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). 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".
63
73%
Does it follow best practices?
Impact
—
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 ./plugin/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 an excellent skill description that excels across all dimensions. It provides specific capabilities, extensive natural trigger terms, clear what/when guidance, and explicit exclusion boundaries to prevent conflicts with related skills. The only minor concern is that the sheer length of the trigger list could be slightly trimmed, but the comprehensiveness is a strength for skill selection accuracy.
| 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, and more. Very detailed about what it does. | 3 / 3 |
Completeness | Clearly answers both 'what' (prepare Azure apps for deployment with infra Bicep/Terraform, azure.yaml, Dockerfiles) and 'when' (explicit WHEN clause with extensive trigger phrases). Also includes explicit exclusions (DO NOT USE FOR copilot-sdk apps, not for cross-cloud migration) which further clarifies when to use it. | 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', 'containerized Node.js app', 'static portfolio website', 'todo list with frontend and API', and many more variations users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting: excludes cross-cloud migration (directs to azure-cloud-migrate) and copilot-sdk apps (directs to azure-hosted-copilot-sdk). The Azure-specific focus and explicit exclusions make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-structured multi-phase workflow with strong validation checkpoints and clear sequencing, which is its primary strength. However, it suffers significantly from extreme verbosity and repetition — critical instructions like the plan-first requirement and the validate-before-deploy mandate are each restated 3-4 times with nearly identical wording, consuming substantial token budget. The actual actionable content (code examples, templates, concrete patterns) is entirely deferred to reference files that aren't provided for evaluation.
Suggestions
Consolidate the repeated plan-first and validate-before-deploy instructions into single authoritative statements rather than restating them 3-4 times each — this alone could reduce the document by 30-40%.
Add a concrete example of what `.azure/deployment-plan.md` should look like (even a minimal skeleton) so Claude can act without depending entirely on the referenced plan-template.md.
Move the Step 0 routing tables (prompt keywords and codebase markers) to the referenced specialized-routing.md file and keep only a brief 'check specialized-routing.md first' instruction inline.
Remove explanatory framing like 'This document is the official, canonical source' and 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' — these consume tokens without changing Claude's behavior compared to simply stating the rules.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The document is extremely verbose and repetitive. The same instructions are stated multiple times — the plan-first requirement is repeated at least 4 times with nearly identical wording (Rules #1, the PLAN-FIRST WORKFLOW box, Phase 1 intro, and Phase 1 Step 6). The mandatory hand-off to azure-validate is repeated 3 times. The file name `.azure/deployment-plan.md` is mentioned over a dozen times. Much of this redundancy wastes tokens without adding clarity. | 1 / 3 |
Actionability | The skill provides a clear structured workflow with specific file paths, tool references, and step sequences, but almost all concrete guidance is deferred to reference files (analyze.md, requirements.md, scan.md, etc.) that are not provided. There are no executable code examples, no concrete Bicep/Terraform snippets, and no example of what the deployment plan should look like. The actionability depends entirely on the referenced files. | 2 / 3 |
Workflow Clarity | The multi-phase workflow is clearly sequenced with explicit blocking gates (STOP before Phase 2), mandatory validation checkpoints (azure-validate before azure-deploy), status update requirements before hand-off, and destructive action confirmations. The Phase 1 → approval → Phase 2 → validate → deploy pipeline is well-defined with explicit error prevention steps. | 3 / 3 |
Progressive Disclosure | The skill references many external files (references/analyze.md, references/requirements.md, etc.) which is good progressive disclosure structure, but since no bundle files are provided, we cannot verify these references exist or are accurate. The main SKILL.md itself contains significant inline repetition that could be consolidated, and the routing tables in Step 0 are quite detailed and could potentially be in a separate reference file. | 2 / 3 |
Total | 8 / 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.
dd731da
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.