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.
85
81%
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 is a strong skill description with excellent trigger term coverage and clear completeness. The explicit WHEN clause with extensive natural keywords makes it highly discoverable. The main weakness is that the 'what' portion is somewhat brief—it could benefit from listing more specific concrete actions beyond just 'build and deploy'.
Suggestions
Expand the 'what' portion to list more specific actions, e.g., 'Build, scaffold, configure, and deploy GitHub Copilot SDK apps to Azure. Handles project initialization, session management, model configuration, and Azure deployment.'
| 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 specific concrete actions like scaffolding steps, configuration, or testing. It's more of a summary than a detailed capability list. | 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 user-facing phrases ('build copilot app', 'create copilot app', 'bring your own model'), SDK-specific terms ('@github/copilot-sdk', 'CopilotClient', 'createSession'), deployment terms ('deploy copilot app', 'host on azure', 'azd init copilot'), and common abbreviations ('BYOM'). These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining GitHub Copilot SDK with Azure deployment. The specific trigger terms like '@github/copilot-sdk', 'copilot-sdk-service template', 'CopilotClient', and 'azd init copilot' are unique enough to avoid conflicts with general Azure or general GitHub skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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 routing/orchestration skill that excels at conciseness and progressive disclosure. The routing table pattern is effective for directing Claude to the right path. The main weaknesses are in actionability (some steps are described abstractly rather than with concrete commands) and workflow clarity (no validation checkpoints or error recovery steps despite involving deployment operations).
Suggestions
Add concrete commands for Steps 2B and 2C instead of prose descriptions (e.g., specific `cp`, `mkdir`, or file manipulation commands for copying template services into existing repos).
Add validation checkpoints after key steps — e.g., verify Docker is running before scaffold, verify `azd` CLI is installed, confirm successful scaffold output before proceeding to deploy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every line serves a purpose — routing table, commands, config options. No unnecessary explanations of what Azure, Docker, or SDKs are. Assumes Claude's competence throughout. | 3 / 3 |
Actionability | The scaffold command (`azd init --template ...`) is concrete and executable, and the routing table is clear. However, Steps 2B and 2C are described abstractly ('scaffold template to a temp dir, copy the API service') without concrete commands. Step 4 references other skills/processes without specifying exact commands. | 2 / 3 |
Workflow Clarity | The routing table in Step 1 is excellent for directing flow, and the numbered steps provide a clear sequence. However, there are no validation checkpoints — no verification after scaffolding, no checks after deployment prep, and Step 4 delegates to external processes without explicit error recovery or feedback loops. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview, well-signaled one-level-deep references, and an explicit reference index with 'when to load' guidance. The instruction to load on demand rather than all at once is a smart touch. | 3 / 3 |
Total | 10 / 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
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- 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.