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.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 description excels at trigger term coverage and completeness with an explicit WHEN clause containing many natural user phrases. The main weakness is the brevity of the 'what' portion - it only states 'Build and deploy' without detailing specific capabilities like scaffolding, configuration, or authentication setup. The description is highly distinctive for its specific niche.
Suggestions
Expand the 'what' portion to list specific concrete actions (e.g., 'scaffold projects, configure Azure authentication, set up model endpoints, integrate CopilotClient')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub Copilot SDK, Azure) and high-level actions ('Build and deploy'), but lacks specific concrete actions like 'scaffold projects', 'configure authentication', or 'set up model endpoints'. | 2 / 3 |
Completeness | Clearly answers both what ('Build and deploy GitHub Copilot SDK apps to Azure') and when (explicit 'WHEN:' clause with comprehensive trigger terms covering various user intents). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'build copilot app', 'copilot SDK', 'deploy copilot app', 'bring your own model', 'azure openai model', plus technical terms like 'DefaultAzureCredential', 'CopilotClient', 'sendAndWait'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining GitHub Copilot SDK with Azure deployment; specific terms like '@github/copilot-sdk', 'copilot-sdk-service template', 'azd init copilot' make it unlikely to conflict with general Azure or general Copilot 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 excels at routing users to the correct workflow path and maintains excellent token efficiency. The progressive disclosure is exemplary with clear references to detailed documentation. The main weakness is that inline actionability is limited since most concrete guidance lives in reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables for routing decisions, minimal prose, and assumes Claude understands Azure, Docker, and SDK concepts without explanation. Every line serves a purpose. | 3 / 3 |
Actionability | Provides concrete command (`azd init --template`) and clear routing table, but most actionable details are delegated to reference files. The BYOM config table gives structure but lacks executable code examples inline. | 2 / 3 |
Workflow Clarity | Clear numbered steps with explicit routing table at the start. Step 4 provides explicit sequencing (azure-prepare → azure-validate → azure-deploy) with a note to skip redundant routing. Validation is handled by delegating to the azure-validate skill. | 3 / 3 |
Progressive Disclosure | Excellent structure with overview routing table, concise step descriptions, and well-signaled one-level-deep references to detailed docs (references/copilot-sdk.md, references/deploy-existing.md, references/azure-model-config.md). | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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/github-copilot-for-azure
- Commit
1f4304b
- Reviewed
Table of Contents
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.