azure-hosted-copilot-sdk
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).
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 an excellent skill description that clearly defines its scope, provides abundant natural trigger terms, and explicitly delineates boundaries with related skills. The inclusion of MANDATORY conditions, PREFER OVER guidance, and DO NOT USE FOR exclusions makes it highly effective for skill selection in a large skill library. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Build, deploy, and modify GitHub Copilot SDK apps on Azure.' Also specifies concrete markers like '@github/copilot-sdk', 'CopilotClient', 'createSession', 'sendAndWait', and 'azd init copilot'. | 3 / 3 |
Completeness | Clearly answers 'what' (build, deploy, modify GitHub Copilot SDK apps on Azure) and 'when' (explicit WHEN clause with trigger terms, MANDATORY conditions, and a DO NOT USE FOR section that clarifies boundaries). Both dimensions are thoroughly addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including package names ('@github/copilot-sdk', 'CopilotClient'), user intent phrases ('build copilot app', 'add feature to copilot app'), and acronyms ('BYOM', 'bring your own model'). These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive with explicit boundary-setting: 'PREFER OVER azure-prepare when copilot-sdk markers detected' and a 'DO NOT USE FOR' section that names competing skills (azure-deploy, azure-prepare, microsoft-foundry) and their respective domains. This minimizes conflict risk significantly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured orchestration workflow with clear routing logic and appropriate delegation to sub-skills and reference files. Its main weaknesses are verbosity in the detection/routing section (the same priority rule is restated multiple times with warning callouts) and limited inline actionable code — most concrete implementation details are deferred to reference files that aren't available in the bundle.
Suggestions
Consolidate the three repeated warning callouts about routing priority into a single concise statement at the top of the detection section to reduce token overhead.
Add at least one inline executable code snippet for the BYOM bearerToken pattern, since it's marked as MANDATORY and is the most error-prone configuration path.
Include a minimal inline code example showing CopilotClient usage (e.g., createSession + sendAndWait) so the skill body is actionable without requiring reference file lookups.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The detection section is quite verbose with repeated warnings and redundant tables explaining routing logic. The scaffolding and deployment steps are lean, but the mandatory first check section could be significantly tightened — the same routing priority is stated three different ways with warning callouts. | 2 / 3 |
Actionability | Provides concrete commands (e.g., `azd init --template`) and specific markers to check, but most steps delegate to reference files without inline executable examples. Key operations like BYOM configuration, SDK integration, and deployment lack copy-paste-ready code snippets in the skill body itself. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: detection → routing → scaffold/deploy → model config → deploy pipeline. The routing table is unambiguous, Step 4 explicitly chains sub-skills in order, and the yield-to-azure-deploy checkpoint prevents misrouting. Validation is handled via the azure-validate sub-skill reference. | 3 / 3 |
Progressive Disclosure | References to supporting files (references/copilot-sdk.md, references/deploy-existing.md, references/azure-model-config.md, references/auth-best-practices.md, references/existing-project-integration.md) are well-signaled and one level deep. However, no bundle files were provided, so we cannot verify these references resolve correctly, and the detection section is overly detailed inline content that could be split out. | 2 / 3 |
Total | 9 / 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
915f809
- 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.