Name: ml-pipeline-workflow
Rating: 36.8 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

ml-pipeline-workflow

Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.

Quality

34%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ml-pipeline-workflow/SKILL.md

The canonical home for this skill is ml-pipeline-workflow in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

31%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 body is well-sectioned and covers the ML lifecycle broadly, but it is padded with tool catalogs Claude already knows, its code blocks are non-executable stubs, and it depends heavily on references/ and assets/ files that are not present in the bundle, breaking progressive disclosure.

Suggestions

Remove tool-name catalogs (Airflow/Dagster/Kubeflow/SageMaker lists) and restated stage lists; keep only decisions Claude could not derive.

Replace comment-stub code blocks with complete, copy-pasteable examples, or explicitly justify the pseudocode.

Either ship the referenced references/ and assets/ files, or stop pointing to them; every dangling path currently breaks navigation.

Dimension	Reasoning	Score
Conciseness	The ~250-line body restates capabilities and tool lists (Airflow, Dagster, Kubeflow, MLflow, SageMaker, etc.) that Claude already knows, and repeats the same stage lists across Overview, Usage Patterns, and Common Patterns, fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Code blocks are non-executable skeletons (comment placeholders like '# See assets/pipeline-dag.yaml.template' and '# pseudocode' style fragments) and the referenced bundle files do not exist, so guidance is high-level hints rather than concrete runnable steps.	2 / 5
Workflow Clarity	The Production Workflow lists a clear data→train→validate→deploy sequence, but this skill performs batch/deploy operations and lacks explicit validation checkpoints (no 'verify before proceed' gates), which the rubric caps at 3.	3 / 5
Progressive Disclosure	The body repeatedly points to references/ and assets/ files (data-preparation.md, model-deployment.md, pipeline-dag.yaml.template, etc.) and resources/implementation-playbook.md, but none of these bundle directories exist, so the disclosure structure is broken — content that should be separate is signaled but missing, fitting 'references are buried / minimal structure'.	2 / 5
	Total	9 / 20 Passed

Description

37%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 declares the domain and lifecycle span but is light on concrete actions and entirely lacks an explicit 'Use when' trigger clause, capping completeness. It is a recognizable niche but broad enough to risk overlap with adjacent ML skills.

Suggestions

Add concrete verbs instead of scope phrasing, e.g. 'Designs, orchestrates, and deploys ML pipelines across data prep, training, validation, and serving.'

Append an explicit trigger clause: 'Use when building or orchestrating ML pipelines, DAG-based training workflows, or automated data-to-deployment pipelines (Airflow, Dagster, Kubeflow).'

Narrow the niche to reduce overlap — call out what is out of scope (e.g. not for single-model training or ad-hoc data analysis).

Dimension	Reasoning	Score
Specificity	Names the domain ('MLOps pipeline orchestration') and the endpoints ('data preparation through model deployment') but lists no concrete actions — it describes scope, not operations, fitting the 'Names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	It states a clear 'what' (end-to-end MLOps orchestration) but has no 'Use when...' trigger clause; the guideline caps completeness at 3 for a missing when-clause, and here the what is only mid-strength, so a 2 fits better than 3.	2 / 5
Trigger Term Quality	Contains relevant terms users might say ('ML pipelines', 'model deployment', 'data preparation') but misses common synonyms and file/tool extensions like Airflow, DAG, Kubeflow, or .yaml, so it is not below 3 but not above it.	3 / 5
Distinctiveness Conflict Risk	'MLOps pipeline orchestration' is a recognizable niche but very broad — it could overlap with separate model-deployment, experiment-tracking, or data-pipeline skills, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	10 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ml-pipeline-workflow/SKILL.md
Commit: 57c135b

Reviewed: 3 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.