azure-prepare

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

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.

A well-structured orchestration skill with excellent workflow sequencing, validation checkpoints, and progressive disclosure through real reference files. The main weakness is redundant restatement of the plan-file and hand-off requirements across multiple MANDATORY callouts, which inflates token cost without adding information.

Suggestions

Consolidate the .azure/deployment-plan.md requirement into a single authoritative callout; the rule is currently restated in Rules #1, the PLAN-FIRST WORKFLOW section, Phase 1 Step 6, and the Next section.

Merge the repeated azure-validate -> azure-deploy hand-off instructions (Rules #5/#9, Phase 2 Steps 6-7, and the Next section) into one canonical block referenced where needed.

Reduce the density of stacked emoji/severity markers (❌/⛔/⚠️) on near-identical mandatory statements; one clear marker per requirement is enough for emphasis.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept over-explanation, but the plan-file requirement and the validate->deploy hand-off are each restated across ~4 separate MANDATORY/CRITICAL callouts (Rules #1, PLAN-FIRST WORKFLOW, Phase 1 Step 6, Next), which is padding that could be tightened. It is not a 4 because the redundancy is more than minor, and not a 2 because it does not over-explain concepts Claude already knows.	3 / 5
Actionability	Gives concrete guidance (the exact path .azure/deployment-plan.md, commands like 'azd init -t' vs plain 'azd init', the edit/ask_user tools, and per-step reference links), but the body is an orchestrator with no inline code blocks; actual templates live in references. It is not a 5 because there are no copy-paste examples covering common cases inline.	4 / 5
Workflow Clarity	Clearly sequenced Phase 1 (8 steps) and Phase 2 (7 steps) with explicit validation checkpoints (user approval gate, mandatory plan-status update before validate, hand-off to azure-validate), matching the anchor for clear sequence with explicit validation steps and feedback gates.	5 / 5
Progressive Disclosure	The body is a lean overview pointing to one-level-deep reference files (analyze.md, generate.md, security.md, etc.) via clearly signaled table links; all referenced files exist and content is appropriately split, matching the anchor for a clear overview with well-signaled one-level-deep references.	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.

A strong, well-structured description that states concrete capabilities, gives a rich set of natural trigger terms, answers both what and when explicitly, and proactively distinguishes itself from sibling skills. No meaningful gaps.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles') with comprehensive coverage of the preparation artifacts, matching the anchor for listing several specific concrete actions.	5 / 5
Completeness	Explicitly answers both what ('generates azure.yaml, infrastructure, and Dockerfiles for the azd workflow') and when ('USE ONLY when... azd' plus a concrete WHEN trigger list), matching the anchor for clear what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	The WHEN clause packs comprehensive natural terms including synonyms ('function app, timer trigger, service bus trigger, event-driven function', 'generate Bicep, generate Terraform') that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Carves a clear azd-only niche and explicitly disambiguates ('DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate)'), giving minimal 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: 14 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 15 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Path: .github/plugins/azure-skills/skills/azure-prepare/SKILL.md
Commit: 9d46511

Reviewed: 1 day 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.