Poorly designed tool schemas cause agents to hallucinate, fail silently, or waste tokens. This skill teaches proven patterns for clear, unambiguous function-calling interfaces that work reliably.

Deploy custom AI agents as containerized services in Azure AI Foundry without managing infrastructure. Use the Azure AI Projects SDK to define, deploy, and manage hosted agents with your own Docker images and integrated tools.

Multi-agent workflows often suffer from coordination bottlenecks and unmanaged costs. This skill provides profiling, orchestration strategies, and cost controls to maximize efficiency.

This skill enables Claude to manage multiple local CLI agents running in parallel tmux sessions, providing start/stop/monitor capabilities and cron-friendly scheduling for automated workflows.

This skill automates Render cloud platform operations including service management, deployment triggering, and status monitoring through the Rube MCP integration.

Testing LLM models as AI agents requires consistent, measurable evaluation. PinchBench provides 23 diverse tasks spanning calendar management, email handling, research, coding, and multi-step workflows with automated grading and public leaderboard submission.

Develop multiple features in parallel without git branch switching. This skill creates clean, isolated worktrees with automatic project setup and test baseline verification.

Building with serverless databases requires understanding connection methods, scaling behavior, and platform-specific features. This skill provides comprehensive guidance for working with Neon Serverless Postgres across all development scenarios.

Simplify AI model development and deployment on Huawei Cloud ModelArts. This skill provides unified resource management for training jobs, models, inference services, and notebooks with built-in security features.

Create text, images, video, speech, and music using the MiniMax AI platform directly from your terminal. Avoid complex API integration by using simple command-line commands for all your AI generation needs.

Manual web testing and repetitive browser tasks consume significant development time. This skill automates browser interactions through Playwright CLI for efficient testing, screenshots, form filling, and data extraction.

Before deploying to Azure, developers need confidence their infrastructure code and configuration are valid. This skill performs comprehensive pre-deployment validation including Bicep compilation, Terraform validation, Azure CLI checks, and policy compliance verification.

This official Microsoft skill provides comprehensive guidance for Azure Storage services including Blob, Files, Queue, Tables, and Data Lake. It offers MCP tools integration and CLI commands to help developers manage cloud storage resources efficiently.

Understand complex Azure infrastructure by generating detailed Mermaid diagrams that map resource relationships, dependencies, and configurations across your entire resource group.

Prevent deployment failures by checking Azure quota availability before provisioning resources. Get accurate capacity information across regions using Azure CLI quota commands.

Provision and configure Azure Kubernetes Service clusters with best-practice settings for networking, security, and operations. Simplifies complex AKS decisions with expert guidance.

Developers struggle to build and host AI-powered apps with GitHub Copilot SDK. This skill scaffolds projects, integrates Copilot SDK into existing codebases, configures Azure models, and deploys to Azure Container Apps.

Cloud architects struggle to design compliant Azure topologies with proper networking, security, and disaster recovery. This skill generates WAF-aligned infrastructure plans and IaC (Bicep or Terraform) from workload descriptions.

This skill helps developers diagnose and troubleshoot production issues in Azure by providing structured debugging workflows, diagnostic commands, and KQL queries for Container Apps.

This skill automates Azure deployments using azd, Bicep, or Terraform. It ensures deployments only proceed after proper validation, reducing failed deployments and cloud costs.