CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-mgmt-arizeaiobservabilityeval-dotnet

Azure Resource Manager SDK for Arize AI Observability and Evaluation (.NET).

43

Quality

44%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-mgmt-arizeaiobservabilityeval-dotnet/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%Scale 1-5

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

This skill provides excellent actionable code examples for Azure ARM SDK operations with Arize AI resources, covering all CRUD operations with complete, executable C# code. However, it suffers from being a monolithic document that inlines reference material (type tables, enums) that should be in separate files, lacks validation checkpoints for destructive operations like delete, and includes some unnecessary content like the tautological 'When to Use' section and explanations of concepts Claude already knows.

Suggestions

Add explicit validation steps after create and delete operations (e.g., check provisioning state after creation, verify deletion completed successfully) to create proper feedback loops for these long-running operations.

Move the Key Types table, Enums table, and Package Info table into a separate REFERENCE.md file, keeping only the most essential types mentioned inline.

Remove the 'When to Use' section (adds no value) and trim the Best Practices section to only include SDK-specific guidance that Claude wouldn't already know.

Add a verification step after the create workflow, such as checking `organization.Data.Properties?.ProvisioningState` equals `Succeeded` before proceeding.

DimensionReasoningScore

Conciseness

The content is reasonably efficient but includes some unnecessary elements: the Package Info table repeats information Claude would rarely need, the 'When to Use' section is a meaningless tautology, and the Best Practices section states things Claude already knows (async/await, using statements, retry policies). The enum tables and key types table add bulk that could be trimmed or moved to a reference file.

3 / 5

Actionability

The skill provides fully executable, copy-paste ready C# code examples covering all CRUD operations (create, read, update, delete, list), authentication setup, error handling, and direct resource access. The code is complete with proper imports and realistic property values.

5 / 5

Workflow Clarity

The CRUD operations are clearly sequenced and individually well-documented, but there are no validation checkpoints. The create operation is a long-running/destructive operation with no verification step after creation (e.g., checking provisioning state). The delete operation has no confirmation or validation step. Per rubric guidelines, missing validation for destructive operations caps this at 3.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no bundle files. The enum tables, key types reference table, and detailed API examples (170+ lines) would benefit from being split into separate reference files. The Links section points to external resources but there's no internal content organization across files.

2 / 5

Total

13

/

20

Passed

Description

27%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.

This description is essentially a technology label rather than a functional skill description. It names the domain and tech stack (Azure Resource Manager SDK, Arize AI, .NET) but fails to describe any concrete actions or provide trigger guidance for when Claude should select it. The description needs significant expansion to be useful for skill selection among multiple available skills.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Deploys and manages Arize AI observability resources in Azure, configures evaluation pipelines, provisions monitoring workspaces.'

Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user needs to deploy Arize AI resources on Azure, configure ARM templates for observability, or manage .NET SDK integrations for AI monitoring.'

Include natural user-facing keywords and synonyms such as 'deploy', 'provision', 'ARM template', 'monitoring', 'tracing', 'LLM observability' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (Azure Resource Manager SDK, Arize AI Observability and Evaluation, .NET) but provides no concrete actions. It identifies the technology stack but doesn't describe what the skill actually does—no verbs or operations are mentioned.

2 / 5

Completeness

The description only vaguely identifies the domain ('what') without any concrete actions, and completely lacks a 'when' clause. There is no guidance on when Claude should select this skill, and the 'what' is essentially just a technology label rather than a description of capabilities.

1 / 5

Trigger Term Quality

Includes some relevant keywords like 'Azure Resource Manager', 'Arize AI', 'Observability', 'Evaluation', and '.NET', which are terms a user might mention. However, it lacks natural phrases users would say (e.g., 'deploy', 'monitor', 'trace', 'ARM template') and common synonyms or abbreviations like 'ARM SDK'.

3 / 5

Distinctiveness Conflict Risk

The combination of Azure Resource Manager + Arize AI + .NET is fairly specific and narrows the niche, but without concrete actions described, it could overlap with other Azure SDK skills or Arize AI skills. The technology stack combination provides some distinctiveness.

3 / 5

Total

9

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.