Lists multiple specific concrete actions: 'runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery.' Also specifies prerequisites like '.azure/deployment-plan.md' and 'validated status from azure-validate.'

Clearly answers both 'what' (execute Azure deployments for already-prepared apps, runs azd up/deploy/terraform apply with error recovery) and 'when' (explicit WHEN clause with trigger phrases, plus a DO NOT USE WHEN clause for disambiguation).

Excellent coverage of natural trigger terms users would say: 'run azd up', 'push to production', 'push to cloud', 'go live', 'ship it', 'bicep deploy', 'terraform apply', 'publish to Azure', 'launch on Azure'. These are highly natural phrases a user would actually type.

Exceptionally distinctive — explicitly differentiates itself from 'azure-prepare' with both positive triggers and negative triggers ('DO NOT use this skill when the user asks to CREATE a new application'). The DO NOT USE WHEN clause with specific phrases like 'create and deploy' and 'build and deploy' minimizes conflict risk.

The skill has significant repetition in prerequisite checks — the same validation requirement is stated in the blockquote at the top, the STOP block, the Rules section, and again in the Steps table. The trigger/scope clarifications are useful but somewhat verbose. The repeated warnings about not manually updating status and not skipping validation add bulk.

The steps table provides a clear sequence but almost all actual execution details are delegated to external references (recipes, checklists, SDK docs). There are no inline executable commands or concrete code examples — the skill is essentially a routing document. The MCP tools table and URL format rule are concrete, but the core deployment actions lack inline specifics.

The workflow is clearly sequenced with an 8-step table, explicit prerequisite checks (plan exists + validated status + validation proof populated), a pre-deploy checklist gate, error handling step, verification step, and result reporting. The feedback loop for validation failure (stop and invoke azure-validate) is explicit. The validation proof check adds an extra safeguard against bypassed validation.

The skill is well-structured as an overview/routing document with clear one-level-deep references to checklists, recipes, SDK docs, troubleshooting, and post-deployment guides. References are clearly signaled with descriptive link text and organized into logical sections (Steps references, SDK Quick References, MCP Tools, References).