azure-prepare

Prepare Azure apps for deployment (infra Bicep/Terraform, azure.yaml, Dockerfiles). Use for create/modernize or create+deploy; not cross-cloud migration (use azure-cloud-migrate). DO NOT USE FOR: copilot-sdk apps (use azure-hosted-copilot-sdk), or Python code-only App Service deploys (use python-appservice-deploy). WHEN: "create app", "build web app", "create API", "modernize application", "host on Azure", "deploy to Azure", "deploy to Azure using Terraform", "deploy to Azure App Service", "deploy to Azure App Service using Terraform", "deploy to Azure Container Apps", "generate Terraform", "generate Bicep", "function app", "timer trigger", "service bus trigger", "event-driven function", "managed identity".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%

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 body with strong actionability, clear gated workflow, and excellent progressive disclosure into verified reference files. Its main weakness is repetition of the plan-file mandate across multiple sections, which inflates the token budget.

Suggestions

Consolidate the plan-file mandate into a single authoritative section; the repetitions across Rules, PLAN-FIRST WORKFLOW, Phase 1 Step 6, Phase 2 Step 6, and Next can cross-reference that one source instead of restating full warnings.

Trim redundant ⛔/AUTHORITATIVE banner blocks — one clear directive per requirement preserves the mandatory tone while reclaiming tokens.

Move the repeated 'do not run azd up / azd deploy directly' guidance to the single hand-off step (Phase 2 Step 7 / Next) rather than restating it in Rules, Phase 2, and the closing banner.

Dimension	Reasoning	Score
Conciseness	Mostly lean and directive (tables, short rules), but the mandatory plan-file requirement is restated across Rules, the PLAN-FIRST WORKFLOW block, Phase 1 Step 6, Phase 2 Step 6, and the Next section with repeated ⛔/AUTHORITATIVE banners that pad tokens without adding new information.	2 / 3
Actionability	Highly actionable: exact artifact paths (`.azure/deployment-plan.md`), concrete commands (`azd init -t <template>` vs plain `azd init`), explicit routing tables, and per-step reference links give copy-ready guidance.	3 / 3
Workflow Clarity	Clear sequenced workflow (Step 0 check → Phase 1 blocking planning → Phase 2 execution) with explicit validation checkpoints: "STOP HERE until user approves", mandatory status update to "Ready for Validation" before invoking azure-validate.	3 / 3
Progressive Disclosure	SKILL.md is an overview that maps each step to one-level-deep reference files via tables; all referenced paths (analyze.md, scan.md, generate.md, services/sql-database/bicep.md, etc.) resolve to real bundle files, giving clean navigation.	3 / 3
	Total	11 / 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.

A strong, third-person description that states concrete capabilities, includes an explicit WHEN trigger list, and actively disambiguates from sibling skills via negative scope. It is concise yet comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete artifacts/actions — "infra Bicep/Terraform, azure.yaml, Dockerfiles" — naming exactly what the skill produces rather than vague language.	3 / 3
Completeness	Explicitly answers what ("Prepare Azure apps for deployment...") and when (dedicated WHEN: trigger list), plus negative-scope guidance — both what and when are clearly stated.	3 / 3
Trigger Term Quality	The WHEN: clause enumerates many natural user phrases ("create app", "build web app", "deploy to Azure App Service", "generate Bicep", "function app", "managed identity") with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Explicit disambiguation — "not cross-cloud migration (use azure-cloud-migrate)", "DO NOT USE FOR: copilot-sdk apps..., or Python code-only App Service deploys" — gives a clear niche unlikely to trigger the wrong skill.	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: 12 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 13 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/github-copilot-for-azure
Commit: 4e2e307

Reviewed: 4 days 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.