[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X010DC4ZF2TAJ2NSFAPXZ0":3,"skill-same:01M6X010DC4ZF2TAJ2NSFAPXZ0":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6X010DC4ZF2TAJ2NSFAPXZ0","foundry-agent-basics",null,"Help a learner build their first AI agent with the Microsoft Agent Framework (MAF) on Microsoft Foundry. Use when the task is creating a basic agent, wiring up FoundryChatClient, choosing a model, running the DevUI, or understanding lesson 1–2 concepts (instructions, tools, threads).","microsoft\u002FBuilding-AI-Agents-From-Zero-To-Production","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6X00M2R68PC89FEP5PT07MG",198,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffoundry-agent-basics\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"foundry","foundry agent basics","basics","basic","ai agent","running","when","wiring","threads","with","learner","maf","microsoft agent framework","lesson","task","agent framework","up","use","model","first","2026-11-10 10:12:30",false,"---\nname: foundry-agent-basics\ndescription: >-\n  Help a learner build their first AI agent with the Microsoft Agent Framework (MAF) on Microsoft\n  Foundry. Use when the task is creating a basic agent, wiring up FoundryChatClient, choosing a\n  model, running the DevUI, or understanding lesson 1–2 concepts (instructions, tools, threads).\n---\n\n# Foundry agent basics\n\nGuidance for building a first agent in this course (Lessons 1–2).\n\n## Guardrails (always apply)\n- **Platform:** Microsoft Foundry (never say \"Azure AI Foundry\"). Framework: Microsoft Agent\n  Framework (MAF).\n- **SDK:** use the pinned `agent-framework` from `requirements.txt` with **`FoundryChatClient`** and\n  the **Responses API**. Do not use `AzureAIClient`, `AzureAIAgentClient`, or `AzureOpenAIChatClient`.\n- **Model:** `gpt-5.1` for chat. Never `gpt-4o` \u002F `gpt-4.1` (retired) and never GitHub Models.\n- **Auth:** `az login` + `AzureCliCredential`; endpoint\u002Fmodel come from `.env` (never hardcoded).\n\n## What a learner should understand first\n1. **Agent = model + instructions + tools + a thread.** Instructions set the persona\u002Ftask; tools\n   extend capability; a thread carries conversation state.\n2. **Design before code (Lesson 1):** identify the scenario, the user, the tools needed, and the\n   success criteria. The course use case is \"Developer Onboarding\".\n3. **One agent, one job.** Lesson 2 builds several small, specialised agents rather than one\n   monolith (employee search, learning recommendation, coding, orchestration, etc.).\n\n## Minimal shape of a sample\n- Load env with `python-dotenv`; read the Foundry project endpoint and model name.\n- Create a `FoundryChatClient` with `AzureCliCredential`.\n- Create the agent with clear `instructions`; attach tools if needed.\n- Run it — most lesson-2 samples expose a local **DevUI** on a dedicated port (8090+).\n\n## How to help\n- Point the learner at the closest existing sample in `lesson-2-agent-development\u002F` and adapt it,\n  rather than writing from scratch.\n- Keep instructions specific and scoped; show how to test with a couple of representative prompts.\n- Remind them to `pip install -r requirements.txt`, `az login`, and populate `.env` first.\n\n## Validate\n- `python -m py_compile \u003Cfile>.py` must pass.\n- The sample should start its DevUI and answer a basic prompt end-to-end.\n\n## References\n- `lesson-1-agent-design\u002FREADME.md`, `lesson-2-agent-development\u002FREADME.md`\n- `MIGRATION-GUIDE.md` for the current SDK patterns.\n","# Foundry agent basics\n\nGuidance for building a first agent in this course (Lessons 1–2).\n\n## Guardrails (always apply)\n- **Platform:** Microsoft Foundry (never say \"Azure AI Foundry\"). Framework: Microsoft Agent\n  Framework (MAF).\n- **SDK:** use the pinned `agent-framework` from `requirements.txt` with **`FoundryChatClient`** and\n  the **Responses API**. Do not use `AzureAIClient`, `AzureAIAgentClient`, or `AzureOpenAIChatClient`.\n- **Model:** `gpt-5.1` for chat. Never `gpt-4o` \u002F `gpt-4.1` (retired) and never GitHub Models.\n- **Auth:** `az login` + `AzureCliCredential`; endpoint\u002Fmodel come from `.env` (never hardcoded).\n\n## What a learner should understand first\n1. **Agent = model + instructions + tools + a thread.** Instructions set the persona\u002Ftask; tools\n   extend capability; a thread carries conversation state.\n2. **Design before code (Lesson 1):** identify the scenario, the user, the tools needed, and the\n   success criteria. The course use case is \"Developer Onboarding\".\n3. **One agent, one job.** Lesson 2 builds several small, specialised agents rather than one\n   monolith (employee search, learning recommendation, coding, orchestration, etc.).\n\n## Minimal shape of a sample\n- Load env with `python-dotenv`; read the Foundry project endpoint and model name.\n- Create a `FoundryChatClient` with `AzureCliCredential`.\n- Create the agent with clear `instructions`; attach tools if needed.\n- Run it — most lesson-2 samples expose a local **DevUI** on a dedicated port (8090+).\n\n## How to help\n- Point the learner at the closest existing sample in `lesson-2-agent-development\u002F` and adapt it,\n  rather than writing from scratch.\n- Keep instructions specific and scoped; show how to test with a couple of representative prompts.\n- Remind them to `pip install -r requirements.txt`, `az login`, and populate `.env` first.\n\n## Validate\n- `python -m py_compile \u003Cfile>.py` must pass.\n- The sample should start its DevUI and answer a basic prompt end-to-end.\n\n## References\n- `lesson-1-agent-design\u002FREADME.md`, `lesson-2-agent-development\u002FREADME.md`\n- `MIGRATION-GUIDE.md` for the current SDK patterns.\n",{"name":5,"description":7},"main","8c4367c3df7138fa869c386fda70f9de89f23c75",".github\u002Fskills\u002Ffoundry-agent-basics",72,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-10-31 01:14:49",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add microsoft\u002FBuilding-AI-Agents-From-Zero-To-Production --skill foundry-agent-basics",{"tool":64,"command":65},"bunx","bunx skills add microsoft\u002FBuilding-AI-Agents-From-Zero-To-Production --skill foundry-agent-basics",{"tool":67,"command":68},"pnpm","pnpm dlx skills add microsoft\u002FBuilding-AI-Agents-From-Zero-To-Production --skill foundry-agent-basics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffoundry-agent-basics\u002FSKILL.md",true,[],[73,97,119,137,157],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":44},"01M6X01NFNWB6R9QV6137VGMS0","multi-agent-a2a","Help a learner compose agents as networked services using the open Agent-to-Agent (A2A) protocol — expose an agent as an A2A server and consume a remote agent as a peer. Use for Lesson 7 tasks: multi-agent orchestration and A2A client\u002Fserver wiring.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmulti-agent-a2a\u002FSKILL.md",[79],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[81,82,83,84,41,31,85,86,34,87,88,37,89,90,91,92,93,94,95,96],"a2a","multi agent","multi","multi agent a2a","for","remote","as","agent-to-agent","peer","agent orchestration","compose","open","services","server","tasks","orchestration",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":44},"01M6X01FJ3ZV88JAAF73R9Q2NQ","microsoft-toolbox","Help a learner use Microsoft Toolbox to define tools once and govern them centrally, then consume a toolbox from an agent through a single MCP endpoint. Use for Lesson 6 tasks: tool discovery, registration, governance, and versioning.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-toolbox\u002FSKILL.md",[103],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[105,106,9,107,108,109,110,111,41,112,113,95,114,115,37,116,85,117,34,118],"microsoft toolbox","toolbox","tool","registration","discovery","Tools","versioning","endpoint","help","governance","MCP","single","tool discovery","define",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":44},"01M6X01A1BEKTXZSPN6817VJV8","mcp-integration","Help a learner give an agent tools through the Model Context Protocol (MCP) — both client-side MCP and Foundry Hosted MCP tools. Use when connecting an agent to an MCP server (e.g. the GitHub MCP server), adding a remote tool, or reasoning about MCP approval\u002Fgovernance.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-integration\u002FSKILL.md",[125],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[127,115,128,41,30,129,86,34,130,131,107,94,132,133,113,114,134,135,136,42],"integration","MCP Integration","about","github mcp","github mcp server","protocol","reasoning","model context protocol","mcp server","github",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":144,"publishedAt":44},"01M6X0146GACX2QRFA1TG1T0A1","hosted-agent-deployment","Help a learner deploy an agent to production as a Microsoft Foundry Hosted Agent, and decide when Capability Hosts are needed. Use for Lessons 4–5: hosted deployment, thread\u002Fmemory persistence, bring-your-own storage, and enterprise governance.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fhosted-agent-deployment\u002FSKILL.md",[143],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[145,146,114,147,9,148,149,113,150,30,151,85,152,153,34,87,41,154,155,156],"hosted agent deployment","deployment","deploy","storage","memory","lessons","thread","hosts","bring","decide","Production","Enterprise",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":44},"01M6X00VV8GSAJZ4MASK7T8CQF","agent-evaluation","Help a learner evaluate and observe an AI agent on Microsoft Foundry — quality\u002Fsafety evaluators, tracing, and reading results. Use for Lesson 3 tasks: measuring agent performance, adding observability, or interpreting evaluation output.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FBuilding-AI-Agents-From-Zero-To-Production\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagent-evaluation\u002FSKILL.md",[163],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[165,166,167,168,85,169,170,34,37,41,171,172,173,174,113,95,24,9,28,175],"Evaluation","agent evaluation","observe","evaluate","reading","output","results","quality","Safety","observability","performance"]