MCP App StoreMCP App Store
from fine-tuning56
Complete lifecycle management for model fine-tuning on Azure AI Foundry, from dataset creation to deployment.
This skill transforms an agent into a specialist for fine-tuning models within the Azure AI Foundry ecosystem. It provides a comprehensive framework for the entire machine learning pipeline, ensuring that model tuning is data-driven and scientifically validated.
Use this skill when a user needs to improve a model's performance on a specific task, distill knowledge from a larger teacher model to a smaller student, or implement reinforcement learning from human feedback (RLHF) via SFT, DPO, or RFT.
auto_finetune.py, auto_rft.py), dataset generation, validation (validate_sft.py), and model evaluation.Designed for high-capability agents with Python execution environments and Azure CLI access, such as those integrated with Azure AI Foundry or professional developer harnesses.
This skill has not been reviewed by our automated audit pipeline yet.
Azure External Attack Surface Management
Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform
Microsoft Foundry Classic — Expert Guidance
Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.
Azure Impact Reporting — Integration & Troubleshooting
Guidance for configuring, troubleshooting, and integrating Azure Impact Reporting with Monitor, Logic Apps, Service Health and HPC guest health APIs.
Azure Blob Storage
Expert knowledge for Azure Blob Storage development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, int
MLX Engineering Helper
Tools and workflow for auditing, porting, and debugging Apple's MLX / MLX-LM code and runtime behavior on Apple silicon.
Azure Arc Expertise
Expert guidance and runbooks for Azure Arc: troubleshooting, security, configuration, integrations, and deployments for Arc-enabled Kubernetes, servers, SQL MI,
Azure Identity SDK (TypeScript) v2
Authenticate to Azure services from TypeScript using DefaultAzureCredential, Managed Identity, service principals, and credential chains with provenance-preserv
Azure Event Hubs (Rust) — Workflow
Run and review Azure Event Hubs workflows in Rust: send/receive events, batch sends, partitioned consumption and checkpointing with preserved provenance.