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

63%

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/machine-learning-ops/skills/ml-pipeline-workflow/SKILL.md

Quality

Content

42%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-structured into clear sections but suffers from low actionability — most code blocks are stubs — and references bundle files that are not present. Workflow sequencing exists but is missing explicit validation gates for destructive/batch operations.

Suggestions

Replace stub code blocks with minimal executable examples (e.g., a real Airflow/Dagster DAG snippet or a concrete training-job invocation) so guidance is copy-paste-ready.

Add explicit validation/feedback-loop checkpoints to the Production Workflow (e.g., 'Validate data quality before training', 'Validate metrics before approving deployment', 'Rollback on validation failure') to satisfy the destructive/batch-operation requirement.

Either create the referenced references/*.md and assets/* files so the progressive-disclosure links resolve, or remove the dangling references and inline the essential content.

Dimension	Reasoning	Score
Conciseness	Mostly organized as lists rather than padded prose, but includes redundant stage restatements and several stub code blocks with no content, which could be tightened.	3 / 5
Actionability	Largely high-level lists and named tools with very little executable code; the Python/YAML blocks are stubs that point elsewhere rather than copy-paste-ready guidance.	2 / 5
Workflow Clarity	A four-phase production workflow is sequenced, but batch/destructive operations (training, deployment, rollouts) lack explicit validate/feedback-loop checkpoints, capping the score per the rubric.	3 / 5
Progressive Disclosure	The body clearly signals one-level-deep references to references/ and assets/ with named files, but those directories do not exist, leaving the navigation references dangling.	3 / 5
	Total	11 / 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 clear, specific, and explicitly covers both what the skill does and when to use it with natural trigger phrases. It is mostly distinct from other skills with only minor overlap risk with related ML tooling.

Dimension	Reasoning	Score
Specificity	Names the MLOps domain and concrete pipeline stages (preparation, training, validation, deployment) but is not fully exhaustive on every action, leaving minor gaps.	4 / 5
Completeness	Explicitly states what it does ('Build end-to-end MLOps pipelines from data preparation through...deployment') and when to use it with concrete trigger phrases, satisfying both anchors.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('ML pipelines', 'MLOps practices', 'model training and deployment workflows') but omits common synonyms and abbreviations like 'machine learning pipelines'.	4 / 5
Distinctiveness Conflict Risk	Has a clear MLOps-pipeline niche with distinct triggers, though it has minor overlap risk with adjacent ML skills like experiment tracking or hyperparameter tuning.	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
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: d6837ae

Reviewed: about 12 hours 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.