帮助你端到端部署、评估、微调并持续优化 Microsoft Foundry 智能体与模型。
该技能材料显示其本体为提示词/工作流文档,系统检查项亦标记为 prompt-only、开源且来自微软 GitHub,整体风险较低。其描述会引导后续调用 Azure MCP foundry 工具处理部署与资源管理,但当前材料本身未声明自带密钥、远程端点或本地执行能力。
材料与系统检查项均显示该技能本身不需要密钥或环境变量,未见其自带收集、存储或传输凭证的说明。需注意其面向 Azure/Foundry 工作流,实际执行相关子流程时可能由外部 Azure MCP 工具处理云凭证,但这不属于当前技能材料直接要求。
当前材料未声明任何远程端点,系统也标注 host 为无;作为 prompt-only 技能,本体未体现主动联网或数据外发逻辑。其文档提及后续调用 Azure MCP foundry 工具,但未在此材料中给出额外不明外发目标。
该对象被标记为 prompt-only,README 内容主要是流程约束与子技能导航;未见该技能自身在本机启动进程、执行脚本或调用系统能力的安装/运行说明。描述中的 Docker build、ACR push、部署等属于其指导的外部工作流能力,而非此技能材料自身直接执行。
材料未声明该技能本身可读写本地文件、数据库或其他资源,也未要求广泛的数据权限。虽提到 traces、dataset curation、logs、telemetry 等场景,但这些更像后续外部工具可能处理的数据类型,当前技能文本未体现直接数据访问实现。
来源为微软 GitHub 开源仓库,具备可审计性,且有一定社区采用度(222 star),这是明显的降风险因素。许可证与维护活跃度在材料中未明确,属于轻微信息缺口,但不足以抵消其官方开源来源带来的正面证据。
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "microsoft-foundry" 技能: 1. 下载 https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/plugin/skills/microsoft-foundry/SKILL.md 2. 保存为 ~/.claude/skills/microsoft-foundry/SKILL.md 3. 装好后重载技能,告诉我可以用了
请指导我在 Microsoft Foundry 中完成智能体部署:从 Docker 构建、推送到 ACR、创建 Foundry 项目与资源,到创建一个托管智能体,并说明所需 RBAC 权限、区域与容量检查项。
一套分步骤的部署指南,包含前置条件、命令示例、权限配置与常见故障排查建议。
我已经有一个 Foundry 智能体,请帮我设计批量评估和持续评估方案,包括数据集准备、grader 设置、关键指标、持续监控流程,以及如何根据评估结果改进提示词和指令。
一个完整的评估方案,涵盖评测数据、指标定义、自动化监控思路和优化建议。
请帮我规划在 Microsoft Foundry 中进行模型微调与智能体优化:比较 SFT、DPO、RFT 的适用场景,说明训练数据准备方式,如何从 traces 筛选数据集,以及如何使用 prompt optimizer 和 Agent Optimizer scaffold 提升效果。
一份微调与优化路线图,包含方法选择建议、数据准备步骤和可执行的优化流程。
This skill helps developers work with Microsoft Foundry resources, covering model discovery and deployment, complete dev lifecycle of AI agent, evaluation workflows, and troubleshooting.
MANDATORY: Before executing ANY workflow, you MUST first call the Azure MCP
foundrytool and inspect the available Foundry MCP tools and related parameters. Treat this initialfoundrycall as a discovery/help step. For this skill, Azure MCPfoundryis the required entry point for Foundry-related MCP operations.
MANDATORY: Before executing ANY workflow-specific steps, you MUST read the corresponding sub-skill document. Do not call workflow-specific MCP tools for a workflow without reading its skill document. This applies even if you already know the MCP tool parameters — the skill document contains required workflow steps, pre-checks, and validation logic that must be followed. This rule applies on every new user message that triggers a different workflow, even if the skill is already loaded.
This skill includes specialized sub-skills for specific workflows. Use these instead of the main skill when they match your task:
| Sub-Skill | When to Use | Reference |
|---|---|---|
| deploy | Containerize, build, push to ACR, create/update/clone agent deployments | deploy |
| invoke | Send messages to an agent, single or multi-turn conversations | invoke |
| invocations-ws | Build, deploy, and connect to hosted agents that speak the invocations_ws duplex WebSocket protocol — voice agents, real-time streams, and signaling for out-of-band media transports. | invocations-ws |
| observe | Evaluate agent quality, run batch evals, analyze failures, optimize prompts, improve agent instructions, compare versions, set up CI/CD monitoring, and enable continuous production evaluation | observe |
| trace | Query traces, analyze latency/failures, correlate eval results to specific responses via App Insights customEvents | trace |
| troubleshoot | View hosted agent logs, query telemetry, diagnose failures | troubleshoot |
| create | Create new hosted agent applications. Supports Microsoft Agent Framework, LangGraph, or custom frameworks in Python or C#, across responses, invocations, or invocations_ws protocols. | create |
| agent-optimizer | Make existing Python hosted-agent code optimization-ready, configure eval.yaml, run Agent Optimizer jobs, apply candidates locally, and deploy through azd after review. | agent-optimizer |
| eval-datasets | Harvest production traces into evaluation datasets, manage dataset versions and splits, track evaluation metrics over time, detect regressions, and maintain full lineage from trace to deployment. Use for: create dataset from traces, dataset versioning, evaluation trending, regression detection, dataset comparison, eval lineage. | eval-datasets |
| project/create | Creating a new Azure AI Foundry project for hosting agents and models. Use when onboarding to Foundry or setting up new infrastructure. | project/create/create-foundry-project.md |
| resource/create | Creating Azure AI Services multi-service resource (Foundry resource) using Azure CLI. Use when manually provisioning AI Services resources with granular control. | resource/create/create-foundry-resource.md |
…
评估 AKS 集群与工作负载对 Automatic 的兼容性并提供迁移修复建议
分析并精简 Markdown 内容,降低 token 消耗并提升 AI 处理效率。
帮助你编写、审查并规范符合 agentskills.io 规范的技能文档
帮助你跨区域与项目查询 Azure OpenAI 容量配额并推荐最佳部署位置
帮助你编写、校验并运行基于 eval.yaml 的智能体评测套件
使用 KQL 查询和分析 Azure Data Explorer 中的日志、遥测与时序数据。
帮助你在 Azure AI Foundry 上完成模型微调、部署与评估全流程
帮助用户按意图在 Azure OpenAI 中部署模型并查询区域容量与可用性。
帮助开发者探索 AI 模型、MCP 服务与智能代理实验集成流程
将 Azure ML 在线端点封装为 MCP 工具,供智能体用自然语言调用模型。
为微软与 Azure 开发场景提供结构化实时技能与官方文档辅助。
引导你逐步自定义 Azure OpenAI 模型部署参数与高级选项。