azure-hosted-copilot-sdk
Build, deploy, modify GitHub Copilot SDK apps on Azure. MANDATORY when codebase contains @github/copilot-sdk or CopilotClient — use this skill instead of azure-prepare. PREFER OVER azure-prepare when codebase contains copilot-sdk markers. WHEN: copilot SDK, @github/copilot-sdk, copilot-powered app, deploy copilot app, add feature, modify copilot app, BYOM, bring your own model, CopilotClient, createSession, sendAndWait, azd init copilot. DO NOT USE FOR: general web apps without copilot SDK (use azure-prepare), Copilot Extensions, Foundry agents (use microsoft-foundry).
94
92%
Does it follow best practices?
Impact
Pending
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 covers all dimensions thoroughly. It provides specific actions, comprehensive trigger terms including both natural language and technical identifiers, explicit when/when-not guidance, and clear differentiation from related skills. The DO NOT USE FOR and MANDATORY/PREFER OVER clauses are particularly effective at preventing skill conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Build, deploy, modify GitHub Copilot SDK apps on Azure.' Also specifies what it covers (BYOM, CopilotClient, createSession, sendAndWait, azd init copilot) and what it doesn't cover. | 3 / 3 |
Completeness | Clearly answers 'what' (build, deploy, modify GitHub Copilot SDK apps on Azure) and 'when' with explicit WHEN clause listing trigger terms, plus MANDATORY/PREFER OVER conditions and DO NOT USE FOR exclusions that clarify boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including package names (@github/copilot-sdk), class names (CopilotClient), method names (createSession, sendAndWait), CLI commands (azd init copilot), and natural phrases (copilot-powered app, deploy copilot app, bring your own model, BYOM). | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly differentiates itself from azure-prepare, Copilot Extensions, and microsoft-foundry with DO NOT USE FOR guidance and MANDATORY/PREFER OVER clauses that resolve potential conflicts. | 3 / 3 |
Total | 12 / 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 orchestration skill with clear routing logic, concrete detection procedures, and excellent progressive disclosure to reference files. The main weakness is some verbosity in the detection section, where multiple warnings repeat the same routing mandate. Overall it's a strong skill that effectively guides Claude through a complex multi-path workflow.
Suggestions
Consolidate the three separate ⚠️ warnings in the detection section into a single concise directive — they all say the same thing (route here when SDK markers found, even without 'copilot' keyword).
The 'Generic prompts that MUST trigger this skill' table could be removed since the detection procedure already covers marker-based routing, and Claude can infer prompt matching.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The detection procedure section is somewhat verbose with repeated warnings and a table of prompt patterns that Claude could infer. The routing table and steps are lean, but the mandatory first check section has redundant emphasis (multiple ⚠️ warnings saying essentially the same thing). | 2 / 3 |
Actionability | Provides concrete commands (`azd init --template azure-samples/copilot-sdk-service`, `docker info`), specific markers to check, exact file paths to inspect, and clear routing decisions. The references to sub-files for detailed implementation are well-signaled. | 3 / 3 |
Workflow Clarity | Clear sequential workflow: detection → route → scaffold/deploy → model config → deploy. Each step has explicit decision criteria, the routing table covers all user intent scenarios, and Step 4 explicitly sequences sub-skills (azure-prepare → azure-validate → azure-deploy). | 3 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure — the SKILL.md serves as a concise overview with well-signaled one-level-deep references to detailed docs (copilot-sdk.md, deploy-existing.md, azure-model-config.md, auth-best-practices.md, existing-project-integration.md). No content that should be in separate files is inlined. | 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
a46a937
- 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.