FVossebeld/agent-skills-for-context-engineering

context-engineering-collection

A Microsoft-native adaptation of context engineering skills for production agent systems. Use when building, optimizing, evaluating, governing, publishing, or debugging agent systems with core context-engineering mechanisms plus Azure AI and Microsoft Foundry…

原文语言：英语

agent-publishing

This skill should be used when publishing Microsoft-native agents: Foundry agent versions, stable endpoints, Teams and Microsoft 365 Copilot distribution, Entra Agent Registry, environment promotion, rollout, and rollback.

原文语言：英语

azure-agentic-retrieval

This skill should be used when implementing private grounded retrieval on Azure: Azure AI Search, agentic retrieval, knowledge sources, File Search, SharePoint grounding, citations, access-controlled indexes, and retrieval traces.

原文语言：英语

azure-identity-for-agents

This skill should be used when binding agent access to Microsoft Entra identity: managed identities, RBAC scopes, on-behalf-of access, tenant boundaries, credential-free SDK use, and per-user authorization for tools and grounding sources.

原文语言：英语

azure-memory-state

This skill should be used when implementing Microsoft-native agent memory and state: Cosmos DB, Blob or ADLS scratchpads, Azure Cache for Redis, session stores, episodic memory, entity state, vector memory, and append-only logs.

原文语言：英语

fabric-data-agent

This skill should be used when grounding agents in Microsoft Fabric: Fabric Data Agent, semantic models, lakehouses, warehouses, Power BI aligned metrics, governed analytical data, and natural-language data access.

原文语言：英语

foundry-hosted-agents

This skill should be used when designing Microsoft Foundry Hosted Agents and managed agent runtimes: production endpoints, runtime boundaries, sandboxing, scaling, tool execution, runtime state, deployment environments, and operational controls.

原文语言：英语

foundry-iq-knowledge-layer

This skill should be used when designing Microsoft Foundry IQ knowledge bases, reusable enterprise grounding, federated knowledge APIs, permission-aware retrieval, knowledge source governance, and shared context layers for agents.

原文语言：英语

foundry-tool-governance

This skill should be used when designing Microsoft Foundry tool surfaces: Foundry Toolbox, tool catalog configuration, MCP servers, Azure Functions, OpenAPI tools, API Management AI Gateway policy, tool versioning, and allowed-tool scoping.

原文语言：英语

responsible-ai-guardrails

This skill should be used when applying Microsoft Responsible AI controls to agents: content filters, Prompt Shields, groundedness checks, task adherence, protected material handling, red teaming, monitoring, and safety evaluation.

原文语言：英语