CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-prepare

**WORKFLOW SKILL** — Prepare Azure apps for deployment (Bicep/Terraform, azure.yaml, Dockerfiles). WHEN: "create app", "build web app", "create API", "deploy to Azure", "generate Bicep", "generate Terraform", "function app", "add authentication", "managed identity". DO NOT USE FOR: cross-cloud migration (azure-cloud-migrate), executing deploys (azure-deploy), preflight (azure-validate).

70

Quality

85%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

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 an excellent skill description that follows best practices across all dimensions. It uses a structured format (WORKFLOW SKILL label, WHEN triggers, DO NOT USE FOR boundaries) that makes it highly parseable and unambiguous. The explicit delineation from related skills (azure-cloud-migrate, azure-deploy, azure-validate) is particularly strong for avoiding conflicts in a multi-skill environment.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: prepare Azure apps for deployment, generate Bicep/Terraform, create azure.yaml, create Dockerfiles, add authentication, managed identity. These are concrete, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (prepare Azure apps for deployment with Bicep/Terraform, azure.yaml, Dockerfiles) and 'when' (explicit WHEN clause with trigger phrases). Also includes a 'DO NOT USE FOR' clause that further clarifies boundaries, which is excellent for disambiguation.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'create app', 'build web app', 'create API', 'deploy to Azure', 'generate Bicep', 'generate Terraform', 'function app', 'add authentication', 'managed identity'. These are realistic user phrases.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause, naming specific sibling skills (azure-cloud-migrate, azure-deploy, azure-validate) to avoid conflicts. The niche of Azure deployment preparation is clearly carved out from execution, migration, and validation.

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 workflow skill with excellent progressive disclosure and clear sequencing through planning, approval, execution, and validation phases. Its main weakness is the lack of concrete, executable examples inline — nearly all actionable detail is deferred to reference files. There is also moderate redundancy where the plan-first workflow and Step 0 routing are described multiple times.

Suggestions

Add a brief concrete example of what a minimal plan.md looks like inline (even 10-15 lines) so the skill is actionable without loading references/plan-template.md

Consolidate the plan-first workflow — it appears in Rules, the dedicated PLAN-FIRST WORKFLOW section, and the Steps summary; merge into one authoritative location and reference it from the others

DimensionReasoningScore

Conciseness

The skill is mostly efficient but has some redundancy — the plan-first workflow is stated in Rules (#1, #2) and then repeated in the dedicated PLAN-FIRST WORKFLOW section and again in the Steps section. The specialized technology check is also described twice (Step 0 section and Steps summary). Some tightening is possible.

2 / 3

Actionability

The skill provides clear procedural guidance (plan location, approval gates, handoff sequence) but lacks concrete executable examples — no sample plan.md content, no example Bicep/Terraform snippets, no example azure.yaml. Most actionable detail is deferred to references that aren't provided, making the skill itself more of a routing document than a hands-on guide.

2 / 3

Workflow Clarity

The workflow is clearly sequenced with explicit phases, a mandatory approval gate between planning and execution, validation before deployment, and a clear handoff chain (prepare → validate → deploy). The plan-first mandate with blocking gates and progressive status updates provides strong validation checkpoints and error prevention.

3 / 3

Progressive Disclosure

Excellent progressive disclosure structure — the SKILL.md serves as a clear overview with a well-organized reference index table pointing to one-level-deep references. Topics are logically grouped by phase, references are clearly signaled with relative paths, and the content appropriately splits detailed guidance into separate 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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
jonathan-vella/azure-agentic-infraops
Reviewed

Table of Contents

Is this your skill?

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.