CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

1.25x
Quality

70%

Does it follow best practices?

Impact

100%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/ml-pipeline-automation/skills/ml-pipeline-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

30%

Production ML Retraining Pipeline

Production Airflow DAG resilience config

Criteria
Without context
With context

retries value

100%

100%

retry_delay

100%

100%

exponential backoff

0%

100%

max retry delay

0%

100%

catchup disabled

100%

100%

single concurrent run

100%

100%

failure alerting

100%

100%

XCom null check

0%

100%

no hardcoded paths

100%

100%

execution timeout

100%

100%

depends_on_past false

100%

100%

conditional deployment

50%

100%

100%

25%

Experiment Tracking for Fraud Detection Model

MLflow experiment tracking and model registry

Criteria
Without context
With context

tracking URI set

100%

100%

experiment named

100%

100%

run context manager

100%

100%

run name set

0%

100%

all hyperparams logged

100%

100%

train metric logged

0%

100%

test metric logged

100%

100%

model artifact logged

100%

100%

model registered

100%

100%

multiple runs executed

100%

100%

dataset params logged

0%

100%

100%

5%

Data Quality Monitoring Module

Data quality validation and drift detection

Criteria
Without context
With context

ColumnSchema dataclass

100%

100%

DataValidator class

87%

100%

schema validation checks

100%

100%

KS test used

100%

100%

KS p-value threshold

100%

100%

DriftMonitor class

100%

100%

alert callback invoked

100%

100%

drift threshold configurable

71%

100%

Prometheus Counter

100%

100%

Prometheus Histogram

100%

100%

Prometheus Gauge metrics

100%

100%

/metrics endpoint

83%

100%

Repository
secondsky/claude-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.