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).