Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Work with geographic points, lines, and areas in Python. Read spatial files, combine datasets by location, calculate areas and distances, transform coordinate systems, and export results as maps or converted files.
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.
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.
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.
Use LaminDB to organize biological datasets, search their metadata, and track how analyses produce results. Standardize annotations with biological vocabularies, validate data structures, and record versions and computational history for reproducible research.
Check CPU cores, GPUs, available memory, and disk space before demanding computing tasks. Save a JSON report with recommendations for parallel workers, GPU use, and processing data in chunks when memory is limited.
Retrieves aggregated hedge fund time series from the public OFR API for research on industry size, leverage, counterparty concentration, and liquidity. It supports finding datasets, comparing series, and downloading data without an API key.
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.
Build and deploy biological data analysis pipelines on Latch using Python, Nextflow, or Snakemake. The skill also guides cloud file management, sample tracking, and CPU, memory, and GPU settings for individual processing tasks.
Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.
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.
Choose embedding models, which turn text into numerical representations of meaning, for semantic search and AI answers grounded in retrieved documents. Includes examples for document splitting, preprocessing, multilingual content, and measuring retrieval quality.
Build automated data checks with Great Expectations and dbt to detect missing values, duplicates, invalid ranges, and stale records. Define data contracts, shared agreements on data structure and quality, and summarize validation results across tables.
Analyze time series, observations ordered over time, using aeon in Python. Build classification, prediction, and clustering workflows, detect unusual patterns or changes, and compare methods through an interface compatible with scikit-learn.
Process datasets that exceed available memory and run Python computations across multiple cores or machines. The skill guides large table and array operations, multi-file cleaning and aggregation, custom task dependencies, and execution settings for parallel workflows.
Work with DNA, RNA, and protein sequences in Python. Read and convert biological files, compare sequences, search for similar sequences with BLAST, retrieve NCBI records, analyze protein structures, and build or visualize evolutionary trees.
Build interactive charts, networks, timelines, and maps with D3.js, Chart.js, or custom SVG graphics. The skill guides data preparation, scale selection, accessible colors, and storytelling so viewers can explore patterns without misleading visual proportions.
Investigate unusual transactions, sensor spikes, rare failures, and other suspicious records. The skill helps compare anomaly detection methods and thresholds, prepare records for human review, and plan checks for false alarms and missed anomalies.
Retrieve population, economic, health, and environmental statistics through the Data Commons Python API. Resolve place names into query identifiers, compare regions, explore historical trends, and convert results into Pandas tables for further analysis.
Turn analytical findings into reports and presentations that explain what the numbers mean and what to do next. Structure the narrative, choose clear visual comparisons, highlight key findings, and communicate uncertainty to audiences without technical expertise.
Learn how to organize the instructions, conversation history, documents, and tool results an AI agent receives. Explains context limits and loading information as needed, helping you review agent designs and investigate behavior caused by poorly managed context.
Helps process astronomical data in Python by converting coordinates, units, and time scales, working with FITS observation files, matching object catalogs, and calculating distances using cosmological models.
Create charts from existing CSV files, tables, or query results to show trends, distributions, comparisons, and relationships. The skill guides chart selection and axis choices for everyday analysis, presentation slides, and simple dashboards.