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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-ml-py/SKILL.md

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 a lean, highly actionable code reference with good in-file organization, but it functions as a flat catalog rather than a guided workflow and lacks the validation checkpoints required for destructive/batch operations. It also misses progressive-disclosure opportunities to split bulk reference material into separate files.

Suggestions

Add validation/feedback loops around destructive and batch operations, e.g., after 'begin_create(...).result()' check the provisioned state, and after job submission confirm terminal status before declaring success.

Move the bulk API reference (the MLClient operations table and per-resource snippets) into a separate references/ file, leaving SKILL.md as a concise overview that links one level deep.

Close the small actionability gaps: include 'import os' before 'os.environ[...]' and provide a concrete definition or import for the pipeline example's 'prep_component'/'train_component'.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely lean, copy-paste-ready code with minimal prose and no over-explanation of concepts Claude already knows; the only padding is the vague closing line 'This skill is applicable to execute the workflow or actions described in the overview.'	4 / 5
Actionability	Provides concrete, executable Python snippets for each resource type plus a concise MLClient operations table; minor gaps (missing 'import os' in the auth snippet, undefined 'prep_component'/'train_component' in the pipeline example) keep it just below fully copy-paste-ready.	4 / 5
Workflow Clarity	Operations are presented as a flat reference catalog with no sequenced multi-step workflow and no validation checkpoints or feedback loops; because the skill includes destructive/batch operations (begin_create, create_or_update, delete, job submission) without verification steps, workflow clarity is capped at 3 per the rubric.	3 / 5
Progressive Disclosure	Section headers are clear and logically grouped, but the skill is a monolithic 265-line single-file reference with no bundle files and no progressive disclosure to separate reference documents; API-reference-style content that could live in deeper files is all inlined.	3 / 5
	Total	14 / 20 Passed

Description

75%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 clear, specific, and well-scoped to the Azure ML SDK v2 niche with explicit trigger guidance. It is held back from top marks by listing capability nouns rather than action verbs and by trigger phrasing that names tasks instead of user-intent scenarios.

Suggestions

Lead with concrete action verbs (e.g., 'Create and manage ML workspaces, submit and monitor jobs, register models and datasets, scale compute, and build pipelines') rather than listing resource nouns alone.

Reframe the trigger clause around user intent (e.g., 'Use when the user asks to provision Azure ML workspaces, run or monitor training jobs, register models/datasets, or orchestrate ML pipelines').

Add natural synonyms and shorthands users commonly say, such as 'Azure ML', 'AML', 'training job', and 'endpoint', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure Machine Learning SDK v2 for Python') and lists six concrete resource areas ('ML workspaces, jobs, models, datasets, compute, and pipelines'), but these are resource nouns rather than explicit action verbs, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Clearly states the 'what' ('Azure Machine Learning SDK v2 for Python') and gives explicit 'Use for...' trigger guidance, but the 'when' lists capability areas rather than concrete user-intent trigger phrases ('Use when the user mentions...').	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('Azure Machine Learning', 'ML', 'workspaces', 'jobs', 'models', 'datasets', 'compute', 'pipelines'), with good keyword coverage but missing common synonyms and file extensions for a top score.	4 / 5
Distinctiveness Conflict Risk	'Azure Machine Learning SDK v2 for Python' carves a clear niche with minimal conflict risk; only minor overlap with generic Azure or ML library skills keeps it just below a top score.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-ml-py/SKILL.md
Commit: 57c135b

Reviewed: 5 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.