CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-mgmt-weightsandbiases-dotnet

Azure Weights & Biases SDK for .NET. ML experiment tracking and model management via Azure Marketplace. Use for creating W&B instances, managing SSO, marketplace integration, and ML observability.

57

Quality

66%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-mgmt-weightsandbiases-dotnet/SKILL.md

The canonical home for this skill is azure-mgmt-weightsandbiases-dotnet in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

The skill provides solid, executable C# code examples covering the main CRUD operations for Azure W&B instances, which is its primary strength. However, it suffers from significant verbosity with generic Azure advice, tangential content (Python SDK integration, Related SDKs), and tables that pad the token count. The lack of validation checkpoints in destructive/long-running operations and the monolithic structure without supporting bundle files are notable weaknesses.

Suggestions

Remove generic Azure best practices Claude already knows (DefaultAzureCredential, tagging, monitoring) and the tangential Python W&B SDK section to reduce token count by ~30%.

Add explicit provisioning state validation after CreateOrUpdateAsync (poll until Succeeded/Failed) and a confirmation check before DeleteAsync to improve workflow safety.

Extract the Key Types Reference table, Available Regions table, and Marketplace Offer Details into a separate REFERENCE.md bundle file to improve progressive disclosure.

Remove the 'When to Use' boilerplate sentence at the end—it adds no value.

DimensionReasoningScore

Conciseness

The skill is noticeably verbose. The 'Best Practices' section contains generic Azure advice Claude already knows (e.g., 'Use DefaultAzureCredential', 'Tag resources'). The 'Related SDKs' section, 'When to Use' boilerplate, the Available Regions table, and the Marketplace Offer Details table add bulk without much value. The Resource Hierarchy diagram and Key Types Reference table are borderline useful but could be trimmed. The Python W&B SDK integration section is tangential to a .NET Azure Resource Manager skill.

2 / 5

Actionability

The code examples are concrete, executable C# with proper using statements, realistic property values, and complete workflows for CRUD operations. Minor gaps include the name availability check using a try/catch workaround rather than a proper API call, and the SSO update pattern of mutating instance.Data directly which may not be the correct pattern. Overall, the examples are copy-paste ready.

4 / 5

Workflow Clarity

The workflows are clearly sequenced as numbered sections (Create, Get, List, SSO, Update, Delete). However, the Create workflow—a long-running operation deploying a marketplace resource—lacks validation checkpoints. There's no guidance on checking provisioning state after creation, no retry logic for failed deployments, and the Delete operation (destructive) has no confirmation or validation step. The 'Best Practices' mentions checking provisioning state but doesn't integrate it into the workflow.

3 / 5

Progressive Disclosure

The skill is a monolithic ~250-line file with no bundle files. The Key Types Reference, Available Regions table, and detailed code examples for 7 workflows could be split into separate reference files. Everything is inlined with no structure beyond flat sections. Reference links are provided but no actual bundle files support progressive disclosure.

2 / 5

Total

11

/

20

Passed

Description

87%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 is a well-crafted description that clearly identifies a narrow technical niche (Azure W&B SDK for .NET) with specific actions and explicit 'Use for' guidance. It has strong trigger terms and minimal conflict risk. Minor improvements could include additional natural language synonyms like 'wandb' and more detail on specific SDK operations.

DimensionReasoningScore

Specificity

Lists several specific actions: creating W&B instances, managing SSO, marketplace integration, and ML observability. These are concrete but could be more detailed about what each action entails.

4 / 5

Completeness

Clearly answers both 'what' (ML experiment tracking and model management via Azure Marketplace) and 'when' ('Use for creating W&B instances, managing SSO, marketplace integration, and ML observability') with explicit trigger phrases.

5 / 5

Trigger Term Quality

Good coverage with terms like 'Azure', 'Weights & Biases', 'W&B', '.NET', 'SDK', 'ML experiment tracking', 'SSO', 'marketplace'. Missing some natural variations like 'wandb', 'model logging', or 'experiment logging'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive niche combining Azure, Weights & Biases, .NET SDK, and marketplace integration. Very unlikely to conflict with other skills given this specific combination of technologies.

5 / 5

Total

18

/

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.