Skill UI

Automates creation of A/B test configurations for ML deployment, guiding users through best practices, code samples, and validation steps so production models are served with monitoring and rollout control.

Specializes in the expert deployment and orchestration of production-grade multi-agent systems using Google's Agent Development Kit (ADK). This skill manages the complex lifecycle, including AgentCard discovery, A2A protocol communication, state management via Memory Bank, and secure execution within the Code Execution Sandbox. Ideal for setting up robust, enterprise-level AI workflows on the Vertex AI Agent Engine, especially during CI/CD pipelines.

This skill provides a comprehensive guide to designing and developing autonomous AI agents for code plugins. It covers the required file structure (YAML frontmatter), best practices for defining agent roles, designing robust system prompts, and setting up clear triggering conditions. Use this when you need to conceptualize, structure, or refine an agent's capabilities to handle complex, multi-step tasks autonomously.

A comprehensive framework for rigorously testing and benchmarking LLM agents. It moves beyond simple pass/fail checks to assess complex behaviors, reliability metrics, and capability consistency across multiple runs. Ideal for production monitoring and identifying subtle failure modes in advanced AI agents.

This comprehensive guide details the architecture of memory for intelligent agents. It covers the distinction between short-term context, long-term vector storage, and advanced cognitive models (CoALA framework: semantic, episodic, procedural). Learn how to implement robust memory retrieval mechanisms, select appropriate vector databases (Pinecone, Qdrant, etc.), and utilize embedding models to build truly context-aware, persistent AI applications.

A systematic workflow designed to significantly improve the reliability and performance of existing AI agents. It covers detailed performance analysis, including gathering metrics (e.g., task success rate, latency), classifying failure modes, and advanced prompt engineering techniques (like Chain-of-Thought and Constitutional AI). The process culminates in structured A/B testing and controlled deployment, ensuring measurable, robust improvements.

AudioCraft is Meta’s PyTorch toolkit for text-to-music and text-to-sound creation via MusicGen, AudioGen and EnCodec, making it ideal for prototyping music apps, effects, and controllable stereo pieces.

AudioCraft is Meta’s PyTorch toolkit for text-to-music and text-to-sound creation via MusicGen, AudioGen and EnCodec, making it ideal for prototyping music apps, effects, and controllable stereo pieces.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

A comprehensive platform designed for building, deploying, and managing continuous, autonomous AI agents. Users can create complex, multi-step automation workflows using a visual, drag-and-drop node editor, or extend functionality using a dedicated developer toolkit. Ideal for implementing persistent agents triggered by webhooks, schedules, or manual input, enabling sophisticated, end-to-end AI automation pipelines.

A comprehensive platform designed for building, deploying, and managing continuous, autonomous AI agents. Users can create complex, multi-step automation workflows using a visual, drag-and-drop node editor, or extend functionality using a dedicated developer toolkit. Ideal for implementing persistent agents triggered by webhooks, schedules, or manual input, enabling sophisticated, end-to-end AI automation pipelines.