skills/azure-hosted-copilot-sdk/SKILL.md
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 copilot-sdk apps (use azure-deploy), general web apps without copilot SDK (use azure-prepare), Copilot Extensions, Foundry agents (use microsoft-foundry).
npx skillsauth add microsoft/azure-skills azure-hosted-copilot-sdkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
⚠️ CRITICAL: This check MUST run before ANY other skill (azure-prepare, azure-deploy, etc.) when an existing codebase is present.
package.json in the workspace root (and any */package.json one level deep)@github/copilot-sdk or copilot-sdk appears in name, dependencies, or devDependencies.ts and .js files for CopilotClient or createSession| Marker | Where to check |
|--------|---------------|
| @github/copilot-sdk | package.json dependencies or devDependencies |
| copilot-sdk | package.json name or dependencies |
| CopilotClient | Source files (.ts, .js) |
| createSession + sendAndWait | Source files (.ts, .js) |
| 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.mdand the user wants to deploy (not modify or add features), route to azure-deploy instead. This skill handles preparation; azure-deploy handles execution.
| User wants | Action | |------------|--------| | Build new (empty project) | Step 2A (scaffold) | | Add new SDK service to existing repo | Step 2B (scaffold alongside) | | Deploy existing SDK app to Azure | Step 2C (add infra to existing SDK app) | | Modify/add features to existing SDK app | Use codebase context + SDK references to implement | | Add SDK to existing app code | Integrate SDK | | Use Azure/own model | Step 3 (BYOM config) |
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.
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.
User already has a working Copilot SDK app and needs Azure infra. See deploy existing ref.
Three model paths (layers on top of 2A/2B):
| Path | Config |
|------|--------|
| GitHub default | No model param — SDK picks default |
| GitHub specific | model: "<name>" — use listModels() to discover |
| Azure BYOM | model + provider with bearerToken via DefaultAzureCredential |
⚠️ BYOM Auth — MANDATORY: Azure BYOM configurations MUST use
DefaultAzureCredential(local dev) orManagedIdentityCredential(production) to obtain abearerToken. The ONLY supported auth pattern isbearerTokenin 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.
Invoke azure-prepare (skip its Step 0 routing — scaffolding is done) → azure-validate → azure-deploy in order.
AGENTS.md in user's repo before changesdocker info)bearerToken via DefaultAzureCredential or ManagedIdentityCredential — no other auth pattern is supporteddevelopment
# Azure App Onboard Scaffold — IaC Generation + Self-Review Generate deployment-ready infrastructure code from an architecture plan, verify it with adversarial self-review, and bridge to validation — all without deploying. ## Quick Reference | Property | Value | |----------|-------| | Parent | [azure-app-onboard](../SKILL.md) | | Best for | Turning `prepare-plan.json` service list into Bicep templates with secure-by-default patterns | | Inputs | `prepare-plan.json` (services, naming, quotas),
development
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud Run migration, Fargate to ACA, ECS/Kubernetes/GKE/EKS to Container Apps, Spring Boot to Container Apps, cross-cloud migration.
development
Use when deploying an existing web application or API to an already-running Azure Kubernetes Service cluster. Detects the framework, generates a Dockerfile and Kubernetes manifests, validates against AKS Deployment Safeguards, and deploys with verification. WHEN: deploy app to AKS, deploy to existing AKS cluster, containerize app for Kubernetes, generate K8s manifests for Azure, set up CI/CD for AKS, my AKS deployment is failing safeguard checks, I have a Django/Express/Spring Boot app to run on AKS. DO NOT USE FOR: creating or provisioning an AKS cluster (use azure-kubernetes), assessing migration to AKS Automatic (use azure-kubernetes-automatic-readiness), or deploying to non-AKS targets like Web Apps, Container Apps, or Functions.
devops
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).