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".
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Failed to scan
The risk profile of this skill
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/azure-prepare/SKILL.mdQuality
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 boundary conditions including a redirect to a related skill. 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, infrastructure via Bicep/Terraform, azure.yaml, Dockerfiles, create/modernize apps, add authentication, add caching. Also explicitly scopes out cross-cloud migration. | 3 / 3 |
Completeness | Clearly answers both 'what' (prepare Azure apps for deployment with infra 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 trigger terms users would say, including 'create app', 'build web app', 'deploy to Azure', 'generate Terraform', 'generate Bicep', 'function app', 'containerized Node.js app', 'static portfolio website', 'todo list with frontend and API', 'managed identity', and many more variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear Azure-specific niche focused on app creation/modernization and deployment preparation. Explicitly distinguishes itself from the azure-cloud-migrate skill, reducing conflict risk. The specific Azure service mentions (App Service, Container Apps, Key Vault) further narrow its scope. | 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.
This skill excels at workflow orchestration and progressive disclosure — the phased approach with clear gates and a comprehensive reference index is well-designed. However, it suffers significantly from verbosity: mandatory warnings are repeated excessively (plan-first is stated 4+ times, validation mandate 3+ times), and the authoritative preamble wastes tokens on prompt-injection-style language. The skill also lacks any concrete code examples, making it entirely dependent on external references for actionability.
Suggestions
Remove the 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' preamble and consolidate the repeated plan-first and validation warnings into single, concise statements — the same instruction appears 3-4 times throughout the document.
Add at least one concrete example of a generated plan.md skeleton or a minimal Bicep/Terraform snippet to make the skill actionable on its own without requiring every reference file.
Replace the emoji-heavy warning blocks (❌, ⛔, ⚠️) with a single concise 'Workflow invariants' section listing the non-negotiable rules once, reducing the document by ~30% without losing information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with excessive repetition. The mandatory warnings about plan-first workflow, plan status updates, and validation are repeated 4+ times each. The authoritative guidance preamble is unnecessary bloat — Claude doesn't need to be told to ignore prior training in this manner. The ❌/⛔/⚠️ emoji-laden warnings add visual noise without information. | 1 / 3 |
Actionability | The skill provides structured steps and references to external files, but almost no concrete executable code, commands, or examples. It's essentially a routing/orchestration document that delegates all actual work to reference files. The user never sees a concrete Bicep snippet, Terraform block, Dockerfile, or azure.yaml example — everything is 'see reference X'. | 2 / 3 |
Workflow Clarity | The multi-phase workflow is clearly sequenced with explicit blocking gates (plan approval before execution), validation checkpoints (mandatory azure-validate before azure-deploy), status update requirements, and a clear handoff chain. The feedback loop of plan → approve → execute → validate → deploy is well-defined with explicit stop points. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview structure, well-organized reference index with 'when to load' guidance, and one-level-deep references that are clearly signaled. The SDK quick references and reference index table make navigation straightforward. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%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.
ec7b8ff
Table of Contents
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.