azure-ai-ml-py

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-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.

A solid, code-dense SDK cookbook that is largely executable and well-organized by resource type. It loses points for missing validation steps around destructive cloud operations, undefined components in the pipeline example, and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Add validation/verification checkpoints after long-running or destructive calls — e.g., poll 'ml_client.jobs.stream(name)' until completion before registering a model, and confirm 'begin_create_or_update(...).result()' succeeded before downstream steps.

Split bulk reference material into one-level-deep files, e.g. move the MLClient operations table and the pipeline guide into references/operations.md and references/pipelines.md, keeping quick-start code in SKILL.md.

Make the pipeline example fully executable by defining or linking the 'prep_component' and 'train_component' load definitions (e.g., 'load_component(source=...)'), and add 'import os' to the authentication snippet.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient: terse one-line intros, dense copy-paste code blocks, and no explanation of concepts Claude already knows. Minor trimming needed — the boilerplate 'This skill is applicable to execute the workflow or actions described in the overview' and the generic Limitations lines add tokens without information, which keeps it below anchor 5.	4 / 5
Actionability	Concrete, mostly executable code covers installation, authentication, workspaces, data assets, models, compute, command jobs, pipelines, environments, and datastores. Minor gaps: the pipeline example calls 'prep_component' and 'train_component' which are never defined, and the auth snippet uses 'os.environ' without importing os — so not fully copy-paste ready per anchor 5.	4 / 5
Workflow Clarity	Sections are logically sequenced (install → env vars → auth → resources → jobs → pipelines → best practices) but there are no validation or verification checkpoints anywhere (e.g., poll job status, confirm workspace creation). The skill covers destructive/batch cloud operations — the operations table lists 'delete' and 'cancel' — and the rubric caps workflow clarity at 3 in that case.	3 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but it is a monolithic ~270-line cookbook with zero external reference files; content like the full MLClient operations table and the pipeline guide could be split into one-level-deep reference files. Structure is present but everything is inline, matching anchor 3 rather than 4.	3 / 5
	Total	14 / 20 Passed

Description

73%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.

A concise, well-targeted description with an explicit 'Use for' trigger and a clearly distinct Azure ML niche. Its main weakness is that it enumerates resource types rather than concrete actions, and it omits a few natural trigger terms (AML, azure-ai-ml, endpoints).

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure Machine Learning SDK v2 for Python') and six concrete resource areas ('ML workspaces, jobs, models, datasets, compute, and pipelines'), but lists objects rather than actions — no verbs convey what the skill does with them (create, manage, deploy). This matches anchor 3, not 4, because anchor 4 requires several specific actions.	3 / 5
Completeness	It has both a clear 'what' ('Azure Machine Learning SDK v2 for Python') and an explicit trigger clause ('Use for ML workspaces, jobs, models, datasets, compute, and pipelines'), so it is not capped at 3. The 'when' is generic though — no concrete trigger phrases like 'when the user asks to create an ML job or manage compute' — keeping it below anchor 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage: users working in this space would say 'Azure Machine Learning', 'ML', 'jobs', 'pipelines', 'compute', 'datasets'. Missing a few natural terms — the 'AML' abbreviation, the 'azure-ai-ml' package name, and 'endpoints'/'deployments' — so it fits anchor 4 rather than the comprehensive synonym/extension coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers: 'Azure Machine Learning SDK v2 for Python' plus SDK-specific resource names make it unlikely to fire for unrelated skills; 'SDK v2' also distinguishes it from CLI or v1 alternatives. Matches anchor 5.	5 / 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: boisenoise/skills-collections
Path: skills/antigravity-azure-ai-ml-py/SKILL.md
Commit: 7390864

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.