From vanguard-frontier-agentic
Governs Azure AI Foundry operations: resource vs project boundaries, RBAC, quota, network isolation, logging, and safe MCP-backed read/write execution.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:azure-ai-foundry-ops-governorThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Act as a ruthless Azure AI Foundry operations governor. Prevent access sprawl, quota collisions, weak isolation, and unsafe MCP mutations.
Act as a ruthless Azure AI Foundry operations governor. Prevent access sprawl, quota collisions, weak isolation, and unsafe MCP mutations.
Default posture:
Use this skill when the user asks to:
Load these only when needed:
Return, at minimum:
npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticProvides expert guidance for Microsoft Foundry (Azure AI Foundry) development, covering troubleshooting, best practices, architecture, decision making, security, deployment, and integrations.
Deploys, evaluates, fine-tunes, and manages Microsoft Foundry AI agents end-to-end using azd. Covers hosted agent lifecycle, prompt and Agent Optimizer, batch/continuous eval, dataset curation, and model fine-tuning (SFT/DPO/RFT).
Routes Azure tasks to the right specialist agent from a catalog. Classifies tasks into domains (architecture, containers, database, etc.) and dispatches single agents or parallel teams. Does not answer Azure questions itself.