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.

1.25x

Quality

70%

Does it follow best practices?

Impact

100%

1.25x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/ml-pipeline-automation/skills/ml-pipeline-automation/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides highly actionable, executable code examples covering Airflow, MLflow, and common ML pipeline patterns, which is its primary strength. However, it is significantly too verbose — containing redundant examples, generic best practices, and explanatory content that Claude doesn't need. The content would benefit from aggressive trimming and moving detailed patterns/known issues into the referenced (but missing) bundle files.

Suggestions

Cut the content by ~50%: remove the redundant Basic Airflow DAG (nearly identical to Quick Start), the generic best practices list, the tool comparison table, and the pipeline stages enumeration — Claude already knows these concepts.

Move the 'Known Issues Prevention' and 'Common Patterns' sections into the referenced bundle files (e.g., references/airflow-patterns.md) to keep SKILL.md as a lean overview.

Add explicit validation checkpoints to the main workflow — e.g., verify Airflow DB init succeeded, confirm DAG appears in scheduler, validate model metrics before any deployment step.

Remove or relocate the pinned version numbers (apache-airflow==3.1.5, mlflow==3.7.0) which will become stale; instead just note to install latest stable versions.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines. It includes redundant code examples (the Quick Start DAG and the Basic Airflow DAG are nearly identical), explains basic concepts Claude already knows (pipeline stages, tool comparisons), lists 8 best practices that are generic software engineering wisdom, and includes a 'When to Use This Skill' section that restates the description. The Quick Start example alone is ~50 lines when it could be half that.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready code throughout — complete Airflow DAG definitions, MLflow tracking integration, bash commands for setup, and concrete patterns for branching, parallel execution, and sensors. The Known Issues section pairs specific problems with working code solutions.	3 / 3
Workflow Clarity	The Quick Start provides a clear 5-step sequence, and the pipeline stages are enumerated. However, there are no explicit validation checkpoints in the main workflows — for example, after 'airflow db init' there's no verification step, and the Basic Airflow DAG doesn't include a validation-before-deploy gate. The conditional execution pattern partially addresses this but it's in a separate section rather than integrated into the core workflow.	2 / 3
Progressive Disclosure	The skill references three reference files (airflow-patterns.md, kubeflow-mlflow.md, pipeline-monitoring.md) with clear descriptions of when to load them, which is good structure. However, no bundle files are provided, so these references are unverifiable. More importantly, the main SKILL.md contains too much inline content (known issues, common patterns, full DAG examples) that should be in reference files, making the overview bloated.	2 / 3
	Total	8 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description that clearly identifies its niche in ML workflow automation and orchestration. It benefits from naming specific tools and including both proactive use cases (pipelines, retraining) and reactive triggers (task failures, dependency errors). The main weakness is that the capabilities could be more concrete—listing specific actions rather than broad categories would strengthen it.

Suggestions

Replace or supplement broad terms like 'automate ML workflows' with specific concrete actions such as 'create and debug Airflow DAGs, configure MLflow experiment tracking, deploy Kubeflow pipelines'.

Dimension	Reasoning	Score
Specificity	Names the domain (ML workflows) and tools (Airflow, Kubeflow, MLflow), and mentions some actions like 'reproducible pipelines' and 'retraining schedules', but doesn't list multiple concrete actions (e.g., 'create DAGs', 'configure experiment tracking', 'debug pipeline failures').	2 / 3
Completeness	Clearly answers both 'what' (automate ML workflows with specific tools) and 'when' ('Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment tracking issues'). The 'Use for...' clause serves as an explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'Airflow', 'Kubeflow', 'MLflow', 'MLOps', 'pipelines', 'retraining', 'task failures', 'dependency errors', 'experiment tracking'. Good coverage of both tool names and problem-oriented terms.	3 / 3
Distinctiveness Conflict Risk	The combination of specific ML orchestration tools (Airflow, Kubeflow, MLflow) and MLOps-specific triggers creates a clear niche that is unlikely to conflict with general coding, data science, or other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: secondsky/claude-skills
Commit: 5e92b71

Reviewed: about 1 month 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.