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). WHEN: "create app", "build web app", "create API", "create serverless HTTP API", "create frontend", "create back end", "build a service", "modernize application", "update application", "add authentication", "add caching", "host on Azure", "create and deploy", "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", "deploy to Azure Container Apps using Terraform", "generate Terraform", "generate Bicep", "function app", "timer trigger", "service bus trigger", "event-driven function", "containerized Node.js app", "social media app", "static portfolio website", "todo list with frontend and API", "prepare my Azure application to use Key Vault", "managed identity".

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/plugins/azure-skills/skills/azure-prepare/SKILL.md

Quality

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 a strong skill description that excels across all dimensions. It provides specific capabilities, extensive natural trigger terms, clear what/when guidance, and explicit boundaries with other skills (the cross-cloud migration exclusion). The only minor concern is that the sheer volume of trigger terms makes it slightly verbose, but each term adds genuine value for skill selection.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Prepare Azure apps for deployment', 'infra Bicep/Terraform', 'azure.yaml', 'Dockerfiles', and distinguishes create/modernize from cross-cloud migration. Covers specific technologies and artifact types.	3 / 3
Completeness	Clearly answers both 'what' (prepare Azure apps for deployment with Bicep/Terraform, azure.yaml, Dockerfiles) and 'when' with an explicit and extensive WHEN clause listing numerous trigger phrases. Also includes a negative boundary ('not cross-cloud migration') with a redirect to the correct skill.	3 / 3
Trigger Term Quality	Excellent coverage of natural user phrases including 'create app', 'build web app', 'deploy to Azure', 'generate Terraform', 'function app', 'containerized Node.js app', 'todo list with frontend and API', and many more variations users would naturally say.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear Azure-specific scope, explicit boundary against cross-cloud migration (redirecting to 'azure-cloud-migrate'), and specific technology triggers like Bicep, Terraform, Azure App Service, and Azure Container Apps that clearly define its niche.	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 and progressive disclosure, with a clear two-phase process, explicit validation gates, and well-organized references to detailed sub-documents. However, it is severely undermined by extreme verbosity — critical instructions like 'create the plan file first' and 'invoke azure-validate before deploying' are each repeated 4-5 times with escalating emphasis markers, wasting significant token budget. The actionability is moderate since nearly all concrete implementation details are deferred to reference files.

Suggestions

Consolidate the repeated plan-first and validate-before-deploy instructions into single authoritative statements rather than restating them 4-5 times across Rules, workflow boxes, phase tables, and the Next section.

Remove the AUTHORITATIVE GUIDANCE preamble — Claude follows skill instructions by default; the meta-instruction about mandatory compliance wastes tokens.

Add a concrete example of what `.azure/deployment-plan.md` skeleton content looks like (even a minimal 5-line template) rather than only referencing plan-template.md, to improve actionability.

Remove redundant emphasis markers (⛔, ❌, MANDATORY, CRITICAL) — use them once per concept rather than stacking multiple markers on repeated statements of the same requirement.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The same instructions are restated multiple times — the plan-first requirement is stated in Rules #1, the PLAN-FIRST WORKFLOW section, Phase 1 Step 6, and the STOP HERE block. The mandatory hand-off to azure-validate is repeated in Rules #5, Phase 2 Steps 6-7, and the entire 'Next' section. The AUTHORITATIVE GUIDANCE preamble and excessive ⛔/❌ markers add tokens without adding information Claude needs.	1 / 3
Actionability	The skill provides structured steps and references to external files, but almost all concrete guidance is deferred to reference documents (analyze.md, requirements.md, scan.md, etc.). The skill itself contains no executable code, no concrete examples of what deployment-plan.md should contain, and no specific commands beyond mentioning `azd init`. The routing tables and phase tables are actionable in structure but lack executable detail.	2 / 3
Workflow Clarity	The two-phase workflow is clearly sequenced with explicit blocking gates (plan approval before execution), mandatory validation checkpoints (azure-validate before azure-deploy), status update requirements, and a clear handoff chain (prepare → validate → deploy). Destructive action safeguards and error prevention are well-specified. The feedback loop of writing the plan skeleton, populating progressively, and finalizing before presenting is explicit.	3 / 3
Progressive Disclosure	The skill serves as a clear orchestration overview with well-signaled one-level-deep references to specific topics (analyze.md, requirements.md, scan.md, recipe-selection.md, etc.). SDK quick references are organized by language. The routing table for specialized skills is well-structured. Content is appropriately split between this overview and the referenced documents.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Commit: 742d20b

Reviewed: 5 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.