Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
Install with Tessl CLI
npx tessl i github:microsoft/azure-skills --skill azure-deploy90
Quality
85%
Does it follow best practices?
Impact
98%
1.96xAverage score across 3 eval scenarios
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 actions, comprehensive trigger terms covering both technical commands and casual phrases like 'ship it' and 'go live', and explicitly addresses both when to use and when NOT to use the skill. The clear disambiguation from azure-prepare makes it highly distinctive and unlikely to cause skill selection conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery' and specifies prerequisites like '.azure/plan.md' and 'validated status from azure-validate'. | 3 / 3 |
Completeness | Clearly answers both what (execute Azure deployments, run specific commands) AND when (explicit 'WHEN:' clause with trigger phrases), plus includes explicit 'DO NOT USE WHEN:' guidance for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'run azd up', 'run azd deploy', 'push to production', 'push to cloud', 'go live', 'ship it', 'bicep deploy', 'terraform apply', 'publish to Azure', 'launch on Azure'. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally clear niche with explicit boundary conditions distinguishing it from azure-prepare. The 'DO NOT use this skill when' and 'DO NOT USE WHEN' clauses directly address potential conflicts with the preparation skill. | 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 skill has strong workflow clarity and progressive disclosure, with a well-organized structure that appropriately delegates details to reference files. However, it suffers from redundant warning boxes that repeat prerequisite information multiple times, and lacks any inline executable examples - relying entirely on external references for actionable guidance.
Suggestions
Consolidate the three prerequisite warning boxes into a single, concise prerequisite section to reduce token usage
Add at least one inline example of a common deployment command (e.g., `azd up` with typical flags) so the skill is actionable without requiring navigation to external files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy with multiple warning boxes repeating the same prerequisite information (azure-validate must run first). The core workflow is reasonably efficient, but the repeated warnings and emphasis boxes add unnecessary tokens. | 2 / 3 |
Actionability | The skill provides a clear step table but delegates all concrete execution details to external references (recipes, checklists). No executable commands or code examples are shown inline - everything requires following links to other files. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with explicit validation checkpoints (check plan status, verify Validation Proof section, pre-deploy checklist). The prerequisite chain (azure-prepare → azure-validate → azure-deploy) is unambiguous with explicit stop conditions and error recovery references. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and well-signaled one-level-deep references. The step table points to specific reference files, SDK references are organized by language, and MCP tools are clearly listed. Navigation is straightforward. | 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.
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.