CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-local-multi-rack

Plan, deploy, operate, and troubleshoot multi-rack (rack scale) deployments of Azure Local — preintegrated racks scaling to hundreds of machines, built on Network Fabric Controller, Cluster Manager, SAN storage, and managed network fabric. Use for the Microsoft.NetworkCloud and Microsoft.ManagedNetworkFabric control plane. NOT for standard 1-16 node Azure Local, and NOT for rack-aware clusters (two racks as availability zones, up to 8 nodes, synchronous replication) — those are standard scale. WHEN: multi-rack, rack scale Azure Local, aggregation rack, compute rack, Network Fabric Controller, NFC, Cluster Manager, network fabric, isolation domain, az networkcloud, az networkfabric, multi-rack logical network, multi-rack Arc VM.

72

Quality

90%

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-local-multi-rack in microsoft/GitHub-Copilot-for-Azure

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-organized overview skill body that is concise and actionable with embedded validation checkpoints. Its main weakness is progressive disclosure: the majority of the workflow links it points to are dead paths, and one reference file is orphaned.

Suggestions

Bundle the four referenced workflow files (workflows/plan-and-deploy, workload-management, networking, operate-and-monitor) or remove/rewrite the links so every path in the body resolves to a real file.

Link references/resource-types.md from the body (e.g., from the Quick Reference or Workflow section) so it is discoverable, or remove it from the bundle.

Surface at least one concrete example command inline (e.g., a read-only az networkcloud show/list invocation) to lift actionability from mostly-executable to fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is a lean overview that assumes Claude's competence: no basic-concept explanations, compact tables, and tight routing prose. The only mild repetition ("When to Use" restating trigger terms) reinforces rather than pads.

5 / 5

Actionability

Concrete, actionable specifics are given (CLI extensions az networkcloud/networkfabric/stack-hci-vm, named MCP tools with caveats, explicit routing to workflow files), but the actual executable commands live in the referenced workflow files rather than inline.

4 / 5

Workflow Clarity

A clear 5-step numbered workflow opens with a scale-confirmation validation checkpoint (step 1) and embeds explicit safety checkpoints ("Start read-only", "Ask before fabric changes...") plus an Error Handling table; minor gap is that the detailed feedback loops live in workflow files that are not bundled.

4 / 5

Progressive Disclosure

Structure is good with clearly signaled one-level-deep links and all three references/ files present, but four referenced workflow paths (workflows/plan-and-deploy, workload-management, networking, operate-and-monitor) do not exist in the bundle, and references/resource-types.md is never linked from the body.

3 / 5

Total

16

/

20

Passed

Description

100%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 dense, well-constructed description that covers what, when, and boundary cases with concrete trigger terms and synonyms. It is long but every clause earns its place; no padding or over-claims detected.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Plan, deploy, operate, and troubleshoot") and names the specific building blocks (NFC, Cluster Manager, SAN, managed network fabric), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what ("Plan, deploy, operate, and troubleshoot multi-rack... deployments") and when ("Use for..." plus a WHEN trigger list), and adds negative boundary guidance, matching the top anchor.

5 / 5

Trigger Term Quality

The explicit "WHEN:" clause packs in natural operator terms with synonyms ("Network Fabric Controller" / "NFC", "az networkcloud" / "az networkfabric") and concrete resource concepts (aggregation rack, isolation domain, multi-rack Arc VM).

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (rack-scale multi-rack) and explicitly disambiguates from the adjacent standard Azure Local and rack-aware cases via "NOT for..." clauses, minimizing wrong-skill triggering.

5 / 5

Total

20

/

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: 4 missing, 4 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
microsoft/azure-skills
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.