Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Reviews machine learning preprocessing, features, and data splits for data leakage: information unavailable when making a real prediction. Identifies risky statistics, future data, and validation setups, then suggests corrections using only appropriate training information.
Create interactive charts in Python for exploring scientific, statistical, geographic, and financial data. Choose quick plotting or detailed customization, add hover details and zoom controls, and export results as interactive HTML or static images.
Write MATLAB or GNU Octave scripts for matrix calculations, statistics, signal processing, and scientific plots. Get help with language syntax, import and export data, or convert code between MATLAB and Python for numerical analysis tasks.
Build and train reinforcement learning agents, which learn actions through rewards. The skill guides custom environment creation, parallel simulation tuning, integration with existing environments, and policy development for image or sequential observations.
Apply NOWAIT to shorten reasoning model outputs by suppressing reflection words during generation. Includes integration examples for HuggingFace Transformers and vLLM, with guidance on model suitability and potential accuracy loss in distilled models.
Supports pathology image analysis in Python, from loading whole-slide images to normalizing stain colors, identifying cell nuclei, mapping spatial relationships, and training machine learning models. It also covers multiplex imaging and marker measurements.
Analyze relationships between people, objects, or places using Python networks. Build connection diagrams, find shortest paths, identify important nodes and closely connected groups, visualize network structure, and save the resulting data and measurements.
Design and automate machine learning workflows from data preparation through training, validation, deployment, and monitoring. Provides guidance and templates for reproducible experiments, quality checks, gradual model rollouts, and restoring a previous model when problems occur.
Create scientific and statistical charts in Python, including line plots, scatter plots, heatmaps, and multi-panel figures. Adjust colors, labels, and layouts, then export figures as PNG, PDF, or SVG for papers and presentations.
Work with microscopy images stored in OMERO through its Python API. Retrieve datasets, analyze pixel values and selected image regions, manage annotations and metadata, and save measurements or automate processing across multiple images.
Process physiological recordings in Python, including heart, brain, breathing, and muscle signals. Supports signal cleaning, heart rate variability measurements, stimulus response analysis, and combined analysis of multiple signal types.
Build and check statistical models in PyMC while quantifying uncertainty. Supports hierarchical models that represent grouped data, sampling diagnostics, predictive checks, and model comparison, with templates and scripts for predictions and diagnostic reports.
Calculate defined business, statistical, or quality metrics from available data and test results. It provides formulas and reproducible calculation steps, with checks on units, denominators, and which records are included in each calculation.
Process and compare mass spectra, measurements used to study chemical compounds, with matchms. Clean peak data, standardize metadata, calculate similarity scores, and search reference libraries for candidate compounds in metabolomics research.
Estimate intervention effects from existing data using causal analysis methods. Set up models, compare observed outcomes with estimates of what would have happened without intervention, check robustness, and interpret fitted results.
Design and implement repeatable workflows that clean, encode, transform, and validate raw data for machine learning. Get a preprocessing plan or implementation outline, with clear steps and guidance on where further checks are needed.
Use pymoo in Python to optimize competing goals such as cost and performance under constraints. Find and visualize trade-off solutions, compare algorithms, and select candidates according to preferred priorities.
Prepare pathology image datasets by detecting tissue in whole slide images and extracting smaller image tiles. Use random, grid, or score-based selection, preview extraction locations, and apply preprocessing filters to review and prepare the resulting tiles.
Develop and review machine learning approaches through at least three rounds of critique and refinement. Compare models with simple reference predictions, question data assumptions, and investigate overfitting, feature choices, and evaluation methods before accepting a solution.
Develop workflows for satellite imagery and geographic data, using guidance and code examples to calculate vegetation indicators, classify land cover, analyze terrain, and find road routes. Covers GIS, software for working with location-based information, and spatial machine learning.
Find and download public cancer imaging datasets from NCI Imaging Data Commons. Filter scans and pathology images by metadata, preview them in a browser, check licenses, and generate source citations for research or AI training.
Analyze genomic regions with gtars using Python or command-line tools. Find overlaps, generate coverage tracks showing read density, prepare regions as tokens for machine learning, and split single-cell fragment data for further analysis.
Work through optimization problems using gradients, which indicate how a function changes. The skill guides method selection, step size choices, and convergence checks, with SciPy examples for conjugate gradient and BFGS methods.
Search NCBI GEO for gene expression studies, retrieve experiment details and expression tables, and prepare public datasets for analysis. Includes workflows for data quality checks, comparisons between sample groups, and expression summaries across studies.