3. Data, Science & AI

Generates configuration files for TorchServe, an ML model serving framework, to streamline deployment processes for machine learning models.

Automates optimization of Spark SQL query execution to enhance data pipeline performance and efficiency.

Routes cryptocurrency trades across multiple decentralized exchanges to find optimal prices, minimize slippage and gas costs, and assess MEV risk.

Detects and highlights unusual data points in datasets using machine learning algorithms for anomaly and outlier analysis.

Analyzes images using object detection, classification, and segmentation techniques for visual data processing.

Configures Triton Inference Server settings for deploying machine learning models, enabling efficient model serving in production environments.

Performs feature engineering tasks including creation, selection, and transformation to enhance machine learning model performance.

Automates creation of Change Data Capture (CDC) pipeline operations within data pipelines. Triggered by 'cdc pipeline creator' phrases.

Analyzes date ranges in datasets to detect trends and patterns for data-driven insights.

Monitors and detects performance drift in machine learning models during deployment to maintain accuracy.

Executes FireCrawl's primary workflow for core web data extraction, enabling main feature implementation in data-driven applications.

Splits datasets into training, validation, and testing sets for machine learning model development and evaluation.

Automates compression optimization in data pipelines to enhance efficiency and reduce storage costs.

Generates customizable report templates for data analytics workflows. Auto-activates on triggers like 'report template generator'.

Auto-activating skill for generating Apache Spark jobs within data pipeline workflows.

Automates machine learning model deployment to Google Cloud Vertex AI, enabling seamless production rollout of AI solutions.

Automates ML model deployment to production, implementing best practices for serving, performance, and error handling.

Executes Perplexity's primary workflow for core research and information gathering tasks, enabling efficient AI-driven data retrieval and analysis.

Provides computer vision capabilities for object detection, image classification, and segmentation.

Executes clustering algorithms (K-means, DBSCAN, hierarchical) to identify natural groupings and patterns in datasets.

Automates gradient clipping during machine learning model training to prevent exploding gradients and stabilize training.

Automates deployment of machine learning models to Amazon SageMaker endpoints, enabling seamless production rollout of AI services.

Configures dashboard layout operations for data analytics, enabling efficient arrangement of visual elements in analytical interfaces.

Automates deployment of machine learning models and services on Vertex AI platform.