azure-ai-ml-py

Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.

1.06x

Quality

70%

Does it follow best practices?

Impact

100%

1.06x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-azure-ai-ml-py/SKILL.md

Quality

Discovery

75%

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 concise and clearly scoped to Azure ML SDK v2, with an explicit 'Use for' clause that aids skill selection. Its main weakness is listing resource nouns rather than concrete actions (e.g., 'create workspaces', 'submit training jobs', 'deploy models'), and it misses common user-facing trigger terms like 'AzureML' or 'AML'. Overall it is functional but could be more actionable and keyword-rich.

Suggestions

Replace noun-only list with concrete actions: e.g., 'Create and manage ML workspaces, submit training jobs, register and deploy models, manage datasets and compute resources, build ML pipelines.'

Add common trigger term variations such as 'AzureML', 'AML', 'azure-ai-ml', 'train model on Azure', 'deploy model to Azure' to improve matching against natural user queries.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure Machine Learning SDK v2) and lists several resource types (workspaces, jobs, models, datasets, compute, pipelines), but these are nouns/concepts rather than concrete actions like 'create', 'deploy', 'train', or 'monitor'.	2 / 3
Completeness	Clearly answers both 'what' (Azure Machine Learning SDK v2 for Python) and 'when' ('Use for ML workspaces, jobs, models, datasets, compute, and pipelines') with an explicit 'Use for...' clause that provides trigger guidance.	3 / 3
Trigger Term Quality	Includes relevant keywords like 'Azure Machine Learning', 'SDK v2', 'ML', 'workspaces', 'jobs', 'models', 'datasets', 'compute', 'pipelines' — but misses common user variations like 'AzureML', 'AML', 'train a model', 'deploy model', 'ml.azure.com', or 'azure-ai-ml'.	2 / 3
Distinctiveness Conflict Risk	The description is highly specific to Azure Machine Learning SDK v2 for Python, which is a distinct niche unlikely to conflict with generic ML skills, other cloud provider skills, or general Python skills.	3 / 3
	Total	10 / 12 Passed

Implementation

64%

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

This is a solid API reference skill with excellent actionability—nearly every section has complete, executable Python code. However, it reads more like a flat reference card than a workflow-oriented skill, lacking sequenced multi-step guidance and validation checkpoints. The content could be tightened by removing the generic best practices, the vacuous 'When to Use' section, and splitting detailed subsections into linked reference files.

Suggestions

Add a 'Typical Workflow' section at the top showing the recommended sequence: authenticate → provision compute → register data → submit job → stream logs → register model, with validation checkpoints (e.g., verify compute is running before submitting a job).

Remove the 'Best Practices' section (generic advice Claude already knows) and the meaningless 'When to Use' section to improve conciseness.

Define or explain the undefined pipeline components (prep_component, train_component) in the pipeline example, or add a note about how to create components, so the example is truly executable.

Consider splitting into a concise SKILL.md overview with quick-start auth + command job, and a separate REFERENCE.md for the full API surface (data, compute, environments, datastores, models).

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with executable code examples, but includes some unnecessary elements like the 'Best Practices' section with generic advice Claude already knows (e.g., 'use versioning', 'tag resources'), and the 'When to Use' section is a meaningless tautology. The operations table is useful but some code blocks are repetitive in pattern.	2 / 3
Actionability	Nearly all guidance is concrete and executable with copy-paste ready Python code. Authentication, workspace creation, data registration, compute setup, job submission, and pipeline creation all have complete, runnable examples with proper imports.	3 / 3
Workflow Clarity	Individual operations are clear, but there's no explicit end-to-end workflow showing the typical sequence (authenticate → create compute → register data → submit job → monitor → register model). The pipeline example references undefined components (prep_component, train_component) without explanation. No validation or error handling steps are shown for operations that could fail (e.g., checking if compute exists before creating).	2 / 3
Progressive Disclosure	The content is well-structured with clear section headers and a useful operations summary table, but it's a long monolithic file (~200 lines of code examples) that could benefit from splitting detailed sections (pipelines, environments, datastores) into separate reference files. No external references are provided for advanced topics.	2 / 3
	Total	9 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: boisenoise/skills-collections
Commit: f1697b6

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.