-python output) into a downstream-ready AnnData. Skip when reads are already counted into AnnData (use sc-standardize-input); raw quality assessment only (use sc-fastq-qc).
Skill Claude CodeCodex
Load when computing per-cell differentiation potency / stemness scores from gene-expression complexity on a scRNA AnnData via the CytoTRACE-simple method. Skip when ordering cells along a trajectory (use sc-pseudotime); marker-based cell-type labelling (use sc-cell-annotation).
Skill Claude CodeCodex
Load when finding marker genes per cluster or comparing condition expression in single-cell RNA-seq. Skip when the data is bulk (use bulkrna-de); spatial (use spatial-de); cluster-only markers without conditions (use sc-markers).
Skill Claude CodeCodex
Load when testing whether cell-type / cluster proportions or neighbourhood densities differ between conditions in a multi-sample scRNA AnnData via Milo, scCODA, simple proportion screen, or R Monte-Carlo permutation. Skip when ranking marker genes (use sc-markers); per-cell DE (use sc-de).
Skill Claude CodeCodex
Load when annotating putative doublets in single-cell RNA-seq using Scrublet, DoubletDetection, DoubletFinder, scDblFinder, or scds. Skip when ambient RNA is the contamination problem (use sc-ambient-removal); before counts exist (use sc-fastq-qc).
Skill Claude CodeCodex
Load when scoring drug sensitivity per cluster on an annotated scRNA AnnData via simple-correlation against drug-target signatures or via CaDRReS-Sc pretrained models (GDSC / PRISM). Skip when the AnnData has no cluster labels yet (use sc-clustering); predicting genetic-perturbation effects (use…
Skill Claude CodeCodex
Load when running bulk-style pathway enrichment (ORA / GSEA / GSEA-R / GSVA-R) on a per-group ranked DE / marker list against a gene-set library. Skip when computing per-cell pathway scores in-place (use sc-pathway-scoring); de-novo gene-program discovery (use sc-gene-programs).
Skill Claude CodeCodex
Load when checking raw single-cell FASTQ read quality (Phred / GC / adapter / length) before counting. Skip when reads are already counted (use sc-qc); bulk FASTQ (use bulkrna-read-qc).
Skill Claude CodeCodex
Load when removing low-quality cells and lowly-detected genes from a single-cell AnnData using QC-derived thresholds or tissue presets. Skip when the full normalize→HVG→PCA→cluster pipeline (use sc-preprocessing); reads are still raw FASTQ (use sc-fastq-qc).
Skill Claude CodeCodex
Load when extracting gene programs (NMF / cNMF factorisation) and per-cell program usage scores from a non-negative scRNA AnnData. Skip when ranking marker genes per cluster (use sc-markers); inferring TF → target regulons (use sc-grn).
Skill Claude CodeCodex
Load when inferring TF → target gene regulatory networks on a normalised scRNA AnnData via pySCENIC (GRNBoost2 + cisTarget + AUCell) or correlation-based GRN fallback (when arboreto is unavailable, in --demo, or with --allow-simplified-grn). Skip when computing ligand-receptor cell-cell signalling (use…
Skill Claude CodeCodex
Load when predicting in-silico gene knockout effects on a normalised scRNA AnnData via GRN-based propagation (Python) or scTenifoldKnk (R). Skip when you have a real Perturb-seq / CRISPR screen (use sc-perturb); predicting drug sensitivity (use sc-drug-response).
Skill Claude CodeCodex
Load when running a single batch-correction representation (none/Harmony/Scanorama/scVI) + clustering of single-cell data as one self-contained unit — normally fanned out as a member of sc-consensus-integration. Skip when you want the full integration consensus (use sc-consensus-integration); resolution-robust…
Skill Claude CodeCodex
Load when ranking cluster-level marker genes from a clustered single-cell AnnData via Scanpy Wilcoxon / t-test / logreg or COSG specificity. Skip when comparing condition-vs-control with replicates (use sc-de); assigning cell-type labels (use sc-cell-annotation).
Skill Claude CodeCodex
Load when aggregating single cells into metacells (sample-aware coarse-grained pseudo-cells) on a normalised scRNA AnnData via SEACells or KMeans on a low-D embedding. Skip when ranking marker genes per cluster (use sc-markers); trajectory pseudotime ordering (use sc-pseudotime).
Skill Claude CodeCodex
Load when merging multiple single-sample scRNA-seq count matrices (one per sample-from-sc-count) into a single downstream-ready AnnData with sample labels. Skip when input is one already-merged AnnData (use sc-standardize-input); FASTQ→counts on each sample (use sc-count).
Skill Claude CodeCodex
Load when computing per-cell pathway / gene-set scores on a normalised scRNA AnnData via AUCell (R or Python) or Scanpy scoregenes. Skip when running condition-vs-control bulk-style enrichment on top of a DE table (use sc-enrichment); de-novo gene-program discovery (use sc-gene-programs).
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: