azure-ai-ml-py

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

Quality

61%

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/azure-ai-ml-py/SKILL.md

Quality

Content

62%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 an efficient, actionable reference for the Azure ML SDK v2 with executable snippets and a useful operations table, but it lacks validation checkpoints for destructive/batch operations and inlines a broad API surface with no progressive disclosure to supporting files.

Suggestions

Add explicit validation/verification steps after long-running or destructive calls (e.g., check `returned_job.status` or poll until terminal state, verify a workspace exists before creating resources).

Move the bulk API reference into one-level-deep reference files (e.g., jobs.md, compute.md) and have SKILL.md point to them, keeping only a quick-start and the operations table inline.

Complete the authentication snippet (add `import os`) and show a minimal job-monitoring loop with status checking so examples run as-is.

Dimension	Reasoning	Score
Conciseness	The body is largely lean reference material with executable snippets and a compact operations table; it avoids explaining concepts Claude already knows, with only minor padding such as the redundant 'Client library for managing...' line and a few bare comments.	4 / 5
Actionability	It provides copy-paste-ready Python snippets for the main operations plus an operations table mapping properties to methods, with only minor gaps (e.g., `import os` omitted in the auth example, no error handling shown).	4 / 5
Workflow Clarity	Operations are organized by resource type with clear code, but multi-step and potentially destructive workflows (workspace creation, compute provisioning, job submission) lack explicit validation checkpoints or verify-after-run steps, which caps this dimension at 3 per the destructive/batch-operation guidance.	3 / 5
Progressive Disclosure	Content is well-sectioned into resource categories, but the entire API reference surface is inlined in one file with no external reference files, and no bundle files are provided, so the structure could be better split for a skill of this breadth.	3 / 5
	Total	14 / 20 Passed

Description

60%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 and well-targeted to the Azure ML SDK v2 niche with good natural trigger terms, but the 'when' guidance is a scope assertion rather than concrete user-facing trigger phrases, which caps completeness.

Suggestions

Add a concrete 'Use when...' clause with user-facing trigger phrases such as 'Use when the user asks to create Azure ML jobs, register models, or manage compute clusters'.

Express capabilities as concrete actions (e.g., 'Create and monitor training jobs, register models and datasets, manage compute clusters, build pipelines') rather than only naming resource types.

Dimension	Reasoning	Score
Specificity	The description names the domain and lists several concrete resource types (workspaces, jobs, models, datasets, compute, pipelines), but each is a noun rather than a discrete action verb, so coverage is broad but not fully action-specific.	4 / 5
Completeness	It clearly states what the skill covers ('Use for ML workspaces, jobs, models, datasets, compute, and pipelines'), which functions as an explicit trigger clause, giving both what and when; however the 'when' is a scope assertion rather than concrete trigger phrases, so it sits just below the 4 anchor.	3 / 5
Trigger Term Quality	It surfaces natural terms a user would say ('ML workspaces', 'jobs', 'models', 'datasets', 'compute', 'pipelines'), though it lacks common synonyms and SDK-specific phrasings some users would use.	4 / 5
Distinctiveness Conflict Risk	The Azure ML SDK v2 framing carves a clear niche with distinct triggers and minimal overlap risk, though the resource list could overlap lightly with general cloud-ML skills.	4 / 5
	Total	15 / 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: sickn33/antigravity-awesome-skills
Path: skills/azure-ai-ml-py/SKILL.md
Commit: 1f67c44

Reviewed: about 16 hours 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.