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.

Quality

85%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured as an orchestration skill: a sequenced 10-step workflow with validation checkpoints and clean progressive disclosure to real reference files. Its weaknesses are repetitive emphatic prerequisite warnings and in-body actionability that leans on referenced recipe files.

Suggestions

Consolidate the prerequisite guidance into a single authoritative block; remove the duplicated plan-status/STOP statements repeated across the AUTHORITATIVE GUIDANCE, STOP, and Rules sections to tighten conciseness.

Inline one minimal end-to-end command example (e.g. the canonical 'azd up' / 'azd deploy' invocation with expected output) so the body is actionable without opening a reference file.

Keep the ⛔ callouts but reduce redundancy between the URL FORMAT RULE, VALIDATION PROOF CHECK, and Step 1/Step 2 entries that restate the same checks.

Dimension	Reasoning	Score
Conciseness	It avoids explaining Azure/deployment concepts Claude already knows, but restates the prerequisite three times (AUTHORITATIVE GUIDANCE block, STOP block, Rules 1-2) and repeats ⛔ emphatic blocks (URL FORMAT, VALIDATION PROOF CHECK) that could be tightened, fitting the mostly-efficient-but-could-be-tighter level 2 rather than the lean level 3.	2 / 3
Actionability	Some concrete commands appear in-body ('azd provision --no-prompt', verify AcrPull, prepend https://), but the bulk of executable detail is delegated to reference files (recipes/README.md, errors.md, verify.md), making the body a routing table rather than copy-paste-ready — the level-2 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	A 10-step table gives a clear sequence with explicit validation checkpoints (check plan status, pre-deploy checklist, RBAC health check) and an error-recovery/verification loop (steps 7-9), matching the level-3 anchor of clear sequence with explicit validation and feedback loops for a destructive operation.	3 / 3
Progressive Disclosure	The body is a concise overview with well-signaled one-level-deep references (all referenced paths verified to exist: pre-deploy-checklist.md, recipes/README.md, sdk/*, troubleshooting.md) and content appropriately split across files, matching the level-3 clear-overview anchor rather than the inline-blob level 2.	3 / 3
	Total	10 / 12 Passed

Description

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.

The description is precise, action-oriented, and well-bounded: it states concrete commands, supplies explicit WHEN and DO NOT USE WHEN triggers, and clearly distinguishes itself from sibling azure-prepare/azure-validate skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery' — matching the anchor for specific concrete actions rather than the partial domain-only level 2.	3 / 3
Completeness	Explicitly answers both what ('Execute Azure deployments...runs azd up, azd deploy...') and when (a WHEN list plus a DO NOT USE WHEN list), meeting the explicit-triggers anchor rather than the when-implied level 2.	3 / 3
Trigger Term Quality	The WHEN clause gives broad natural-phrase coverage — 'push to production', 'push to cloud', 'go live', 'ship it', 'bicep deploy', 'terraform apply', 'publish to Azure', 'launch on Azure' — terms a user would naturally say, beyond the partial-coverage level 2.	3 / 3
Distinctiveness Conflict Risk	A clear niche (ALREADY-PREPARED apps) reinforced by explicit anti-triggers ('DO NOT use...use azure-prepare instead', 'Requires...validated status from azure-validate') makes triggering for the wrong skill unlikely, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 10 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 10 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

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.