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.

64

Quality

76%

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/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

65%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.

The content is highly actionable with executable code covering all core Azure W&B management workflows, but it is a long monolithic document that inlines reference material better suited to separate files and lacks explicit validation checkpoints for its destructive resource operations, capping workflow clarity. Conciseness and progressive disclosure are middling due to the inlined bulk and absence of file-based structure.

Suggestions

Add explicit validation checkpoints to the destructive workflows — e.g. confirm provisioning state reaches 'Succeeded' after Create and prompt for confirmation before Delete — to lift workflow_clarity above the destructive-operation cap of 3.

Move the Key Types Reference, Available Regions, Marketplace Offer Details, and Reference Links tables into separate reference files (e.g. REFERENCE.md, REGIONS.md) and link to them from the body to improve progressive_disclosure and reduce inline bulk.

Trim the generic boilerplate 'When to Use' line ('This skill is applicable to execute the workflow or actions described in the overview.') and tighten any redundant prose to improve conciseness.

DimensionReasoningScore

Conciseness

The body is mostly efficient reference material (code and tables) without explaining concepts Claude already knows, but it is a long monolithic document that inlines bulk content (Key Types Reference, Available Regions, Marketplace Offer Details, Reference Links) that could be tightened or split, plus a generic boilerplate 'When to Use' line; this matches the score-3 anchor of mostly efficient with some unnecessary/could-be-tightened material, not score-4 because the inlined bulk and boilerplate are more than minor.

3 / 5

Actionability

Provides fully executable, copy-paste-ready C# code across create, get, list, SSO, update, delete, and name-availability workflows plus error handling and Python integration, covering the common cases specifically; this matches the score-5 anchor despite the small 'Implement via direct ARM call if SDK doesn't expose this' hint, which is a negligible gap rather than the minor gaps of score-4.

5 / 5

Workflow Clarity

The seven numbered Core Workflows are clearly sequenced with code, but the skill performs destructive Azure resource operations (create/delete instances) and the workflows lack explicit validation checkpoints and feedback loops — the delete workflow has no confirmation/check and provisioning-state validation is only mentioned in Best Practices rather than inline; per the rubric's destructive-operations cap, workflow_clarity cannot exceed 3, matching the score-3 anchor of steps present but validation gaps.

3 / 5

Progressive Disclosure

The SKILL.md has clear section headers and is navigable, but it is monolithic with no bundle files and no references to separate files, while content that clearly belongs in separate files (Key Types Reference, Available Regions, Reference Links) is inlined; this sits between the score-2 anchor (minimal structure, inlined content) and score-4 (good split with clear references), closer to score-3 because the section organization is genuinely good even though no external references exist.

3 / 5

Total

14

/

20

Passed

Description

87%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.

The description is specific, uses third person, and explicitly answers both what the skill does and when to use it with concrete trigger phrases, achieving strong completeness and distinctiveness. Minor gaps in concrete action coverage and synonym variants keep specificity and trigger_term_quality just below the top anchor.

DimensionReasoningScore

Specificity

Lists several specific concrete actions — 'creating W&B instances, managing SSO, marketplace integration, and ML observability' — comparable to the score-4 example of several specific actions with minor gaps; 'marketplace integration' and 'ML observability' are slightly less concrete than the fully comprehensive score-5 anchor.

4 / 5

Completeness

Clearly answers 'what' ('Azure Weights & Biases SDK for .NET. ML experiment tracking and model management via Azure Marketplace') AND explicitly answers 'when' with concrete trigger phrases ('Use for creating W&B instances, managing SSO, marketplace integration, and ML observability'), matching the score-5 anchor; it is not the score-4 anchor because the 'when' is explicit and concrete rather than weakly specified.

5 / 5

Trigger Term Quality

Includes natural domain terms a user would say — 'Weights & Biases', 'W&B instances', 'SSO', 'ML experiment tracking', 'Azure Marketplace' — giving good keyword coverage, but misses common synonyms/variants (e.g. lowercase 'wandb', '.NET' alternates), so it sits at the score-4 anchor rather than comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche ('Azure Weights & Biases SDK for .NET' via Azure Marketplace) with distinct triggers and minimal conflict risk, matching the score-5 clear-niche anchor; not the score-4 anchor because the overlap risk with other skills is negligible rather than 'minor'.

5 / 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.