azure-deploy
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 excels across all dimensions. It provides specific concrete actions, comprehensive natural trigger terms, explicit 'when' and 'when not' guidance, and clear differentiation from the related azure-prepare skill. The inclusion of both positive and negative trigger examples is a best practice that significantly reduces misselection risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery.' Also specifies prerequisites like '.azure/deployment-plan.md' and 'validated status from azure-validate.' | 3 / 3 |
Completeness | Clearly answers both 'what' (executes Azure deployments for already-prepared applications, runs specific commands with error recovery) and 'when' (explicit WHEN clause with trigger phrases, plus a DO NOT USE WHEN clause for disambiguation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'run azd up', 'push to production', 'push to cloud', 'go live', 'ship it', 'bicep deploy', 'terraform apply', 'publish to Azure', 'launch on Azure'. These are highly natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly differentiates itself from 'azure-prepare' with both positive triggers and negative triggers ('DO NOT use this skill when...', 'DO NOT USE WHEN...'). The boundary between preparation and execution is clearly drawn, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent workflow clarity and progressive disclosure, with a well-sequenced 10-step process and clear references to supporting documents. Its main weaknesses are verbosity in the prerequisite warnings (which repeat the same message 3+ times in different formats) and limited inline actionability — nearly all concrete commands are delegated to external references rather than shown directly.
Suggestions
Consolidate the three prerequisite warning blocks into a single concise block to reduce token waste while preserving the safety message.
Include at least the primary deployment commands inline (e.g., `azd up --no-prompt`, `azd deploy`) so the skill is actionable without requiring navigation to recipe files for the most common path.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The prerequisite warnings are heavily repeated (the same stop/check message appears in multiple forms at the top), and the forbidden/do-not-assume language is verbose. The core workflow table is efficient, but the surrounding guardrails could be consolidated significantly. | 2 / 3 |
Actionability | The skill provides a clear step table with references to external files, but almost no concrete commands or executable code are shown inline. The actual deployment commands (azd up, terraform apply, etc.) are delegated entirely to referenced recipes and checklists rather than shown directly, making the skill itself more of a routing document than an actionable guide. | 2 / 3 |
Workflow Clarity | The 10-step workflow table is clearly sequenced with explicit validation checkpoints (prerequisite verification, pre-deploy checklist, RBAC health check, post-deploy verification, live role verification). Error handling and feedback loops are addressed in steps 7-9, and destructive actions require user confirmation. | 3 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with clear one-level-deep references to checklists, recipes, SDK docs, troubleshooting, and verification guides. Navigation is easy with a mix of inline links and organized reference sections. | 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
- 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.