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.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/skills/azure-deploy/SKILL.mdQuality
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 minimizes conflict 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 apps, 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 and negative trigger conditions. The 'DO NOT use this skill when...' and 'DO NOT USE WHEN' clauses with specific counter-examples make it very unlikely to conflict with the preparation skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
54%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 structure with clear sequencing, validation gates, and progressive disclosure to supporting references. However, it is significantly undermined by extreme verbosity — prerequisite checks and warnings are repeated 3-4 times each, consuming tokens without adding value. Actionability suffers because nearly all concrete execution details are delegated to external files with no inline examples or commands.
Suggestions
Consolidate the prerequisite check into a single concise block instead of repeating it in the header callout, the STOP block, the Rules section, and the Validation Proof Check callout.
Add at least one concrete inline command example (e.g., `azd up --no-prompt` or `azd deploy`) so the skill is partially actionable without loading external references.
Remove the 'DO NOT MANUALLY UPDATE THE PLAN STATUS' and 'DO NOT ASSUME' paragraphs — a single sentence like 'Only azure-validate may set status to Validated' suffices.
Move the URL format rule to the verification step reference rather than calling it out as a top-level warning block.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The prerequisite check is stated at least 4 times (header callout, stop block, rules section, validation proof check). The forbidden status update warning, the URL format rule, and the workflow sequence are all repeated multiple times. Much of this is defensive repetition that doesn't add new information. | 1 / 3 |
Actionability | The steps table provides a clear sequence but almost all actual execution details are delegated to external references (recipes, checklists, SDK docs). There are no inline executable commands or concrete code examples — the skill tells you to 'follow recipe steps' and 'see recipe's errors.md' rather than providing direct guidance. The MCP tools table is helpful but lacks usage examples. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation checkpoints (check plan status, pre-deploy checklist, RBAC health check, verify success, live role verification). There are feedback loops — if prerequisites aren't met, it directs to the correct prior skill. Error handling has a dedicated step with references. The prerequisite gate pattern is well-defined. | 3 / 3 |
Progressive Disclosure | The skill is structured as an overview with well-signaled one-level-deep references to checklists, recipes, SDK docs, troubleshooting, and verification guides. Navigation is clear with both inline links in the steps table and a dedicated References section. Content is appropriately split between the overview and detailed reference files. | 3 / 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.