CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-compute

Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, can't connect / RDP / SSH, refused, black screen, reset password, reach VM, port 3389, NSG, security, Linux, troubleshoot, troubleshooting, connectivity, capacity reservation (CRG), reserve, guarantee capacity, pre-provision, CRG association, CRG disassociation, machine enrollment (EMM), Essential Machine Management, monitor. PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents — use compute_vm_list-skus / compute_vm_list-images / compute_vm_check-quota.

72

Quality

87%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 router skill that efficiently directs Azure compute intents to the appropriate workflow files. Its strengths are excellent organization, clear routing logic with a visual decision tree, and appropriate progressive disclosure. The only minor weakness is that as a pure router it contains no directly executable commands or code, though this is largely appropriate for its purpose.

DimensionReasoningScore

Conciseness

The skill is lean and efficient. It avoids explaining what VMs, VMSS, or Azure are. Every section serves a clear routing purpose with no filler or redundant explanation.

3 / 3

Actionability

The skill provides clear routing logic and a disambiguation rule, but it contains no executable code, CLI commands, or concrete examples of what to do once routed. It relies entirely on downstream workflow files for actionable guidance, which is appropriate for a router skill but means the skill itself is more directional than executable.

2 / 3

Workflow Clarity

The routing tree is unambiguous with a clear decision structure covering all expected intents, including an 'Unclear' fallback. The routing rule ('read the matched workflow file before any reference file') provides explicit sequencing. For a router skill, this is a well-defined workflow.

3 / 3

Progressive Disclosure

The skill is a concise overview that cleanly delegates to five one-level-deep workflow files via a well-organized table with clear file paths and 'use when' descriptions. Navigation is straightforward and references are clearly signaled.

3 / 3

Total

11

/

12

Passed

Description

89%

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 description excels at trigger term coverage and completeness, providing an extensive WHEN clause and even a disambiguation directive against a competing skill. Its main weakness is that the capabilities are presented as a keyword dump rather than clearly structured concrete actions, which slightly reduces readability and specificity. Overall, it is a strong functional description well-suited for skill selection among many options.

Suggestions

Restructure the capability keywords into clearer action phrases (e.g., 'Provisions and deploys Azure VMs and VMSS, recommends VM sizes, compares pricing, troubleshoots connectivity issues including RDP/SSH/NSG') rather than a flat keyword list to improve specificity and readability.

DimensionReasoningScore

Specificity

The description names the domain (Azure VM/VMSS) and lists some actions like 'create/provision/deploy', 'recommend VM size', 'compare VM pricing', 'troubleshoot connectivity', but these are mostly keyword dumps rather than clearly articulated concrete actions. It's more specific than vague but not as structured as listing multiple distinct concrete capabilities.

2 / 3

Completeness

The description clearly answers both 'what' (Azure VM/VMSS routing for creation, sizing, pricing, troubleshooting, capacity reservation, monitoring) and 'when' with an explicit WHEN clause listing extensive trigger scenarios. It also includes a PREFER OVER clause for disambiguation, which strengthens the 'when' guidance.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'create VM', 'spin-up VM', 'GPU', 'machine learning', 'can't connect', 'RDP', 'SSH', 'black screen', 'reset password', 'port 3389', 'NSG', 'autoscale', 'scale set', 'dev/test', 'cost estimate'. These are highly natural phrases users would actually type when needing Azure VM help.

3 / 3

Distinctiveness Conflict Risk

The description is clearly scoped to Azure VM/VMSS with very specific triggers like 'VMSS', 'scale set', 'port 3389', 'NSG', 'CRG', 'EMM'. It even explicitly disambiguates from a competing skill (mcp__azure__get_azure_bestpractices) with a PREFER OVER clause, reducing conflict risk significantly.

3 / 3

Total

11

/

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
microsoft/github-copilot-for-azure
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.