3. Data, Science & AI

Installs and configures authentication for the Lindy AI SDK/CLI, enabling integration with Lindy AI services.

Manages machine learning model versioning for deployment, enabling tracking and deployment of model iterations.

Automatically tracks and alerts on machine learning model predictions during deployment for real-time performance insights.

Configures AI model selection in Cursor editor. Triggers on phrases like 'cursor model' or 'cursor claude'.

Automates TensorBoard visualization operations for machine learning model training and monitoring.

Automates setup of monitoring for data pipelines, enabling real-time tracking and alerting of data processing workflows.

Automates database schema comparison and synchronization, providing diff and guidance for seamless database versioning and deployment.

Automatically generates BigQuery views for data virtualization and efficient querying within Google Cloud Platform.

Auto-generates customizable report templates for data analytics, enabling consistent data visualization and presentation.

Auto-activating helper that streamlines machine learning model export for seamless deployment into production environments.

Forecasts future values from historical time series data by identifying trends, seasonality, and patterns for predictive insights.

Auto-generates dbt models to streamline data pipeline development and transformation in warehouse environments.

Automates construction of scikit-learn pipelines for machine learning training, including data preprocessing and model integration.

Executes and compares AI models across multiple providers via OpenRouter, enabling provider-agnostic system development and model evaluation.

Automates creation of Optuna studies for machine learning hyperparameter optimization, streamlining model training workflows.

Automates dataset loader creation for machine learning training, streamlining data preparation workflows.

Creates and configures Windsurf Cascade agents for domain-specific AI tasks, enabling tailored agent behavior.

Enables function/tool calling with OpenRouter models for building AI agents and structured outputs, triggered by specific phrases.

Builds production Genkit applications with RAG systems, multi-step flows, and tool calling for Node.js, Python, and Go, deploying to Firebase or Cloud Run.

Intelligently routes AI model requests to optimize cost, speed, or quality based on request characteristics.

Provides a minimal code example for Perplexity API integration, ideal for initial setup and learning basic API patterns.

Tracks data lineage across pipelines, providing visibility into data flow and transformations for data engineering and management.

Automates machine learning model training including dataset analysis, model selection, parameter configuration, and performance metric generation with scikit-learn.

Constructs and configures neural network architectures using the neural-network-builder plugin for AI model development.