This skill runs and reads evaluations for Google ADK (Agent Development Kit) agents, through the agents-cli eval commands. It walks a loop of preparing a dataset, running the eval, studying failures, and fixing the agent, then repeating. It also helps pick metrics, including LLM-as-judge scoring, and lists usual reasons a score drops.
Build agents with the Mastra frameworkThis skill guides building with Mastra, a TypeScript framework for building agents and workflows with tools, memory, and storage. It tells the agent to check current docs and APIs rather than rely on memory, and it helps with setup, frequent errors, version migrations, and the mastra api CLI.ai agent frameworkAgentsTypeScript
Google Agents CLI ScaffoldScaffolds, enhances, and upgrades Google ADK agent projects through agents-cli.ai agent frameworkAgentsInfra
Prioritization FrameworksApplies PM prioritization frameworks (RICE, MoSCoW, etc.) to rank opportunities and roadmap items.ai agent framework
Security best practices (OpenAI)Performs language/framework-specific security best-practice reviews when explicitly requested.ai agent framework
Azure AI GatewayConfigures Azure API Management as an AI gateway for models, MCP tools, and agents.Agent platformInfraAgents
Entra Agent IDProvisions Microsoft Entra Agent Identity blueprints and identities for individual agent instances.Agent platformSecurityAgents
