azure-hosted-copilot-sdk

Build and deploy GitHub Copilot SDK apps to Azure. WHEN: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API.

Quality

87%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description with excellent trigger term coverage and clear distinctiveness. The explicit WHEN clause with extensive keyword variations ensures reliable skill selection. The main weakness is that the 'what' portion is somewhat brief—it could benefit from listing more specific concrete actions beyond 'build and deploy'.

Suggestions

Expand the capability statement to list more specific actions, e.g., 'Build and deploy GitHub Copilot SDK apps to Azure: scaffold projects from templates, configure Azure OpenAI models, set up authentication with DefaultAzureCredential, and deploy via azd.'

Dimension	Reasoning	Score
Specificity	The description names the domain ('GitHub Copilot SDK apps') and two high-level actions ('Build and deploy'), but doesn't list multiple concrete sub-actions like scaffolding steps, configuration, or specific deployment procedures beyond the brief phrase.	2 / 3
Completeness	Clearly answers both 'what' (build and deploy GitHub Copilot SDK apps to Azure) and 'when' with an explicit 'WHEN:' clause containing extensive trigger terms. The when clause is thorough and well-structured.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including package names (@github/copilot-sdk), user intent phrases ('build copilot app', 'create copilot app'), Azure-specific terms ('DefaultAzureCredential', 'azure openai model'), API methods ('CopilotClient', 'createSession', 'sendAndWait'), and acronyms ('BYOM'). These are terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche targeting specifically GitHub Copilot SDK development with Azure deployment. The combination of Copilot SDK-specific terms, Azure hosting, and BYOM concepts makes it very unlikely to conflict with generic coding, deployment, or other AI-related skills.	3 / 3
	Total	11 / 12 Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill that efficiently routes users through multiple scenarios using a decision table, keeps the main file lean, and delegates details to clearly-signaled reference files. The main weakness is that Steps 2B and 2C lack concrete inline commands, relying entirely on references for actionability. The routing-first approach and model configuration table are particularly effective.

Suggestions

Add a concrete command or two for Steps 2B/2C inline (e.g., the temp-dir scaffold + copy commands) so Claude has immediate actionable guidance before consulting references.

Dimension	Reasoning	Score
Conciseness	Extremely lean — uses tables for routing, minimal prose, no unnecessary explanations of what Azure or Copilot SDK are. Every token serves a purpose.	3 / 3
Actionability	Provides the concrete scaffold command (`azd init --template ...`) and clear routing, but most steps delegate to references without inline executable examples. Steps 2B and 2C are described abstractly rather than with specific commands.	2 / 3
Workflow Clarity	Clear routing table at the top directs to the right step. Steps are sequenced (2→3→4) with explicit ordering for deployment (azure-prepare → azure-validate → azure-deploy). The skip instruction for Step 0 in azure-prepare shows awareness of workflow context. Docker check is a validation checkpoint.	3 / 3
Progressive Disclosure	Excellent use of one-level-deep references (copilot-sdk.md, deploy-existing.md, azure-model-config.md, existing-project-integration.md) clearly signaled inline. The SKILL.md serves as a concise overview/router with details appropriately split into reference files.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Commit: 9d594ab

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.