[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699C55AYGT1ZVZDHWFZNBDB":3,"skill-same:01M699C55AYGT1ZVZDHWFZNBDB":117},{"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":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M699C55AYGT1ZVZDHWFZNBDB","agent-framework-builder-python",null,"Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting Python applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.","microsoft\u002Fagent-framework","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6999R99RF2DY8AXYFS5HZRM",14676,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,9],"agent framework","agent framework builder python","framework","python","builder","correct","when","declarative","for","orchestrations","with","middleware","pattern","hosting","use","integrations","applications","Evaluation","observability","harness","microsoft agent framework","sessions","workflows","2026-11-10 10:12:30",false,"---\nname: agent-framework-builder-python\ndescription: Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting Python applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.\nlicense: MIT\nmetadata:\n  version: \"0.3\"\n  project: agent-framework\n  language: python\n---\n\n# Agent Framework builder for Python\n\nUse this skill as the entry point for Python Agent Framework application work. Choose the smallest framework pattern\nthat preserves the required behavior, load only the relevant references, and validate against current APIs instead of\nrelying on remembered preview-era syntax.\n\n## Workflow\n\n1. Inspect the existing project, Python version, dependency manager, and installed Agent Framework packages.\n2. Choose the simplest matching path from the table below.\n3. Resolve design questions only when they materially change the implementation.\n4. Read only the linked reference for the selected path.\n5. Implement the smallest coherent change and run the narrowest validation that exercises it.\n\n## Core abstractions\n\n- A **chat client** implements the model-facing `SupportsChatGetResponse` protocol. It sends messages and options to a\n  model provider and returns chat responses or streaming updates.\n- An **agent** implements the `SupportsAgentRun` protocol. The standard `Agent` implementation combines a chat client\n  with instructions, tools, middleware, context providers, and session handling behind one `run(...)` interface.\n- A **harness agent** is a regular `Agent` assembled by `create_harness_agent`. It adds an opinionated set of context\n  providers and middleware; it does not introduce a separate agent abstraction.\n- A **workflow** coordinates explicit execution paths. Graph workflows and most orchestration builders can use multiple\n  `SupportsAgentRun` implementations or executors. `HandoffBuilder` is the exception: its participants must be concrete\n  `Agent` instances.\n\n## User interface options\n\n- **DevUI** is a local development, testing, and debugging tool for interacting with agents and workflows. Never run\n  or deploy DevUI as a production application host.\n- **AG-UI** is the application-facing protocol integration for connecting an agent or workflow to an AG-UI-compatible\n  frontend. Use the `agent-framework-ag-ui` package when the product needs streaming UI events, tool interactions,\n  shared state, interrupts, or resume behavior.\n\n## Choose the build path\n\n| Path | Choose it when | Details |\n| --- | --- | --- |\n| Plain agent | One model-driven actor owns the task and tools, sessions, context, and middleware are sufficient. | [Plain agents](references\u002Fagent-builder.md) |\n| Harness agent | The product needs an operating loop with todos, modes, memory, approvals, skills, optional file access, background agents, shell, compaction, or repeated execution. | [Harness agents](references\u002Fharness-agent-builder.md) |\n| Workflow or orchestration | Explicit stages, routing, parallelism, multiple participants, checkpointing, human input, or intermediate outputs are central to correctness. | [Workflows](references\u002Fworkflow-builder.md) |\n| Declarative definition | YAML or JSON should be the source of truth for a supported agent or workflow. | [Declarative definitions](references\u002Fdeclarative.md) |\n| Evaluation | Expected outputs, tool calls, failed runs, or quality regressions are the main concern. | [Evaluation](references\u002Fevaluation.md) |\n| Observability | The task is diagnosing or monitoring runtime behavior with traces, logs, and metrics. | [Observability](references\u002Fobservability.md) |\n| Extensibility | The application needs a custom provider, ContextProvider, or middleware component. | [Extensibility](references\u002Fextensibility.md) |\n| Integration | The task is choosing or wiring a provider, protocol, memory store, tool service, UI, or platform extension. | [Integrations](references\u002Fintegrations.md) |\n| Hosting and deployment | Working Agent Framework code needs a process host, protocol endpoint, identity contract, or deployment shape. | [Hosting and deployment](references\u002Fhosting-and-deployment.md) |\n\n## Defaults\n\n- Agent Framework requires Python 3.11 or later. Prefer the latest\n  supported Python release or the previous release (N-1), unless a required dependency has a narrower compatibility\n  range.\n- Install the narrow Agent Framework distribution needed by the application instead of defaulting to the\n  `agent-framework` meta-package.\n- Agent Framework does not automatically read `.env` files. If the project uses one, call `load_dotenv()` explicitly\n  or use the selected API's documented `env_file_path` or equivalent initialization option.\n\n## Current documentation lookup\n\nThis skill and its references guide high-level development choices; they are not product documentation. Use them for\nselection criteria, trade-offs, and constraints that materially change a choice. Microsoft Learn is the documentation\nsource for implementing the selected approach.\n\nFor provider matrices, package maturity, hosted tools, deployment details, or unfamiliar APIs, consult current sources\nbefore generating code. Use public docstrings or API reference pages for signatures and option details, and use Learn\nor maintained samples for end-to-end procedures. Do not copy those details into this skill or its references.\n\nWhen the coding agent supports MCP, configure the Microsoft Learn MCP Server as a Streamable HTTP server:\n\n```text\nhttps:\u002F\u002Flearn.microsoft.com\u002Fapi\u002Fmcp\n```\n\nSee [Microsoft Learn MCP Server setup](https:\u002F\u002Flearn.microsoft.com\u002Ftraining\u002Fsupport\u002Fmcp-get-started) for client\nconfiguration. The endpoint is for MCP clients and returns an error when opened directly in a browser.\n\n1. Search Microsoft Learn with `microsoft_docs_search`.\n2. Fetch the relevant page with `microsoft_docs_fetch`.\n3. Use `microsoft_code_sample_search` when a current implementation example is needed.\n4. If Learn MCP is unavailable and a trusted `mslearn` CLI is already installed, use the equivalent command:\n\n| MCP tool | Preinstalled CLI |\n| --- | --- |\n| `microsoft_docs_search(query=\"...\")` | `mslearn search \"...\"` |\n| `microsoft_docs_fetch(url=\"...\")` | `mslearn fetch \"...\"` |\n| `microsoft_code_sample_search(query=\"...\", language=\"python\")` | `mslearn code-search \"...\" --language python` |\n\nDo not fetch and execute an unpinned CLI package during a coding session. Use the\n[official Microsoft Learn MCP\u002FCLI setup](https:\u002F\u002Fgithub.com\u002FMicrosoftDocs\u002Fmcp) to install or update it intentionally.\n\nCanonical starting points:\n\n- [Agent Framework overview](https:\u002F\u002Flearn.microsoft.com\u002Fagent-framework\u002Foverview\u002F)\n- [Your first agent](https:\u002F\u002Flearn.microsoft.com\u002Fagent-framework\u002Fget-started\u002Fyour-first-agent)\n- [Python SDK samples](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Ftree\u002Fmain\u002Fpython\u002Fsamples)\n- [Foundry-hosted Agent Framework samples](https:\u002F\u002Fgithub.com\u002Fmicrosoft-foundry\u002Ffoundry-samples\u002Ftree\u002Fmain\u002Fsamples\u002Fpython\u002Fhosted-agents\u002Fagent-framework)\n","# Agent Framework builder for Python\n\nUse this skill as the entry point for Python Agent Framework application work. Choose the smallest framework pattern\nthat preserves the required behavior, load only the relevant references, and validate against current APIs instead of\nrelying on remembered preview-era syntax.\n\n## Workflow\n\n1. Inspect the existing project, Python version, dependency manager, and installed Agent Framework packages.\n2. Choose the simplest matching path from the table below.\n3. Resolve design questions only when they materially change the implementation.\n4. Read only the linked reference for the selected path.\n5. Implement the smallest coherent change and run the narrowest validation that exercises it.\n\n## Core abstractions\n\n- A **chat client** implements the model-facing `SupportsChatGetResponse` protocol. It sends messages and options to a\n  model provider and returns chat responses or streaming updates.\n- An **agent** implements the `SupportsAgentRun` protocol. The standard `Agent` implementation combines a chat client\n  with instructions, tools, middleware, context providers, and session handling behind one `run(...)` interface.\n- A **harness agent** is a regular `Agent` assembled by `create_harness_agent`. It adds an opinionated set of context\n  providers and middleware; it does not introduce a separate agent abstraction.\n- A **workflow** coordinates explicit execution paths. Graph workflows and most orchestration builders can use multiple\n  `SupportsAgentRun` implementations or executors. `HandoffBuilder` is the exception: its participants must be concrete\n  `Agent` instances.\n\n## User interface options\n\n- **DevUI** is a local development, testing, and debugging tool for interacting with agents and workflows. Never run\n  or deploy DevUI as a production application host.\n- **AG-UI** is the application-facing protocol integration for connecting an agent or workflow to an AG-UI-compatible\n  frontend. Use the `agent-framework-ag-ui` package when the product needs streaming UI events, tool interactions,\n  shared state, interrupts, or resume behavior.\n\n## Choose the build path\n\n| Path | Choose it when | Details |\n| --- | --- | --- |\n| Plain agent | One model-driven actor owns the task and tools, sessions, context, and middleware are sufficient. | [Plain agents](references\u002Fagent-builder.md) |\n| Harness agent | The product needs an operating loop with todos, modes, memory, approvals, skills, optional file access, background agents, shell, compaction, or repeated execution. | [Harness agents](references\u002Fharness-agent-builder.md) |\n| Workflow or orchestration | Explicit stages, routing, parallelism, multiple participants, checkpointing, human input, or intermediate outputs are central to correctness. | [Workflows](references\u002Fworkflow-builder.md) |\n| Declarative definition | YAML or JSON should be the source of truth for a supported agent or workflow. | [Declarative definitions](references\u002Fdeclarative.md) |\n| Evaluation | Expected outputs, tool calls, failed runs, or quality regressions are the main concern. | [Evaluation](references\u002Fevaluation.md) |\n| Observability | The task is diagnosing or monitoring runtime behavior with traces, logs, and metrics. | [Observability](references\u002Fobservability.md) |\n| Extensibility | The application needs a custom provider, ContextProvider, or middleware component. | [Extensibility](references\u002Fextensibility.md) |\n| Integration | The task is choosing or wiring a provider, protocol, memory store, tool service, UI, or platform extension. | [Integrations](references\u002Fintegrations.md) |\n| Hosting and deployment | Working Agent Framework code needs a process host, protocol endpoint, identity contract, or deployment shape. | [Hosting and deployment](references\u002Fhosting-and-deployment.md) |\n\n## Defaults\n\n- Agent Framework requires Python 3.11 or later. Prefer the latest\n  supported Python release or the previous release (N-1), unless a required dependency has a narrower compatibility\n  range.\n- Install the narrow Agent Framework distribution needed by the application instead of defaulting to the\n  `agent-framework` meta-package.\n- Agent Framework does not automatically read `.env` files. If the project uses one, call `load_dotenv()` explicitly\n  or use the selected API's documented `env_file_path` or equivalent initialization option.\n\n## Current documentation lookup\n\nThis skill and its references guide high-level development choices; they are not product documentation. Use them for\nselection criteria, trade-offs, and constraints that materially change a choice. Microsoft Learn is the documentation\nsource for implementing the selected approach.\n\nFor provider matrices, package maturity, hosted tools, deployment details, or unfamiliar APIs, consult current sources\nbefore generating code. Use public docstrings or API reference pages for signatures and option details, and use Learn\nor maintained samples for end-to-end procedures. Do not copy those details into this skill or its references.\n\nWhen the coding agent supports MCP, configure the Microsoft Learn MCP Server as a Streamable HTTP server:\n\n```text\nhttps:\u002F\u002Flearn.microsoft.com\u002Fapi\u002Fmcp\n```\n\nSee [Microsoft Learn MCP Server setup](https:\u002F\u002Flearn.microsoft.com\u002Ftraining\u002Fsupport\u002Fmcp-get-started) for client\nconfiguration. The endpoint is for MCP clients and returns an error when opened directly in a browser.\n\n1. Search Microsoft Learn with `microsoft_docs_search`.\n2. Fetch the relevant page with `microsoft_docs_fetch`.\n3. Use `microsoft_code_sample_search` when a current implementation example is needed.\n4. If Learn MCP is unavailable and a trusted `mslearn` CLI is already installed, use the equivalent command:\n\n| MCP tool | Preinstalled CLI |\n| --- | --- |\n| `microsoft_docs_search(query=\"...\")` | `mslearn search \"...\"` |\n| `microsoft_docs_fetch(url=\"...\")` | `mslearn fetch \"...\"` |\n| `microsoft_code_sample_search(query=\"...\", language=\"python\")` | `mslearn code-search \"...\" --language python` |\n\nDo not fetch and execute an unpinned CLI package during a coding session. Use the\n[official Microsoft Learn MCP\u002FCLI setup](https:\u002F\u002Fgithub.com\u002FMicrosoftDocs\u002Fmcp) to install or update it intentionally.\n\nCanonical starting points:\n\n- [Agent Framework overview](https:\u002F\u002Flearn.microsoft.com\u002Fagent-framework\u002Foverview\u002F)\n- [Your first agent](https:\u002F\u002Flearn.microsoft.com\u002Fagent-framework\u002Fget-started\u002Fyour-first-agent)\n- [Python SDK samples](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Ftree\u002Fmain\u002Fpython\u002Fsamples)\n- [Foundry-hosted Agent Framework samples](https:\u002F\u002Fgithub.com\u002Fmicrosoft-foundry\u002Ffoundry-samples\u002Ftree\u002Fmain\u002Fsamples\u002Fpython\u002Fhosted-agents\u002Fagent-framework)\n",{"name":5,"license":15,"metadata":52,"description":7},{"project":53,"version":54,"language":27},"agent-framework","0.3","main","31399727b0fd0142b4042e683d15cbf09104fd0a","skills\u002Fagent-framework-builder-python",2624,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework","https:\u002F\u002Faka.ms\u002Fagent-framework","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 14:06:55",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add microsoft\u002Fagent-framework --skill agent-framework-builder-python",{"tool":71,"command":72},"bunx","bunx skills add microsoft\u002Fagent-framework --skill agent-framework-builder-python",{"tool":74,"command":75},"pnpm","pnpm dlx skills add microsoft\u002Fagent-framework --skill agent-framework-builder-python","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002FSKILL.md",true,[79,85,89,93,97,101,105,109,113],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fagent-builder.md","REFERENCE","参考文档",7081,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fagent-builder.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fdeclarative.md",3191,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fdeclarative.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fevaluation.md",2866,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fevaluation.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fextensibility.md",7822,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fextensibility.md",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fharness-agent-builder.md",3421,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fharness-agent-builder.md",{"path":102,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fhosting-and-deployment.md",4873,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fhosting-and-deployment.md",{"path":106,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fintegrations.md",5828,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fintegrations.md",{"path":110,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fobservability.md",1919,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fobservability.md",{"path":114,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fworkflow-builder.md",3144,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-python\u002Freferences\u002Fworkflow-builder.md",[118,141,151,174,191,205],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":47},"01M70H1GNJPW85ENXA0BCPC6PF","draft-release-notes","Create or rewrite Agent Framework release notes from a generated GitHub release log. Use when preparing Python or .NET release notes, filtering mixed-language changelogs, deduplicating changes, preserving inline contributor credits, or documenting breaking-change migrations from pull requests. Requires the user to provide the generated GitHub log, language, and release version before work begins.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fdraft-release-notes\u002FSKILL.md",[],[125,126,127,128,129,130,30,131,132,133,134,135,136,38,137,138,139,140,24,27],"notes","release notes","release","draft release notes","draft","pull","contributor","mixed-language","rewrite","release version","log","version","filtering","generated","create","pull requests",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":47},"01M699C2PH4WPRCMV90NHANCY9","agent-framework-builder-dotnet","Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting .NET (C#) applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fskills\u002Fagent-framework-builder-dotnet\u002FSKILL.md",[147],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[28,26,149,24,150,46,43,45,9,42,40,29,39,38,44,35,30,31,32,33,34],"agent framework builder dotnet","dotnet",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"publishedAt":47},"01M699C0QKV5XEBE61PB8NV544","foundry-hosted-agent-validation","Step-by-step process for validating a Python Foundry hosted agent sample (under python\u002Fsamples\u002F04-hosting\u002Ffoundry-hosted-agents\u002F) end to end — running it locally (native runtime and `azd ai agent run`) and after deploying it to an Azure AI Foundry project with `azd`. Use this when asked to validate a hosted agent sample.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fpython\u002Fscripts\u002Fsample_validation\u002Fskills\u002Ffoundry-hosted-agent-validation\u002FSKILL.md",[157],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[159,160,161,162,163,164,32,165,166,167,168,38,169,170,26,171,30,172,173,27],"foundry","foundry hosted agent validation","validation","running","project","run","native","end","runtime","sample","model","tool","azure ai foundry","azure","ai agent",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":47},"01M699BYCYJD8RXC5MYY61WBPR","foundry-config-setup","Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder\u002Fhardcoded project_endpoint (for example \"https:\u002F\u002Fyour-project.services.ai.azure.com\") or a hardcoded model instead of reading them from the environment.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fpython\u002Fscripts\u002Fsample_validation\u002Fskills\u002Ffoundry-config-setup\u002FSKILL.md",[],[159,181,182,183,38,184,169,170,185,186,187,172,188,189,30,32,34,190,168,163],"setup","config","foundry config setup","environment","services","https","tool use","placeholder","example","missing",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":47},"01M699BWSTE6SGCCBY3JFP10GQ","support-style","Contoso Outdoors customer-support tone and formatting guidelines.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fpython\u002Fsamples\u002F04-hosting\u002Ffoundry-hosted-agents\u002Fresponses\u002Ffoundry_toolbox_mcp_skills\u002Fskills\u002Fsupport-style\u002FSKILL.md",[],[198,199,200,201,202,203,204],"style","support","support style","tone","formatting","guidelines","customer",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":47},"01M699BV1KJRPZQ932J8HRHD3E","escalation-policy","When and how to escalate Contoso Outdoors customer-support tickets.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fagent-framework\u002Fblob\u002Fmain\u002Fpython\u002Fsamples\u002F04-hosting\u002Ffoundry-hosted-agents\u002Fresponses\u002Ffoundry_toolbox_mcp_skills\u002Fskills\u002Fescalation-policy\u002FSKILL.md",[],[212,213,214,30,215,216,217,218,199,204],"escalation policy","escalation","policy","escalate","tickets","how to","how"]