Research

--> --- name: bio-bgpt-paper-search description: Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone. tool_type: mixed primary_tool: Unknown measurable_outcome: Execute skill workflow successfully with vali...

--> --- name: bio-metabolomics-pathway-enrichment description: Metabolomics pathway analysis using MetaboAnalystR (KEGG, Reactome), pathview visualization, MSEA, mummichog, and network-based topology analysis. tool_type: mixed primary_tool: metabolomics measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Map metabolites to biological pathways and perform enrichment, topology, and network analysis.

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'pubmed-ncbi-mcp-server' description: 'Use the cyanheads PubMed MCP server to search PubMed, fetch metadata and full text, generate citations, inspect MeSH, and find related research.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'biocontext-ai-mcp-registry' description: 'Use the BioContextAI Registry to discover, compare, and select biomedical MCP servers for bioinformatics, systems biology, and biomedical AI workflows.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: bio-literature description: Parse scholarly articles (PDF, DOI, URL) to extract metadata, GEO accessions, and acquisition links using OpenAlex + GROBID pipelines. tool_type: mixed primary_tool: literature measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-genomics-variant-calling description: Germline and somatic variant calling (SNVs, Indels) using GATK HaplotypeCaller, Mutect2, DeepVariant, or FreeBayes. Includes GVCF workflow, VQSR, and hard filtering. tool_type: mixed primary_tool: genomics measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Germline and somatic small variant calling (SNVs, Indels). Supports GATK HaplotypeCaller, M...

--> --- name: bio-genomics-cnv-calling description: Copy number variant detection from exome/WGS data using CNVkit, Control-FREEC, or GATK gCNV. Supports tumor-normal pairs, tumor-only, and germline modes. tool_type: mixed primary_tool: genomics measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Detect copy number variants from targeted/exome/WGS sequencing data.

--> --- name: bio-sc-doublet-detection description: Doublet detection and removal using Scrublet (Python), DoubletFinder (R), and scDblFinder (R). Essential QC step before clustering. tool_type: mixed primary_tool: singlecell measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Detect and remove doublets (multiple cells captured in one droplet) from scRNA-seq data. Essential QC step before clustering.

--> --- name: bio-sc-cell-annotation description: Automated cell type annotation using marker genes, CellTypist, SingleR, or scmap. Supports custom references and marker gene lists. tool_type: mixed primary_tool: singlecell measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- You are **SC Annotate**, a specialised OmicsClaw agent for automated cell type annotation in single-cell data. Your role is to as...

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'precision-grounded-variant-summarization' description: 'Produce evidence-grounded genetic variant summaries with provenance, conflict handling, and hallucination controls.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: 'notion-research-documentation' description: 'Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Enables comprehensive research workf...

Load when estimating RNA velocity on a spatial AnnData with `layers["spliced"]` + `layers["unspliced"]` via scVelo (stochastic / deterministic / dynamical) or veloVI (deep generative). Skip when input lacks the spliced/unspliced layers (must be quantified upstream by velocyto / kb-python / STARsolo) or for non-spatial scRNA velocity (use `sc-velocity`).

Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics. Skip if the data is single-cell (use sc-de) or bulk (use bulkrna-de), or for spatially variable expression discovery (use spatial-genes).

Load when computing ligand-receptor cell-cell communication on a preprocessed spatial AnnData with `obs[cell_type_key]` (default `leiden`) via LIANA (default), CellPhoneDB, FastCCC, or CellChat (R). Skip when running scRNA-only L-R inference (use `sc-cell-communication`) or when no cell-type labels exist (run `spatial-annotate` or `spatial-domains` first).

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), or for bulk RNA-seq (use bulkrna-qc) or spatial (use spatial-preprocess).

Load when computing per-cell QC metrics (n_genes, total counts, mt%, ribo%) on a single-cell AnnData before filtering. Skip when reads are still raw FASTQ (use sc-fastq-qc) or you want to filter cells now (use sc-filter).

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) or for batch correction across samples (use sc-batch-integration).

Load when computing per-cell pathway / gene-set scores on a normalised scRNA AnnData via AUCell (R or Python) or Scanpy score_genes. Skip when running condition-vs-control bulk-style enrichment on top of a DE table (use sc-enrichment) or for de-novo gene-program discovery (use sc-gene-programs).

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) or for assigning cell-type labels (use sc-cell-annotation).

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 finding marker genes per cluster or comparing condition expression in single-cell RNA-seq. Skip if the data is bulk (use bulkrna-de) or spatial (use spatial-de), or for cluster-only markers without conditions (use sc-markers).

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 extracting GEO accessions, dataset metadata, and downloadable references from a scientific paper (PDF / URL / DOI / PubMed ID / raw text) for downstream omics analysis. Skip when the dataset is already in hand or when only routing a query (use `orchestrator`).

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).