Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 clearly defines its scope (Azure pre-deployment validation), lists specific concrete capabilities (configuration checks, Bicep/Terraform infrastructure validation, RBAC, managed identity), and provides an extensive explicit 'WHEN:' clause with natural trigger terms. The description is well-structured, uses third person voice, and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying.' These are clearly defined, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (pre-deployment validation covering configuration, infrastructure, RBAC, managed identity, prerequisites) and 'when' with an explicit 'WHEN:' clause listing numerous trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'validate my app', 'check deployment readiness', 'run preflight checks', 'validate azure.yaml', 'validate Bicep', 'troubleshoot deployment errors', 'verify RBAC roles', 'check role assignments', 'what-if analysis', and many more variations covering different user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Azure pre-deployment validation specifically, with distinct triggers like 'validate azure.yaml', 'validate Bicep', 'verify RBAC roles', 'validate Container Apps deployment' that are unlikely to conflict with general deployment or non-Azure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with clear workflow sequencing, explicit validation gates, and good progressive disclosure to reference files. Its main weakness is limited actionability — it delegates almost all concrete commands to external references rather than showing inline examples, and it has some redundancy in its callout boxes that repeat information already in the steps table.
Suggestions
Add 2-3 concrete example validation commands inline (e.g., `azd provision --preview`, `bicep build main.bicep`, `terraform validate`) rather than only mentioning them in a callout box, so the skill is more immediately actionable.
Consolidate the bottom callout boxes with the steps table to reduce redundancy — the 'Validation Authority' and 'Mandatory Next Step' callouts largely repeat steps 6-9.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy — the mandatory next step callout at the bottom repeats what step 9 already says, and the validation authority callout partially overlaps with steps 6-8. The prerequisite check block is somewhat verbose but justified for safety. | 2 / 3 |
Actionability | Steps are listed but heavily delegate to external references (recipes/README.md, role-verification.md, deployment-plan.md) without providing concrete commands or examples inline. The table mentions 'recipe-specific validation commands' without showing any actual commands like `azd provision --preview` or `bicep build` (those only appear in the callout box, not as executable guidance). | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps, explicit validation checkpoints (steps 3-5), a proof-recording step (step 6), an error resolution feedback loop (step 7), and a gate condition before status update (step 8). The validation authority callout reinforces the checkpoint pattern effectively. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear overview with well-signaled one-level-deep references to recipes/README.md, role-verification.md, global-rules.md, and the deployment plan. Content is appropriately split between the skill overview and reference files. | 3 / 3 |
Total | 10 / 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.
742d20b
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.