ml-pipeline-workflow

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/machine-learning-ops/skills/ml-pipeline-workflow/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 body is a well-structured overview of ML pipeline concepts and tools, but it over-relies on general knowledge lists and comment-only code snippets that point to bundle files which are absent. Missing validation checkpoints in the workflow and dangling references keep every dimension at the middle anchor.

Suggestions

Create the referenced bundle files (references/data-preparation.md, model-training.md, model-validation.md, model-deployment.md and assets/pipeline-dag.yaml.template, training-config.yaml, validation-checklist.md) or remove the pointers, so the progressive-disclosure navigation actually resolves.

Replace the comment-only code blocks ('# See assets/...', '# Stream processing for real-time features') with minimal executable examples, since the current snippets provide no copy-paste-ready guidance.

Add explicit validation checkpoints and a fix-retry feedback loop to the Production Workflow (e.g. validate data quality before training, validate model metrics before approval, and re-validate on failure before deployment).

Dimension	Reasoning	Score
Conciseness	The body is padded with bullet lists restating tools and best practices Claude already knows (e.g. 'Apache Airflow: DAG-based workflow orchestration', 'Implement gradual rollouts', 'Monitor model performance drift'); mostly organized but includes unnecessary content that could be tightened, matching the level-2 anchor rather than lean level-3.	2 / 3
Actionability	Code blocks are largely comment stubs and pointers such as '# See assets/pipeline-dag.yaml.template' and '# Stream processing for real-time features ... See references/data-preparation.md' rather than executable examples, so guidance is concrete in intent but incomplete and missing key details.	2 / 3
Workflow Clarity	The Production Workflow lays out a four-phase sequence (data preparation, training, validation, deployment), but there are no explicit validation checkpoints or fix-retry feedback loops for these batch and deployment operations, which the guidelines cap at 2.	2 / 3
Progressive Disclosure	References are clearly signaled and one level deep ('data-preparation.md', 'model-deployment.md', 'pipeline-dag.yaml.template'), but the referenced references/ and assets/ directories do not exist, so navigation is broken and the promised split content is missing rather than appropriately separated.	2 / 3
	Total	8 / 12 Passed

Description

92%

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 and pairs them with an explicit 'Use when' trigger, addressing both what and when clearly. The only weakness is moderate overlap with adjacent deployment-focused skills, which keeps distinctiveness below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'data preparation', 'model training', 'validation', and 'production deployment' — rather than vague domain references, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers what it does (build end-to-end MLOps pipelines through named phases) and when to use it via a clear 'Use when...' clause, satisfying both halves of the completeness anchor.	3 / 3
Trigger Term Quality	Trigger phrasing ('creating ML pipelines', 'implementing MLOps practices', 'automating model training and deployment workflows') aligns with natural language a user would say when needing this skill, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	MLOps pipeline orchestration is a recognizable niche, but 'production deployment' and 'deployment workflows' overlap with the related model-deployment-patterns skill, so it could trigger for the wrong skill; not the level-3 'unlikely to conflict' anchor.	2 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Path: plugins/machine-learning-ops/skills/ml-pipeline-workflow/SKILL.md
Commit: c4b82b0

Reviewed: 5 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.