OmicsClaw

LLM-grounded biological interpretation of a verified typed consensus run. Reads the typed run dir + the original adata, runs inline per-cluster DE, looks up markers in a bundled tissue-keyed marker DB, and asks the chair LLM to (γ) name each cluster's likely cell type with mandatory marker citations and (β) recommend top-3 next-step skills with mandatory evidence_refs. Output banner [A+I: Interpreted on verified consensus]. Failure-mode contract per ADR 0012.

Multi-resolution typed consensus over sc-clustering. Fans out leiden / louvain at several resolutions in parallel, scores members by silhouette + cross-method NMI, runs kmode / weighted / LCA consensus on the surviving base clusterings, and emits a verified report carrying the mandatory A-path banner per ADR 0010.

Multi-method consensus over spatial-domains. Fans out 5 methods in parallel, computes a SACCELERATOR-style base-clustering ranking, runs typed consensus (kmode / weighted / LCA), and emits a verified consensus report with the mandatory A-path banner per ADR 0010.

Load when scaffolding a NEW OmicsClaw skill from a natural-language request — generates the skill directory layout (SKILL.md, parameters.yaml, references/, tests/) under the chosen domain. Skip when modifying an existing skill (edit its files directly) or when only routing a query (use `orchestrator`).

Load when routing a natural-language omics query to the correct domain skill across spatial / singlecell / genomics / proteomics / metabolomics / bulkrna domains via keyword / LLM / hybrid matching. Skip when the target skill is already known — invoke that skill directly.

Load when copying this directory to bootstrap a new OmicsClaw v2 skill (rename, fill in, then `git add`). Skip when an existing skill already covers the request.

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) or for inferring TF → target regulons (use sc-grn).

Load when removing batch effects from a multi-cohort bulk RNA-seq dataset using ComBat (R or Python implementation). Skip if there is only one batch, or for single-cell batch integration (use sc-batch-integration), or for spatial multi-slice integration (use spatial-integrate).

Load when discovering gene co-expression modules and hub genes in a bulk RNA-seq cohort via WGCNA-style soft-thresholded networks. Skip for direct DE comparison (use bulkrna-de) or PPI lookup of an existing gene list (use bulkrna-ppi-network); single-cell co-expression uses sc-grn instead.

Load when comparing gene expression between two conditions in bulk RNA-seq count data. Skip when the data is single-cell (use sc-de) or spatial (use spatial-de), or when you need exon-level alternative splicing (use bulkrna-splicing).

Load when estimating cell-type proportions in bulk RNA-seq samples from a single-cell or signature-matrix reference. Skip if the data is already single-cell (no deconvolution needed) or for spatial deconvolution (use spatial-deconv).

Load when running pathway / GO term enrichment on a bulk RNA-seq DE result list. Skip if the input is single-cell (use sc-enrichment), spatial (use spatial-enrichment), or for metabolite pathways (use metabolomics-pathway-enrichment).

Load when converting gene identifiers between Ensembl, Entrez, and HGNC symbol in a bulk RNA-seq count matrix. Skip if the input is already in the desired identifier system, for organisms outside human/mouse, or for non-bulk-counts inputs.

Load when querying STRING for the protein-protein interaction subgraph induced by a bulk RNA-seq DEG list and finding hub genes. Skip for pathway enrichment of the same list (use bulkrna-enrichment) or for de novo co-expression network discovery (use bulkrna-coexpression).

Load when checking a bulk RNA-seq count matrix for library-size outliers, gene detection rates, and sample-sample correlation before DE. Skip if data is raw FASTQ (use bulkrna-read-qc) or aligner logs (use bulkrna-read-alignment), or for single-cell counts (use sc-qc).

Load when summarising STAR / HISAT2 / Salmon alignment-rate logs in bulk RNA-seq. Skip if data is raw FASTQ (use bulkrna-read-qc) or already counted (use bulkrna-qc), or for genome-DNA alignment (use genomics-alignment).

Load when checking raw FASTQ quality (Phred / GC / adapter / Q20-Q30) before alignment in bulk RNA-seq. Skip if reads are already aligned (use bulkrna-read-alignment) or counted (use bulkrna-qc), or for single-cell FASTQ (use sc-fastq-qc).

Load when summarising rMATS / SUPPA2 alternative-splicing output and identifying significant differential splicing events. Skip if you only have count-level DE (use bulkrna-de) or for splicing in single-cell or spatial data (currently unsupported).

Load when stratifying patients by gene expression and testing for survival differences (Kaplan-Meier + Cox) in bulk RNA-seq. Skip if no time-to-event clinical data exists, or for non-bulk cohorts (single-cell / spatial survival is not supported).

Load when placing bulk RNA-seq samples on a single-cell reference's pseudotime axis (NNLS deconvolution + nearest-neighbour mapping). Skip for plain cell-type proportions (use bulkrna-deconvolution alone) or for native single-cell trajectory inference (use sc-pseudotime).

Load when computing alignment QC metrics (mapping rate, MAPQ distribution, insert size, duplicate rate, proper-pair rate) from a SAM or BAM file produced by any short-/long-read aligner (BWA / Bowtie2 / Minimap2). Skip when running the alignment step itself or when only FASTQ-level QC is needed (use `genomics-qc`).

Load when computing genome-assembly QC metrics — N50/N90, L50/L90, total length, contig count, GC content, longest-contig — from a FASTA produced by any assembler (SPAdes / Megahit / Flye / Canu). Skip when running the assembly itself or when assessing alignment quality (use `genomics-alignment`).

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 a peak file (BED / narrowPeak) from ATAC-seq / ChIP-seq / CUT&Tag — peak count, width distribution, per-chromosome counts, score statistics. Skip when calling peaks from BAM (run MACS / Genrich externally first) or when working with single-cell ATAC (use `scatac-preprocessing`).

Load when summarising a phased VCF (output of WhatsHap / SHAPEIT5 / Eagle2) — phased fraction of het variants, phase-block N50, PS-field parsing, pipe-delimited genotype detection. Skip when the input is unphased (run a phaser first) or when calling small variants (use `genomics-variant-calling`).

Load when running pre-alignment FASTQ quality control — Phred quality scores, Q20/Q30 rates, GC / N content, read-length distribution, adapter-contamination detection. Skip when working with already-aligned BAMs (use `genomics-alignment`) or when peak / variant files are the input (use the relevant downstream skill).

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 small variants (SNVs / indels) from a VCF or computing demo-pattern variant statistics (Ti/Tv ratio, per-chromosome distribution, SNP / indel split). Skip when filtering / merging VCFs (use `genomics-vcf-operations`), when calling structural variants (use `genomics-sv-detection`), or when adding functional annotations (use `genomics-variant-annotation`).

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`).

Load when ingesting a MaxQuant `proteinGroups.txt`, FragPipe `combined_protein.tsv`, DIA-NN report, or generic CSV / TSV protein-quantification table — normalises columns to a standard schema, emits `tables/proteins.csv`. Skip when raw spectra are the input (run the search engine first) or when the file is already OmicsClaw schema.

Load when computing two-group differential protein abundance (group2 vs group1, log2FC + p-value + BH-adjusted FDR) via Welch t-test, equal-variance t-test, or Mann-Whitney on a wide protein × sample CSV. Skip when you need multi-condition DE (run pairwise contrasts manually) or label-based TMT linear-mixed models.

Load when running over-representation analysis (ORA) on a list of proteins via Fisher's exact test against a built-in 8-pathway DEMO dictionary, with BH-FDR correction. Skip when needing a real pathway database (this skill is demo-only — use `bulkrna-enrichment` for real KEGG / Reactome / MSigDB) or for rank-based GSEA.

Load when summarising peptide identifications (PSM count, unique peptide count, distinct protein count, score / charge distributions) from a peptide-level CSV produced by MaxQuant / FragPipe / DIA-NN. Skip when raw spectra are the input (run a search engine first) or when working with protein-quantification tables (use `proteomics-ms-qc`).

Load when computing protein-table QC — proteins × samples count, missing-value rate, intensity CV (median + mean) — from a MaxQuant / FragPipe / DIA-NN protein-quantification CSV. Skip when raw mzML / RAW spectra are the input (run a search engine first) or when peptide-level QC is needed (use `proteomics-identification`).

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`).

Load when computing per-protein abundance from a peptide / PSM table via LFQ (intensity summation), iBAQ (intensity / tryptic peptide count), or spectral counting (PSMs per protein). Skip when the input is already protein-level (use `proteomics-ms-qc` for QC) or for label-based TMT / iTRAQ workflows (search upstream first).

Load when summarising cross-linking MS (XL-MS) results — intra/inter-protein link split, optional FDR filtering, distance-constraint validation against a per-crosslinker (DSS / BS3 / EDC / DSSO / DSBU) max distance. Skip when raw spectra are the input (run XlinkX / pLink / xiSEARCH first) or no XL-MS experiment was performed.

Load when preprocessing a single-cell ATAC peak × cell AnnData via Signac-style TF-IDF + LSI + Leiden, producing a clustered UMAP-ready object. Skip when input is fragments or BAM (peak calling not implemented here) or for scRNA preprocessing (use sc-preprocessing).

Load when removing ambient RNA contamination from droplet-based scRNA-seq using a simple subtraction path, CellBender, or SoupX. Skip when the contamination is multiplet barcodes (use sc-doublet-detection) or before counts exist (use sc-count).