azure-ai-ml-py

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

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-ml-py

What are skills?

1.06x

Review — 68%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 100%

↑ 1.06x

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Automate Model Training Submission

Command job submission and monitoring

Criteria

Without context

With context

MLClient constructor

50%

100%

Env var credentials

100%

command() function

100%

Input syntax in command

100%

Input() objects

100%

code param

100%

compute param

100%

environment param

100%

display_name param

100%

Job submission call

100%

studio_url access

100%

Job streaming

100%

Without context: $0.2371 · 3m 23s · 18 turns · 24 in / 3,394 out tokens

With context: $0.3658 · 3m 40s · 19 turns · 21 in / 4,341 out tokens

100%

Bootstrap ML Infrastructure for a New Project

Compute cluster and data asset registration

Criteria

Without context

With context

AmlCompute entity

100%

idle_time_before_scale_down

100%

min_instances=0

100%

max_instances set

100%

begin_create_or_update pattern

100%

Data entity used

100%

AssetTypes constant

100%

Data versioning

100%

data.create_or_update call

100%

Tags on compute

100%

MLClient auth

100%

Without context: $0.2685 · 3m 20s · 17 turns · 22 in / 3,568 out tokens

With context: $0.3972 · 4m 3s · 23 turns · 27 in / 4,163 out tokens

100%

13%

Build an Automated Model Training Pipeline

Multi-step DSL pipeline definition

Criteria

Without context

With context

dsl import

100%

@dsl.pipeline decorator

100%

compute in decorator

100%

description in decorator

100%

Input() for pipeline param

100%

Step output chaining

100%

Pipeline returns dict

100%

Pipeline instantiation

100%

Pipeline job submission

100%

MLClient with env vars

57%

100%

Two distinct steps

100%

Without context: $0.1879 · 2m 11s · 13 turns · 20 in / 3,058 out tokens

With context: $0.3289 · 4m 8s · 20 turns · 22 in / 3,287 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Automate Model Training Submission Bootstrap ML Infrastructure for a New Project Build an Automated Model Training Pipeline

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.