Data & Analytics

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'mutual-information-fairness-auditor' description: 'Audit and mitigate intersectional, multiclass model fairness by estimating mutual information between prediction-derived variables and sensitive attributes.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: bio-tcr-bcr-analysis-vdjtools-analysis description: Calculate immune repertoire diversity metrics, compare samples, and track clonal dynamics using VDJtools. Use when analyzing repertoire diversity, finding shared clonotypes, or comparing immune profiles between conditions. tool_type: cli primary_tool: VDJtools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-immunoinformatics-tcr-epitope-binding description: Predict TCR-epitope specificity using ERGO-II and deep learning models for T-cell receptor antigen recognition. Match TCRs to their cognate epitopes or predict TCR targets. Use when analyzing TCR repertoire specificity or identifying antigen-reactive T-cells. tool_type: python primary_tool: ERGO-II measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_sh...

--> --- name: 'tme-immune-profiling-agent' description: 'Comprehensive AI-powered tumor microenvironment immune profiling integrating bulk deconvolution, single-cell analysis, and spatial transcriptomics for immunotherapy biomarker discovery.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **TME Immune Profiling Agent** provides comprehensive tumor microenvironment (TME) immune profiling by in...

--> --- name: 'tcr-repertoire-analysis-agent' description: 'AI-powered T-cell receptor repertoire analysis for cancer diagnosis, immunotherapy response prediction, and therapeutic TCR selection using deep learning and multi-layer ML approaches.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **TCR Repertoire Analysis Agent** provides comprehensive T-cell receptor repertoire analysis for cancer...

--> --- name: bio-imaging-mass-cytometry-spatial-analysis description: Spatial analysis of cell neighborhoods and interactions in IMC data. Covers neighbor graphs, spatial statistics, and interaction testing. Use when analyzing spatial relationships between cell types, testing for neighborhood enrichment, or identifying cell-cell interaction patterns in imaging mass cytometry data. tool_type: python primary_tool: squidpy measurable_outcome: Execute skill workflow successfully with valid outpu...

--> --- name: bio-imaging-mass-cytometry-quality-metrics description: Quality metrics for IMC data including signal-to-noise, channel correlation, tissue integrity, and acquisition QC. Use when assessing data quality before analysis or troubleshooting problematic acquisitions. tool_type: python primary_tool: numpy measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-imaging-mass-cytometry-phenotyping description: Cell type assignment from marker expression in IMC data. Covers manual gating, clustering, and automated classification approaches. Use when assigning cell types to segmented IMC cells based on protein marker expression or when phenotyping cells in multiplexed imaging data. tool_type: python primary_tool: scanpy measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_fi...

--> --- name: bio-imaging-mass-cytometry-interactive-annotation description: Interactive cell type annotation for IMC data. Covers napari-based annotation, marker-guided labeling, training data generation, and annotation validation. Use when manually annotating cell types for training classifiers or validating automated phenotyping results. tool_type: python primary_tool: napari measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_...

--> --- name: bio-imaging-mass-cytometry-cell-segmentation description: Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for nuclear and whole-cell segmentation. Use when extracting single-cell data from IMC or MIBI images after preprocessing. tool_type: python primary_tool: cellpose measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-flow-cytometry-gating-analysis description: Manual and automated gating for defining cell populations in flow cytometry. Covers rectangular, polygon, and data-driven gates. Use when identifying cell populations through hierarchical gating strategies. tool_type: r primary_tool: flowWorkspace measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-flow-cytometry-fcs-handling description: Read and manipulate Flow Cytometry Standard (FCS) files. Covers loading data, accessing parameters, and basic data exploration. Use when loading and inspecting flow or mass cytometry data before preprocessing. tool_type: r primary_tool: flowCore measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-flow-cytometry-differential-analysis description: Differential abundance and state analysis for cytometry data. Compare cell populations between conditions using statistical methods. Use when testing for significant changes in cell frequencies or marker expression between groups. tool_type: r primary_tool: CATALYST measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-flow-cytometry-bead-normalization description: Bead-based normalization for CyTOF and high-parameter flow cytometry. Covers EQ bead normalization, signal drift correction, and batch normalization. Use when correcting instrument drift in CyTOF or harmonizing data across batches. tool_type: r primary_tool: CATALYST measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: 'coagulation-thrombosis-agent' description: 'AI-powered analysis of coagulation disorders, thrombosis risk prediction, anticoagulation management, and platelet function assessment using machine learning.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Coagulation and Thrombosis Agent** provides AI-driven analysis of hemostatic disorders, thrombosis risk assessment, and anticoag...

--> --- name: 'chic-ml-framework-agent' description: 'Machine learning framework for inferring high-risk clonal hematopoiesis from complete blood count data without sequencing, reducing the number needed to sequence for CHIP screening.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **CHIC (Clonal Hematopoiesis Inference from Counts) ML Framework Agent** uses machine learning to identify indiv...

--> --- name: 'scfoundation-model-agent' description: 'Unified agent for leveraging single-cell foundation models (scGPT, scBERT, Geneformer, scFoundation) for cross-species annotation, perturbation prediction, and gene network inference.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **scFoundation Model Agent** provides a unified interface to leverage state-of-the-art single-cell foundation...

--> --- name: bio-phasing-imputation-imputation-qc description: Quality control of phasing and imputation results. Filter by INFO scores, assess accuracy, and prepare imputed data for downstream analysis. Use when filtering low-quality imputed variants or validating imputation accuracy before GWAS. tool_type: mixed primary_tool: bcftools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-longread-qc description: Quality control for long-read sequencing data using NanoPlot, NanoStat, and chopper. Generate QC reports, filter reads by length and quality, and visualize read characteristics. Use when assessing ONT or PacBio run quality or filtering reads before assembly or alignment. tool_type: cli primary_tool: nanoplot measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: bio-genome-intervals-interval-arithmetic description: Core interval arithmetic operations including intersect, subtract, merge, complement, map, and groupby using bedtools and pybedtools. Use when finding overlapping regions, removing overlaps, combining adjacent intervals, or transferring annotations between interval files. tool_type: mixed primary_tool: bedtools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_f...

--> --- name: bio-genome-intervals-coverage-analysis description: Calculate read depth and coverage across genomic intervals using bedtools genomecov and coverage. Generate bedGraph files, compute per-base depth, and summarize coverage statistics. Use when assessing sequencing depth, creating coverage tracks, or evaluating target capture efficiency. tool_type: mixed primary_tool: bedtools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tool...

--> --- name: bio-genome-intervals-bigwig-tracks description: Create and read bigWig browser tracks for visualizing continuous genomic data. Convert bedGraph to bigWig, extract signal values, and generate coverage tracks using UCSC tools and pyBigWig. Use when preparing coverage tracks for genome browsers or extracting signal at specific regions. tool_type: mixed primary_tool: pyBigWig measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: ...

--> --- name: bio-genome-assembly-assembly-qc description: Assess genome assembly quality using QUAST for contiguity metrics and BUSCO for completeness. Essential for evaluating assembly success and comparing assemblers. Use when evaluating assembly completeness and quality. tool_type: cli primary_tool: QUAST measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Evaluate genome assembly quality with cont...

--> --- name: bio-crispr-screens-mageck-analysis description: MAGeCK (Model-based Analysis of Genome-wide CRISPR-Cas9 Knockout) for pooled CRISPR screen analysis. Covers count normalization, gene ranking, and pathway analysis. Use when identifying essential genes, drug targets, or resistance mechanisms from dropout or enrichment screens. tool_type: cli primary_tool: mageck measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file -...