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

75%

Does it follow best practices?

Impact

100%

1.25x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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 a solid, code-heavy ML pipeline skill with executable examples, clear staging, and well-signaled references to real bundle files. Its main weaknesses are moderate verbosity (a duplicated DAG, time-sensitive version pins, and inlined sections that belong in references) and a few code placeholders that keep actionability from a perfect score.

Suggestions

Remove the 'Basic Airflow DAG' section or replace it with a reference pointer, since it duplicates the Quick Start DAG and inflates token count.

Move version pins ('apache-airflow==3.1.5 mlflow==3.7.0', 'current as of December 2025') into a short, clearly dated note or the references rather than the Quick Start, to avoid time-sensitive decay in the main body.

Relocate the 'Known Issues Prevention' and 'Common Patterns' sections into the existing reference files, keeping SKILL.md as a lean overview with signaled pointers.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful code, but the 'Basic Airflow DAG' duplicates the Quick Start DAG, the Known Issues/Common Patterns sections inline material that could live in references, and pinned versions with a 'current as of December 2025' note add time-sensitive tokens that should be trimmed.	3 / 5
Actionability	Provides mostly executable, copy-paste-ready code (DAGs, callbacks, sensors, TaskGroups, validation), but a few placeholders ('# model.fit(X, y) ...', undefined 'my_function', 'train_lr ...') prevent a 5.	4 / 5
Workflow Clarity	Clear sequences appear in the 5-step Quick Start and the 7-stage pipeline, and the core DAG includes a validate_data >> train checkpoint with XCom passing and a metric-gated deploy; minor gaps remain (the Quick Start itself has no verification step), keeping it below 5.	4 / 5
Progressive Disclosure	Good structure with a well-signaled 'When to Load References' section pointing to three real one-level-deep reference files, but the body still inlines substantial material (7 Known Issues, Common Patterns) that could be split out, so it falls short of 5.	4 / 5
	Total	15 / 20 Passed

Description

83%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 strong: it states concrete capabilities with named tools and provides an explicit 'Use for...' clause with concrete triggers covering both what and when. It is third-person/imperative in voice with no first/second person. Minor gaps in trigger synonym coverage and some broad MLOps terminology keep specificity, trigger quality, and distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and tools ('Automate ML workflows with Airflow, Kubeflow, MLflow') plus several concrete actions ('reproducible pipelines, retraining schedules, MLOps'), but coverage is not fully comprehensive, sitting just below the 5 anchor.	4 / 5
Completeness	Explicitly answers both what ('Automate ML workflows with Airflow, Kubeflow, MLflow') and when ('Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('task failures, dependency errors, experiment tracking issues, retraining schedules') with good coverage, though a few synonyms/extensions are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche in ML pipeline orchestration anchored by named tools, but broad terms like 'MLOps' and 'ML workflows' carry minor overlap risk with adjacent MLOps skills, placing it just below 5.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/ml-pipeline-automation/skills/ml-pipeline-automation/SKILL.md
Commit: 84802a4

Reviewed: 6 days 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.