Loading...
Loading...
Found 8 Skills
Industry-standard gradient boosting libraries for tabular data and structured datasets. XGBoost and LightGBM excel at classification and regression tasks on tables, CSVs, and databases. Use when working with tabular machine learning, gradient boosting trees, Kaggle competitions, feature importance analysis, hyperparameter tuning, or when you need state-of-the-art performance on structured data.
Compare two CSV files and generate a unified diff file showing line-by-line differences.
Search input component in Observable Framework — filter tabular data.
Build a production-ready multilabel classifier on tabular data using XGBoost wrapped in MultiOutputClassifier. Use when each row can have multiple labels simultaneously (tags, attributes, gene functions, content moderation categories, multi-disease detection). Covers hamming loss, per-label metrics, label co-occurrence, MultiOutputClassifier vs ClassifierChain, and per-label SHAP. Default to this for any tabular multilabel problem.
Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.
Implements and customize Syncfusion .NET MAUI DataGrid (SfDataGrid) for displaying tabular data. Use when working with MAUI data grids, SfDataGrid, tabular data display, data binding to grids, or column configuration. Covers editing cells, sorting, filtering, grouping, paging, exporting to Excel/PDF, row operations, selection, and summaries.
DeepKnow Knowledge and Search Assistant — manage and import knowledge, search by knowledge base or folder and read source material in depth, conduct comprehensive searches for professional sources and WeChat Official Account articles, and query actual data from FoodPartner, approved websites, and tables.
Turn a data file (CSV/TSV/TXT/XLSX/XLS/JSON) into standalone interactive ECharts HTML charts - 32 chart types, 3 themes, fully offline with no CDN. A data profile (--profile) lets the agent read the data itself and decide what to plot; each chart ships with an embedded fact sheet (plot_stats plus data_preview). This skill produces charts and facts, not written reports or narrative documents. TRIGGER: user supplies or points to a tabular data file and wants a chart; asks to generate a chart/make a graph/visualize data.