CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-app-onboard

End-to-end orchestrator: from a business idea, app idea, or existing app to running Azure deployment with cost estimates and pre-deploy approval. Analyzes your app, auto-detects the right Azure services, scaffolds infrastructure code, and deploys — tailored to your app, not a template. Handles moving existing apps to Azure without rewriting or with minimal changes. WHEN: bring your app to Azure, plan my app, cost to run, is my code ready to deploy, deploy my app to the cloud, deploy all my services, what Azure services do I need, plan my Azure deployment, deploy my new app to Azure, one-click deploy, I have an app and want it on Azure, migrate my app to Azure, help me get started, build an app, no code yet, starter project. DO NOT USE FOR: use azd for deployment(use azure-deploy), optimizing existing costs (use cost-optimization), code readiness checks only (use azure-app-onboard-prereq).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is azure-app-onboard in microsoft/GitHub-Copilot-for-Azure

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-orchestrated body: the 10-step pipeline table with mandatory per-step references, double approval gates, and halt conditions gives excellent workflow clarity, and tables keep it token-efficient. The main defects are repeated warnings that could be consolidated and workflow-table links to phase files that do not exist in the provided bundle.

Suggestions

Consolidate the 'NEVER invoke azure-deploy' warning and the deploy-recovery blockquote into a single authoritative note (e.g., in the Workflow section or pipeline-rules.md) instead of repeating it in the table note, Step 8, and the deploy-recovery paragraph.

Ensure prepare/PHASE.md, scaffold/PHASE.md, and deploy/PHASE.md actually exist at the linked relative paths (or fix the paths), since three of ten steps currently point to unresolvable files.

Reduce the length of the two blockquote transition notes in the Workflow section by moving their procedural detail (context.json field updates, gate prompt wording) into approval-gates.md, keeping only the directive in SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no explanations of concepts Claude already knows, but the 'NEVER invoke {"skill": "azure-deploy"}' warning and PHASE.md read mandates are repeated two to three times across the Workflow notes and Step 8, and the two long blockquote notes in the Workflow section restate table content. Minor trimming would earn the lean anchor.

4 / 5

Actionability

Guidance is concrete for an orchestrator skill: named artifacts per phase ('prereq-output.json', 'prepare-plan.json', 'scaffold-manifest.json', 'deploy-result.json'), explicit halt conditions ('overallHealth: "blocked" OR routeToSkill set'), state checks ('completedPhases: [...,"scaffold"]' + 'currentPhase: "deploy"'), and the exact gate prompt text. Minor gaps remain because executable detail (commands, schemas) is deferred to references.

4 / 5

Workflow Clarity

A 10-step sequenced table where every step names its action and mandatory reference, with two explicit approval gates (Steps 6 and 8), a halt condition on prereq failure, a health-check after deploy, and an error-handling table with a user-driven retry/skip/abort feedback loop — matching the strongest anchor including validation checkpoints and error recovery.

5 / 5

Progressive Disclosure

Good structure: SKILL.md is an overview with clearly signaled, one-level-deep MUST-read references per step, and detail is appropriately split out (all 11 references/ files are real and reachable directly or via one hop). However, three of the ten workflow steps link to 'prepare/PHASE.md', 'scaffold/PHASE.md', and 'deploy/PHASE.md', which are not present in the shipped bundle, leaving unresolvable core paths — more than the 'minor organization gaps' of the top anchor.

4 / 5

Total

17

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly covers what, when, and when-not with an unusually rich set of natural trigger phrases and explicit sibling-skill disambiguation. The only deductions are second-person voice in the capability prose and a few overly generic greenfield triggers that create mild conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Analyzes your app, auto-detects the right Azure services, scaffolds infrastructure code, and deploys' plus 'cost estimates and pre-deploy approval' and migration handling — which meets the comprehensive anchor. However, the capability prose addresses the user in second person ('Analyzes your app', 'tailored to your app'), which the judging guidelines penalize by reducing specificity by 1.

4 / 5

Completeness

Clearly answers 'what' (analyze app, auto-detect services, scaffold IaC, deploy with cost estimates and pre-deploy approval, migrate existing apps) and 'when' via an explicit 'WHEN:' clause with concrete trigger phrases, plus a 'DO NOT USE FOR' exclusion clause — the strongest anchor.

5 / 5

Trigger Term Quality

The 'WHEN:' clause enumerates 16 natural user phrases with strong synonym coverage — 'deploy my app to the cloud', 'migrate my app to Azure', 'what Azure services do I need', 'cost to run', 'no code yet', 'starter project', 'one-click deploy' — spanning greenfield, existing-app, and cost-planning intents, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

'DO NOT USE FOR: ... (use azure-deploy) ... (use cost-optimization) ... (use azure-app-onboard-prereq)' explicitly disambiguates the closest sibling skills, and Azure-specific triggers are distinct. But broad greenfield triggers like 'build an app', 'help me get started', and 'no code yet' could fire in non-Azure contexts, leaving minor overlap risk — the 'mostly distinct' anchor rather than 'minimal conflict risk'.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

microsoft/azure-skills

Path

.github/plugins/azure-skills/skills/azure-app-onboard/SKILL.md

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.