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

Failed to scan

The risk profile of this skill

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 clearly defines what the skill does (prepare Azure apps for deployment with specific tooling), explicitly delineates when to use it with an extensive list of natural trigger phrases, and proactively reduces conflict risk by specifying what it should NOT be used for with a redirect to the appropriate alternative skill. The only minor concern is that the sheer volume of trigger terms makes it slightly verbose, but each term adds genuine value.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Prepare Azure apps for deployment', 'infra Bicep/Terraform', 'azure.yaml', 'Dockerfiles', 'create/modernize', 'create+deploy'. Also distinguishes from cross-cloud migration with a clear boundary.	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', 'generate Bicep', 'function app', 'add authentication', 'add caching', '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 a clear Azure-specific niche, explicit boundary against the azure-cloud-migrate skill, and specific infrastructure tooling (Bicep/Terraform). The negative trigger ('not cross-cloud migration') actively reduces conflict risk with related skills.	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 clear phased execution, explicit validation gates, and well-organized references to detailed materials. However, it is severely undermined by extreme verbosity — critical instructions are repeated 3-4 times each, the authoritative compliance preamble wastes tokens on meta-instructions Claude doesn't need, and warning markers (❌/⛔/⚠️) are overused. The skill would be significantly more effective at roughly half its current length.

Suggestions

Remove the 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' preamble entirely — Claude follows skill instructions by default and this wastes ~60 tokens on meta-instruction.

Consolidate repeated instructions: the plan-status-update-before-validation requirement appears 3 times (Phase 2 Step 5, Phase 2 Step 6, and the Next section) — state it once in the workflow and remove duplicates.

Remove the redundant 'PLAN-FIRST WORKFLOW — MANDATORY' callout box since the same information is already conveyed by the Phase 1 section header, the Rules section, and the blocking gate between phases.

Add at least one concrete inline example — e.g., a minimal deployment-plan.md skeleton or a sample azure.yaml — so the skill has some directly actionable content rather than deferring everything to reference files.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with excessive repetition. The same instructions are repeated multiple times (e.g., 'create plan before any work' is stated 4+ times, 'update plan status to Ready for Validation before invoking azure-validate' appears 3+ times). The authoritative guidance preamble and constant ❌/⛔/⚠️ warnings add significant token bloat. The 'MANDATORY COMPLIANCE' header explaining that Claude must follow instructions is unnecessary meta-instruction.	1 / 3
Actionability	The skill provides structured tables with step references and clear artifact locations, but almost all actual guidance is deferred to reference files (analyze.md, requirements.md, scan.md, etc.). The skill itself contains no executable code, no concrete commands, and no inline examples of what generated artifacts should look like. It's essentially a routing document pointing elsewhere.	2 / 3
Workflow Clarity	The two-phase workflow (Planning → Execution) is clearly sequenced with explicit blocking gates ('STOP HERE — Do NOT proceed to Phase 2 until user approves'). Validation checkpoints are explicit (azure-validate before azure-deploy), and the plan status update is a concrete verification step before hand-off. The numbered steps with clear dependencies form a well-defined workflow.	3 / 3
Progressive Disclosure	Content is well-structured as an overview with clear one-level-deep references to detailed materials. Each planning and execution step links to a specific reference file. SDK references are organized by language. The routing table for specialized technologies is clearly presented with links to dedicated skills.	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: 9d594ab

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.