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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-5

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

Well-structured, actionable, and strongly sequenced with validation and error-recovery loops appropriate to a destructive deployment skill. The main weakness is repetitive emphatic warning blocks that pad the token budget without adding new information.

Suggestions

Consolidate the multiple prerequisite/validation callout blocks (AUTHORITATIVE GUIDANCE, ⛔ STOP, DO NOT ASSUME/SKIP, FORBIDDEN) into a single concise prerequisite section; the message is restated in Rules 1-2 and Step 1 already.

Replace repeated emphatic warnings with a single canonical prerequisite checklist and reference it once from the Steps table to reduce redundancy.

Move the URL-format and validation-proof rules into their respective step rows or a short 'Output conventions' subsection to keep the main flow scannable.

Dimension	Reasoning	Score
Conciseness	The steps table, SDK/MCP references, and Rules are efficient, but the mandatory-compliance callouts (AUTHORITATIVE GUIDANCE, ⛔ STOP, DO NOT ASSUME/SKIP, FORBIDDEN) repeat the same prerequisite/validation message several times and could be tightened.	3 / 5
Actionability	Provides concrete commands (azd up, azd deploy, terraform apply, azd provision --no-prompt) and a precise 10-step table, with the bulk of executable detail correctly delegated to reference files; minor gaps inline.	4 / 5
Workflow Clarity	A clear 10-step sequence with explicit validation checkpoints (plan status + Validation Proof, pre-deploy checklist, RBAC health check, verify success, live role verification) and an error-recovery feedback loop via recipe errors.md.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview pointing to one-level-deep references (checklist, recipes/, sdk/, troubleshooting, live-role-verification), all of which resolve to real files, with clear navigation via the steps table and references section.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 a high-quality description: concrete, comprehensive in triggers, explicit on both what and when, and clearly distinguished from sibling skills via negative guidance. No meaningful improvements needed.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery" — giving comprehensive coverage of deployment execution rather than vague language.	5 / 5
Completeness	Explicitly answers both what (execute Azure deployments for already-prepared apps) and when (concrete WHEN trigger phrases plus a DO NOT USE WHEN clause), matching the top anchor.	5 / 5
Trigger Term Quality	The WHEN clause lists a comprehensive set of natural user phrases ("push to production", "go live", "ship it", "terraform apply", "publish to Azure") with strong synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche — deployment execution only — reinforced by negative triggers routing creation tasks to azure-prepare and prerequisites on azure-validate, minimizing conflict risk.	5 / 5
	Total	20 / 20 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
Path: .github/plugins/azure-skills/skills/azure-deploy/SKILL.md
Commit: 16dc8c5

Reviewed: about 12 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.