Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Plan DNA variant detection workflows by identifying the assay and sample model, then routing to germline, cancer somatic, or molecular-barcode panel skills. It also supports focused local BAM/CRAM checks with variant files, depth summaries, and optional filters.
Plan or run targeted DNA panel analysis using UMIs, barcodes that identify DNA molecules. Organize consensus reads, coverage checks, and low-frequency variant results with molecular support, filtering reasons, and explicit quality limitations.
Analyze marker-gene sequencing data to study microbial communities. Supports FASTQ quality checks and, with primers, metadata, and taxonomy resources, workflows that produce sequence variant tables, taxonomic assignments, diversity measurements, and plots.
Plan or run DNA analysis to find small genetic changes in tumors, using tumor samples alone or paired with normal tissue. Check sample pairing, contamination, data quality, filtering, and annotations that add information to detected variants.
Plan or run bulk RNA-seq analysis to find genes whose expression differs between conditions. Check sample replication, study design, batch effects, and data quality, then produce comparison tables, diagnostic plots, and ranked gene lists.
Guide the use of NVIDIA cuOpt for route planning and mathematical optimization, choosing values to minimize cost or maximize profit under constraints. Covers requirements, environment checks, installation guidance, and verification of solver results.
Plan or run ATAC-seq analysis to identify accessible DNA regions. Check sequencing quality, align reads, detect peaks, combine evidence across replicate samples, and prepare comparisons between conditions with quality summaries and visualization tracks.
Start shotgun metagenomics workflows for mixed-community DNA reads in FASTQ files. Check read quality, remove host sequences, and profile organisms and biological functions using supported tools and databases, producing tables and visual summaries when results are available.
Plan or run inherited DNA variant detection from whole-genome, exome, or targeted-panel sequencing. Check reference compatibility, sample quality, and combined analysis across samples, with documented commands, resource versions, and paths to variant and annotation outputs.
Prepare a Python environment for Mixpanel analysis by installing required libraries and checking credentials and connectivity. Use it for first-time setup, missing dependencies, or guidance on service account and OAuth sign-in options.
Validate Illumina BCL run folders and sample sheets, plan demultiplexing—the separation of reads by sample—and convert data to FASTQ using installed tools. Review conversion metrics, index settings, and reads that could not be assigned.
Plan or run bulk RNA-seq processing from sequencing reads to count matrices, tables of expression counts across samples. Check sample metadata, reference consistency, read mapping, and quantification quality, and produce summaries for downstream analysis.
Routes bulk RNA-seq requests to workflows for generating expression counts and checking quality, or comparing gene expression between groups. Checks input data, sample information, and analysis requirements before directing the next step.
Validate FASTQ sequencing files, run local quality checks, and interpret reports to decide whether trimming is needed. Optionally remove adapters or low-quality read ends while preserving original reads and their quality reports.
Plan or run quality checks and peak calling, which identifies enriched genomic regions, for ChIP-seq, CUT&RUN, and CUT&Tag. The workflow accounts for controls and replicates and prepares signal tracks, quality reports, and differential binding designs.
Prepare single-cell or single-nucleus RNA-seq analysis by checking inputs and selecting workflows that turn FASTQ sequencing files into count matrices. Route quality checks, cell annotation, clustering, and UMAP visualization to the embedded downstream skill.
Find the right workflow for next-generation sequencing data by inspecting files and clarifying only missing setup details. Receive a recommended analysis skill, checks of available tools, and plans for software installation and reference data.
Analyze Mixpanel data with Python to explore usage trends, conversion steps, returning users, and differences between user groups. Also manage business context documents that explain an organization's structure and goals to AI assistants.
Prioritizes candidate genes from GWAS, studies linking genetic variants to traits. Combines locus predictions, gene expression evidence, and rare variant support into ranked results with source attribution, confidence labels, reproducible files, and optional figures.
Retrieve concise FinnGen association results for one genetic variant. Accepts rsID identifiers or GRCh37/GRCh38 genome coordinates, resolves the query format, and reports association counts, truncation, and optional raw output files.
Query gnomAD for variant frequencies, gene constraint measures, and effects on gene transcripts. Get concise Markdown summaries from focused requests, with options to return machine-readable JSON or save the full response to a file.
Retrieve GTEx associations between a genetic variant and gene expression in individual tissues. Supply one rsID or genome coordinate, and receive JSON with the resolved variant, association rows, counts, and warnings.
Create, edit, or validate Jupyter notebooks for SQL and Python analysis. Organize data sources, assumptions, calculations, and findings into a readable document that others can review and rerun, with execution gaps clearly identified.
Choose, build, and review charts that answer a clear analytical question. The skill checks chart types, labels, units, colors, and data sufficiency, then refines the visual in its intended report, dashboard, notebook, or other output.