Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Use Evo 2 to score DNA sequences, turn genomic regions into numerical representations for classification, and generate sequences from a supplied prefix. Compare reference and variant sequences or assess coding and regulatory regions across species.
Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.
Use Boltz-2 to predict structures of complexes containing proteins, DNA, RNA, and small molecules. Obtain structure files and confidence scores to assess designed binders, with optional predictions of binding strength between a protein and a small molecule.
Predict how a small molecule may sit within a protein using structural inputs. Generate ranked 3D poses without defining a search region, then use those poses as starting points for further evaluation.
Design amino acid sequences from a protein backbone stored in a PDB file using ProteinMPNN. Generate multiple candidates, redesign selected chains while preserving specified residues, and vary sampling settings to prepare sequences for downstream structure prediction.
Design amino acid sequences from a protein backbone using SolubleMPNN, a model trained on soluble protein structures. Generate candidates with a solubility bias for redesigning aggregation-prone proteins or preparing an E. coli expression screen.
Predict patterns of gene expression and other genomic measurements from DNA sequences with Borzoi. Compare reference and altered sequences to estimate regulatory effects, generate predicted coverage tracks, and prioritize variants in regions that do not encode proteins.
Predict three-dimensional structures of complexes containing proteins, RNA, DNA, and small molecules with Chai-1. Compare candidate structures using confidence scores and clash indicators, or run repeated predictions from Python to evaluate designed binders.
Predict structures of complexes containing proteins, DNA, RNA, and ligands with OpenFold3, an AlphaFold3 reproduction with publicly available model weights. Prepare JSON inputs, generate candidate structures, and inspect confidence scores and molecular clashes.
Predict structures for single proteins or protein complexes with AlphaFold2 through ColabFold. Use confidence scores and comparisons with a designed structure to assess whether a designed sequence folds as intended.
Analyze single-cell RNA sequencing data with scVI and scANVI. Combine experimental batches while correcting technical differences, produce compact cell features for clustering, assign cell types using reference labels, and assess differences in gene expression between groups.
Design protein sequences while accounting for bound small molecules, nucleic acids, or metals. Use LigandMPNN to redesign binding pockets or metal-coordinating sites, and export sequence files alongside PDB structures with the designed sequences applied.
Find and run over 2,000 AI models and API tools through one MCP connection, a shared interface for agents. Inspect inputs and pricing before generating media, searching the web, or retrieving structured and social data.
Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.
Model queues, production lines, logistics, and other systems that share limited resources in Python. Use discrete-event simulation, which advances through individual events, to measure waiting times, resource use, and throughput when comparing staffing or equipment levels.
Build Python machine learning workflows for classification, numerical prediction, and grouping similar records. Use scikit-learn guidance and examples to prepare data, compare algorithms, tune model settings, and evaluate results with repeatable processing steps.
Create statistical charts from tabular data to explore distributions, relationships, and group differences. This skill guides plot selection, multi-panel layouts, and styling, including box plots, heatmaps, and charts with estimates and uncertainty bands.
Analyze relationships between people, objects, or papers as networks in Python. Use NetworkX to find shortest paths, identify important nodes and communities, visualize connections, exchange graph data, and generate sample networks for testing.
Forecast sales, sensor readings, or other time series without training a custom model. Using Google's TimesFM, this skill produces forecasts and uncertainty ranges from CSV files or arrays, supports batch processing, and checks local computing resources before use.
Explore design options in Python when goals such as cost and performance compete. This skill guides optimization, constraint handling, and visualization of trade-offs, then helps compare candidate solutions using stated preferences.
Process astronomical data in Python with Astropy. This skill covers celestial coordinate, unit, and time conversions; reading and editing FITS astronomy files; matching object catalogs; and calculating cosmic distances using cosmological models.
Write MATLAB or GNU Octave scripts for matrix calculations, data analysis, signal processing, and scientific plots. The skill also helps explain syntax and functions, convert code between MATLAB and Python, and run scripts when an interpreter is installed.
Choose statistical tests for research data, check their assumptions, and interpret effect sizes, which describe the magnitude of differences or relationships. This skill also supports sample size planning and produces results in APA reporting style, with figures and tables.
Inspect scientific data files to understand their format, structure, and quality. Covering over 200 formats, this skill produces Markdown reports with statistical summaries, potential issues, and recommendations for preprocessing, visualization, and further analysis.