Data & Analytics

Expert-level Data Analyst skill covering SQL analysis, Python/pandas data manipulation, statistical analysis, A/B test design and interpretation, business intelligence, dashboard design, and data storytelling

Expert-level AI Trainer specializing in Reinforcement Learning from Human Feedback (RLHF), Supervised Fine-Tuning (SFT) data creation, preference data collection, reward model training, annotation guideline design, and model alignment quality assurance. Use when: ai-training, rlhf, rlaif, preference-data, sft.

Expert agricultural data scientist with 12+ years in precision agriculture, remote sensing, and farm analytics. Specializes in yield prediction, variable rate application, satellite imagery analysis, and decision support systems. Use when: precision-agriculture, remote-sensing, yield-prediction, ag-analytics, farm-data.

Closed-loop inverse-design validation. Given a target deformation field, solve the inverse problem on a trained surrogate (Ridge / linear), then run an Abaqus FEA verification and compare surrogate-predicted vs. true displacement field. Reports MSE / MAE / max-abs-error / NRMSE side-by-side, plus saturated-channel count, so you can quantify the surrogate-FEA gap. Use when the user wants to evaluate "is my surrogate good enough for inverse design?", "how big is the surrogate-FEA gap on this ta...

Use when working with GOAT's Windmill instance — running or syncing analytics tools, inspecting job execution, adding a new tool, or checking which f/goat/tools/* scripts exist. Use the Windmill MCP tools for API calls.

Use when inspecting, debugging, or understanding the GOAT PostgreSQL database — querying projects, layers, users, orgs, teams, roles, jobs, or checking data state during local dev.

Universal VC investor analysis and outreach agent. Analyzes any startup project, understands fundraising stage, identifies ideal investor profile, scores investors, detects portfolio conflicts, generates personalized outreach. Starts with discovery questions to understand the project. Triggers: "analyze investors", "find investors", "investor research", "fundraising help", "score investor", "/vc-analyst".

Spreadsheet creation, editing, and analysis. Use when working with .xlsx, .xlsm, .csv, .tsv files for: (1) Creating spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Data analysis and visualization, (5) Recalculating formulas.

--> --- name: bio-splicing-pipeline description: End-to-end alternative splicing analysis from FASTQ to differential splicing results. Aligns with STAR 2-pass mode, performs junction QC, runs rMATS-turbo for differential analysis, and generates sashimi visualizations. Use when performing comprehensive splicing analysis from raw RNA-seq data. tool_type: mixed primary_tool: rMATS-turbo measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - ...

--> --- name: bio-workflows-spatial-pipeline description: End-to-end spatial transcriptomics workflow for Visium/Xenium data. Covers data loading, preprocessing, spatial analysis, domain detection, and visualization with Squidpy. Use when analyzing spatial transcriptomics data. tool_type: python primary_tool: Squidpy workflow: true depends_on: - spatial-transcriptomics/spatial-data-io - spatial-transcriptomics/spatial-preprocessing - spatial-transcriptomics/spatial-neighbors - spatial-transcr...

--> --- name: bio-workflows-rnaseq-to-de description: End-to-end RNA-seq workflow from FASTQ files to differential expression results. Covers QC, quantification (Salmon or STAR+featureCounts), and DESeq2 analysis with visualization. Use when running RNA-seq from FASTQ to DE results. tool_type: mixed primary_tool: DESeq2 workflow: true depends_on: - read-qc/fastp-workflow - rna-quantification/alignment-free-quant - rna-quantification/tximport-workflow - differential-expression/deseq2-basics - ...

--> --- name: bio-workflows-proteomics-pipeline description: End-to-end proteomics workflow from MaxQuant output to differential protein abundance. Orchestrates data import, normalization, imputation, and statistical testing with MSstats or limma. Use when processing mass spectrometry proteomics. tool_type: mixed primary_tool: MSstats workflow: true depends_on: - proteomics/data-import - proteomics/proteomics-qc - proteomics/quantification - proteomics/protein-inference - proteomics/different...

--> --- name: bio-workflows-multi-omics-pipeline description: End-to-end multi-omics integration workflow. Orchestrates data harmonization, MOFA/mixOmics integration, factor interpretation, and downstream analysis across transcriptomics, proteomics, metabolomics, and other modalities. Use when integrating multiple omics datasets. tool_type: r primary_tool: MOFA2 workflow: true depends_on: - multi-omics-integration/data-harmonization - multi-omics-integration/mofa-integration - multi-omics-int...

--> --- name: bio-workflows-microbiome-pipeline description: End-to-end 16S amplicon workflow from FASTQ reads to differential abundance. Orchestrates DADA2 ASV inference, taxonomy assignment, diversity analysis, and compositional testing with ALDEx2. Use when processing 16S/ITS amplicon data. tool_type: r primary_tool: dada2 workflow: true depends_on: - microbiome/amplicon-processing - microbiome/taxonomy-assignment - microbiome/diversity-analysis - microbiome/differential-abundance measurab...

--> --- name: bio-workflows-metabolomics-pipeline description: End-to-end metabolomics workflow from raw MS data to pathway analysis. Orchestrates XCMS preprocessing, annotation, normalization, statistical analysis, and pathway mapping. Use when processing LC-MS metabolomics data. tool_type: r primary_tool: XCMS workflow: true depends_on: - metabolomics/xcms-preprocessing - metabolomics/metabolite-annotation - metabolomics/normalization-qc - metabolomics/statistical-analysis - metabolomics/pa...

--> --- name: bio-workflows-imc-pipeline description: End-to-end imaging mass cytometry workflow from raw acquisitions to spatial cell analysis. Orchestrates image preprocessing, segmentation, phenotyping, and spatial statistics. Use when analyzing imaging mass cytometry data end-to-end. tool_type: python primary_tool: steinbock workflow: true depends_on: - imaging-mass-cytometry/data-preprocessing - imaging-mass-cytometry/cell-segmentation - imaging-mass-cytometry/phenotyping - imaging-mass-...

--> --- name: bio-workflows-hic-pipeline description: End-to-end Hi-C analysis workflow from contact pairs to compartments, TADs, and loops. Covers cooler matrices, cooltools analysis, and visualization. Use when processing Hi-C data to compartments and TADs. tool_type: mixed primary_tool: cooler workflow: true depends_on: - hi-c-analysis/hic-data-io - hi-c-analysis/contact-pairs - hi-c-analysis/matrix-operations - hi-c-analysis/compartment-analysis - hi-c-analysis/tad-detection - hi-c-analys...

--> --- name: bio-workflows-gwas-pipeline description: End-to-end GWAS workflow from VCF to association results. Covers PLINK QC, population structure correction, and association testing for case-control or quantitative traits. Use when running genome-wide association studies. tool_type: mixed primary_tool: PLINK2 workflow: true depends_on: - population-genetics/plink-basics - population-genetics/population-structure - population-genetics/association-testing - population-genetics/linkage-dise...

--> --- name: bio-workflows-cytometry-pipeline description: End-to-end flow cytometry workflow from FCS files to differential analysis. Orchestrates compensation, transformation, gating/clustering, and statistical testing with CATALYST/diffcyt. Use when processing flow or mass cytometry data end-to-end. tool_type: r primary_tool: CATALYST workflow: true depends_on: - flow-cytometry/fcs-handling - flow-cytometry/compensation-transformation - flow-cytometry/gating-analysis - flow-cytometry/clus...

--> --- name: bio-workflows-crispr-screen-pipeline description: End-to-end CRISPR screen analysis from FASTQ to hit genes. Orchestrates guide counting, QC, statistical analysis with MAGeCK, and hit calling with multiple methods. Use when analyzing pooled CRISPR screens from count data to hit calling. tool_type: mixed primary_tool: MAGeCK workflow: true depends_on: - crispr-screens/screen-qc - crispr-screens/mageck-analysis - crispr-screens/hit-calling - crispr-screens/library-design - crispr-...

--> --- name: bio-workflows-biomarker-pipeline description: End-to-end biomarker discovery workflow from expression data to validated biomarker panels. Covers feature selection with Boruta/LASSO, classifier training with nested CV, and SHAP interpretation. Use when building and validating diagnostic or prognostic biomarker signatures from omics data. tool_type: python primary_tool: sklearn workflow: true depends_on: - machine-learning/biomarker-discovery - machine-learning/model-validation - ...

--> --- name: ngs-analysis description: "Next-generation sequencing data analysis pipelines including bulk RNA-seq, scRNA-seq preprocessing, variant calling, and quality control. Use when working with FASTQ files, alignment (STAR, BWA), quantification (featureCounts, Salmon), DESeq2/edgeR analysis, or building NGS pipelines. Supports GEO/SRA data retrieval." license: Proprietary ---

--> --- name: data-visualization-biomedical description: "Publication-quality visualizations for biomedical and genomics data. Use when creating volcano plots, heatmaps, UMAP plots, dot plots, survival curves, forest plots, or multi-panel figures. Includes scanpy, matplotlib, seaborn, plotly workflows with journal-ready aesthetics and proper statistical annotations." license: Proprietary ---

--> --- name: bioinformatics-singlecell description: "Advanced single-cell multi-omics analysis including scRNA-seq, scCITE-seq, scATAC-seq, and TARGET-seq. Use when analyzing single-cell data, cell type identification, trajectory analysis, differential expression, UMAP/clustering, integrating protein and RNA modalities (TotalVI), or working with Scanpy, Seurat, scvi-tools. Includes workflows for MPN, hematologic malignancies, megakaryocyte biology." license: Proprietary ---