azure-hosted-copilot-sdk

作者: microsoft

Build, deploy, and modify GitHub Copilot SDK apps on Azure. MANDATORY when codebase contains @github/copilot-sdk or CopilotClient in package.json. PREFER OVER azure-prepare when copilot-sdk markers detected. WHEN: copilot SDK, @github/copilot-sdk, copilot-powered app, build copilot app, prepare copilot app, add feature to copilot app, modify copilot app, BYOM, bring your own model, CopilotClient, createSession, sendAndWait, azd init copilot. DO NOT USE FOR: deploying already-prepared...

npx skills add https://github.com/microsoft/azure-skills --skill azure-hosted-copilot-sdk

GitHub Copilot SDK on Azure

Codebase Detection — MANDATORY FIRST CHECK

⚠️ CRITICAL: This check MUST run before ANY other skill (azure-prepare, azure-deploy, etc.) when an existing codebase is present.

Detection procedure (run IMMEDIATELY for any build/modify/add-feature/prepare prompt):

  1. Read package.json in the workspace root (and any */package.json one level deep)
  2. Check if @github/copilot-sdk or copilot-sdk appears in name, dependencies, or devDependencies
  3. If NOT found in package.json, scan .ts and .js files for CopilotClient or createSession
  4. If ANY marker is found → invoke this skill as the entry point. Do not route directly to azure-prepare or azure-deploy — this skill orchestrates them as sub-skills.
MarkerWhere to check
@github/copilot-sdkpackage.json dependencies or devDependencies
copilot-sdkpackage.json name or dependencies
CopilotClientSource files (.ts, .js)
createSession + sendAndWaitSource files (.ts, .js)

Generic prompts that MUST trigger this skill when markers are detected:

Prompt pattern (no "copilot" keyword)Why this skill
"Build this app" / "Prepare this app for Azure"Codebase contains @github/copilot-sdk - needs SDK-aware scaffolding
"Add a new feature to this app"Requires SDK-aware implementation patterns
"Update this app" / "Modify this app"Must preserve SDK integration patterns

⚠️ Warning: ANY build, modify, add-feature, or prepare prompt targeting an existing codebase MUST route to this skill when codebase contains @github/copilot-sdk, even if the prompt does not mention "copilot". This skill then orchestrates azure-prepare and azure-deploy as sub-skills.

⚠️ Yield to azure-deploy: When the codebase already has .azure/deployment-plan.md and the user wants to deploy (not modify or add features), route to azure-deploy instead. This skill handles preparation; azure-deploy handles execution.

Step 1: Route

User wantsAction
Build new (empty project)Step 2A (scaffold)
Add new SDK service to existing repoStep 2B (scaffold alongside)
Deploy existing SDK app to AzureStep 2C (add infra to existing SDK app)
Modify/add features to existing SDK appUse codebase context + SDK references to implement
Add SDK to existing app codeIntegrate SDK
Use Azure/own modelStep 3 (BYOM config)

Step 2A: Scaffold New (Greenfield)

azd init --template azure-samples/copilot-sdk-service

Template includes API (Express/TS) + Web UI (React/Vite) + infra (Bicep) + Dockerfiles + token scripts — do NOT recreate. See SDK ref.

Step 2B: Add SDK Service to Existing Repo

User has existing code and wants a new Copilot SDK service alongside it. Scaffold template to a temp dir, copy the API service + infra into the user's repo, adapt azure.yaml to include both existing and new services. See deploy existing ref.

Step 2C: Deploy Existing SDK App

User already has a working Copilot SDK app and needs Azure infra. See deploy existing ref.

Step 3: Model Configuration

Three model paths (layers on top of 2A/2B):

PathConfig
GitHub defaultNo model param — SDK picks default
GitHub specificmodel: "<name>" — use listModels() to discover
Azure BYOMmodel + provider with bearerToken via DefaultAzureCredential

⚠️ BYOM Auth — MANDATORY: Azure BYOM configurations MUST use DefaultAzureCredential (local dev) or ManagedIdentityCredential (production) to obtain a bearerToken. The ONLY supported auth pattern is bearerToken in the provider config. See auth-best-practices.md for the credential pattern and model config ref for the full BYOM code example.

See model config ref.

Step 4: Deploy

Invoke azure-prepare (skip its Step 0 routing — scaffolding is done) → azure-validateazure-deploy in order.

Rules

  • Read AGENTS.md in user's repo before changes
  • Docker required (docker info)
  • BYOM auth: ONLY bearerToken via DefaultAzureCredential or ManagedIdentityCredential — no other auth pattern is supported

来自 microsoft 的更多技能

oss-growth
microsoft
OSS growth hacker persona
official
microsoft-foundry
microsoft
端到端部署、评估和管理Foundry代理:Docker构建、ACR推送、托管/提示代理创建、容器启动、批量评估、持续评估、提示优化工作流、agent.yaml、从追踪中整理数据集。用途:将代理部署到Foundry、托管代理、创建代理、调用代理、评估代理、运行批量评估、持续评估、持续监控、持续评估状态、优化提示、改进提示、提示优化器、优化代理指令、改进代理...
officialdevelopmentdevops
azure-ai
microsoft
用于Azure AI:搜索、语音、OpenAI、文档智能。支持搜索、向量/混合搜索、语音转文字、文字转语音、转录、OCR。适用场景:AI搜索、查询搜索、向量搜索、混合搜索、语义搜索、语音转文字、文字转语音、转录、OCR、文字转语音。
officialdevelopmentapi
azure-deploy
microsoft
对已准备好的应用程序执行Azure部署,这些程序需包含现有的.azure/deployment-plan.md和基础设施文件。当用户要求创建新应用程序时,请勿使用此技能——应改用azure-prepare。此技能运行azd up、azd deploy、terraform apply和az deployment命令,并内置错误恢复机制。需要来自azure-prepare的.azure/deployment-plan.md以及来自azure-validate的已验证状态。适用场景:"运行azd up"、"运行azd deploy"、"执行部署"...
officialdevopsaws
azure-storage
microsoft
Azure存储服务,包括Blob存储、文件共享、队列存储、表存储和Data Lake。解答关于存储访问层(热、冷、冷、归档)的问题,说明各层的使用场景及对比。提供对象存储、SMB文件共享、异步消息传递、NoSQL键值存储和大数据分析。包含生命周期管理。用途:Blob存储、文件共享、队列存储、表存储、Data Lake、上传文件、下载Blob、存储账户、访问层等。
officialdevelopmentdatabase
azure-diagnostics
microsoft
使用AppLens、Azure Monitor、资源健康和安全分类调试Azure生产问题。适用场景:调试生产问题、排查应用服务、应用服务CPU过高、应用服务部署失败、排查容器应用、排查函数、排查AKS、kubectl无法连接、kube-system/CoreDNS故障、Pod挂起、CrashLoop、节点未就绪、升级失败、分析日志、KQL、洞察、镜像拉取失败、冷启动问题、健康探测失败……
officialdevopsdevelopment
azure-prepare
microsoft
为Azure应用准备部署(基础设施Bicep/Terraform、azure.yaml、Dockerfile)。用于创建/现代化或创建+部署;不用于跨云迁移(使用azure-cloud-migrate)。请勿用于:copilot-sdk应用(使用azure-hosted-copilot-sdk)。适用场景:"创建应用"、"构建Web应用"、"创建API"、"创建无服务器HTTP API"、"创建前端"、"创建后端"、"构建服务"、"现代化应用"、"更新应用"、"添加身份验证"、"添加缓存"、"托管在Azure上"、"创建并...
officialdevelopmentdevops
azure-validate
microsoft
部署前对Azure就绪状态进行验证。对配置、基础设施(Bicep或Terraform)、RBAC角色分配、托管标识权限及先决条件进行深度检查,然后再部署。适用场景:验证我的应用、检查部署就绪状态、运行预检、验证配置、检查是否可部署、验证azure.yaml、验证Bicep、部署前测试、排查部署错误、验证Azure Functions、验证函数应用、验证无服务器...
officialdevopstesting