Explorar skills

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create vi

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create vi

Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Deep expertise in Logseq's Datascript database schema. Auto-invokes when users ask about Logseq DB schema, Datascript attributes, built-in classes, property types, entity relationships, schema validation, or the node/block/page data model. Provides authoritative knowledge of the DB graph architecture.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Gestiona el desarrollo de proyectos Chronicle utilizando hitos rastreados en base de datos, próximos pasos y visualización de la hoja de ruta. Funciona con herramientas MCP o comandos CLI, eliminando las actualizaciones manuales de DEVELOPMENT_HISTORY.md.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Busca y recupera contexto de sesiones de desarrollo pasadas utilizando datos de Chronicle, funcionando con MCP (rápido, estructurado) o comandos CLI (portátil). Úselo para recordar trabajos previos, comprender el historial del código o evitar repetir enfoques anteriores.

Orchestrate Google Colab Pro/Pro+ GPU instances as remote training backends via SSH. Compounds /agent-browser (to launch Colab sessions and install colab-ssh) with SSH (to operate the runtime remotely). Use when: (1) launching a Colab notebook for GPU training, (2) running training jobs on Colab from the local terminal, (3) transferring datasets/checkpoints to/from Colab, (4) monitoring GPU utiliz

Esta habilidad ayuda a los usuarios a extraer listados de productos estructurados de Amazon, como títulos, ASINs, precios, calificaciones y especificaciones, siendo útil para la búsqueda de productos, el seguimiento de precios, la comparación y la investigación de mercado.

Diseñe, audite y mejore sistemas de seguimiento de análisis para producir datos fiables y listos para decisiones. Esta habilidad ayuda a configurar, corregir o evaluar el seguimiento de análisis (GA4, GTM, etc.), centrándose en la estrategia de medición, calidad de la señal y validación.