ml-pipeline-automation

Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment tracking issues.

Install with Tessl CLI

npx tessl i github:secondsky/claude-skills --skill ml-pipeline-automation

What are skills?

Review — 87%

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

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

92%

-4%

Daily Model Retraining Pipeline

Airflow DAG retry and branching config

Criteria

Without context

With context

retries count

50%

retry_delay

100%

exponential backoff

100%

max_retry_delay

100%

catchup disabled

100%

max_active_runs

100%

email_on_failure

100%

email_on_retry false

100%

execution_timeout

100%

XCom null check

100%

BranchPythonOperator

100%

No hardcoded paths

100%

Without context: $0.3258 · 1m 35s · 13 turns · 13 in / 5,615 out tokens

With context: $0.7135 · 2m 34s · 21 turns · 21 in / 9,396 out tokens

93%

21%

Hyperparameter Tuning Experiment Tracker

MLflow experiment tracking and model registry

Criteria

Without context

With context

set_tracking_uri

100%

set_experiment

100%

log_params

100%

log both train and test metrics

70%

log_model artifact

100%

log confusion matrix

100%

parent run for grid search

100%

nested child runs

100%

register_model

100%

transition stage

100%

archive_existing_versions

100%

load from registry

100%

50%

Without context: $0.5602 · 2m 29s · 22 turns · 22 in / 6,524 out tokens

With context: $0.9143 · 3m 9s · 29 turns · 29 in / 8,160 out tokens

98%

47%

Data Quality Monitor for ML Pipelines

Data quality validation and drift detection

Criteria

Without context

With context

ColumnSchema dataclass

20%

100%

DataValidator class

87%

100%

required columns check

100%

nullable check

50%

100%

numeric range check

100%

allowed values check

100%

KS test for numerical drift

33%

100%

chi-squared for categorical drift

100%

drift threshold config

37%

100%

structured alert output

70%

100%

drift history stored

75%

Without context: $1.2858 · 3m 51s · 37 turns · 38 in / 17,913 out tokens

With context: $1.3582 · 4m 20s · 35 turns · 83 in / 17,028 out tokens

Evaluated: 3 days ago
Agent: Claude Code

Table of Contents

Daily Model Retraining Pipeline Hyperparameter Tuning Experiment Tracker Data Quality Monitor for ML Pipelines

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.