Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Clean and compare tandem mass spectra, measurements used to study molecular fragments, with matchms. Standardize metadata, filter peaks, search reference libraries, and export ranked candidate matches with similarity scores and matched-peak counts.
Helps organize biological datasets and models in LaminDB. Covers data registration, table validation, annotation with standardized biological terms, metadata searches, and tracking analysis inputs and outputs so researchers can preserve the context needed to repeat their work.
Work with geographic points, lines, and areas in Python using GeoPandas. Guidance and local audit tools help check coordinate systems, geometry validity, spatial join matches, and export settings before trusting or sharing analysis results.
Build, analyze, and visualize relationship data in Python with NetworkX. Find shortest routes, identify important nodes and groups, generate networks for simulations, and exchange graph data through tables and common file formats.
Convert single-plane, single-channel two-photon TIFF images and timestamped behavioral position CSV files into NWB, a neuroscience data format. Preserve metadata, check clock alignment against acquisition evidence, and report format validation findings and source-to-output comparisons.
Measure fluid velocity from pairs of particle images with OpenPIV. The skill covers image preparation, velocity calculation, correction of unreliable vectors, plotting, and calculation of vorticity and strain rate to examine flow patterns.
Match scientific labels to ontology identifiers, standardized IDs for concepts such as tissues, cell types, and diseases. Checks existing IDs, labels, obsolete terms, and prefixes to support metadata annotation, submission preparation, and table audits.
Prepare small image tiles from whole-slide histology scans with Histolab. Inspect tissue regions, choose random, grid, or score-based extraction, standardize H&E staining, and organize tile datasets with patient-level splits and visual checks.
Process satellite imagery and map data for geospatial research. Helps align coordinate systems and image grids, calculate vegetation and terrain measures, summarize data by area, and analyze road networks while preserving masks and source information.
Helps build and review NeuroKit2 research workflows for physiological recordings such as ECG, respiration, and skin conductance. Covers preprocessing, time alignment, event analysis, heart rate variability, and complexity measures, while recording methods and checking data quality.
Analyze Neuropixels neural recordings with SpikeInterface, from loading and preprocessing to motion correction and spike sorting, which separates signals by neuron. Calculate quality metrics, review candidate units, and export plots and data for further inspection.
Analyze pooled CRISPR screens from FASTQ reads or guide-count tables using MAGeCK. Validate inputs, assess library and replicate quality, and rank enriched or depleted genes with effect sizes and false discovery rates, which estimate false-positive proportions.
Create scientific charts in Python with detailed control over axes, colors, labels, legends, and layout. Arrange multiple plots in one figure and export PNG, PDF, or SVG files for papers and presentations.
Prepare and analyze genomic intervals, regions defined by chromosome coordinates, with Gtars. Validate BED files, compare overlaps and coverage, combine region sets, and plan tokenization or reference storage while tracking data provenance and resource limits.
Turn small-molecule structures into numerical features for similarity searches and models that predict activity or properties. Using Molfeat, the skill covers representation choices, invalid inputs, alignment with experimental labels, and saving feature-generation settings for reuse.
Inspect FCS files from flow cytometry, a method for measuring cell properties, using FlowIO. Extract measurement data into NumPy arrays, review channel metadata, export tables, and create FCS 3.1 files for downstream work.
Use Dask to process tables, numerical arrays, and file collections in pieces across CPU cores or machines. Helps choose data structures, size memory-friendly chunks, coordinate dependent tasks, and diagnose slow or memory-heavy workflows.
Inspect supported local scientific files before modeling, summarize structure and missing values, and flag possible data leakage or outlier effects. Produces bounded aggregate reports with identifiers obscured and provides a structured analysis report template.
Retrieve and combine protein annotations, biological pathways, and chemical identifiers from services such as UniProt, KEGG, and UniChem using Python. Supports cross-database lookups and batch identifier conversion while preserving multiple matches and failed requests.
Analyze flow cytometry data in Python by correcting fluorescence spillover and applying gates that select cell populations. Produce population counts, percentages, and fluorescence summaries, or reproduce supported FlowJo 10 workspace analyses with recorded analysis settings.
Prepare bulk RNA-seq sequencing files or quantification outputs for gene-level comparisons. Check sample information and data quality, configure processing workflows, and assemble validated count tables and metadata for downstream differential expression analysis with PyDESeq2.
Use hosted DNA models to predict gene structures, expression levels, and regions that regulate gene activity. Start from a gene symbol, genomic coordinates, or a DNA sequence, without installing model weights or running a local GPU.
Implement and debug astronomical data analysis with Astropy in Python. Work with physical units, celestial coordinates, observation files, tables, precise time conversions, and cosmological models to prepare data and calculate astronomical quantities.
Organize repeated experiments to improve models, prompts, or agent systems against measurable goals. The skill records hypotheses and lessons in a persistent tree, isolates trials, and compares promising candidates using evaluation data kept separate from development.