Name: mlops-engineer
Rating: 41.6 (1 reviews)
Author: administrakt0r

mlops-engineer

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.

Quality

41%

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/mlops-engineer/SKILL.md

The canonical home for this skill is mlops-engineer in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

17%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 an exhaustive enumeration of MLOps tools and capabilities rather than actionable guidance: it contains no executable code or commands, only abstract workflow steps without validation, and a broken in-body reference. It functions as a domain outline, not an instruction set Claude can follow.

Suggestions

Replace the tool catalog with concise, executable guidance (e.g., concrete MLflow/Kubeflow commands or minimal code snippets) for the common cases.

Add validation/verification checkpoints to the Response Approach for destructive or batch operations (model promotion, infra teardown, deployment rollout).

Move the capability/tool catalog into a real reference file under references/ (the cited resources/ path does not exist) and keep SKILL.md as a lean overview with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The ~210-line body is mostly a catalog of tool names and one-line descriptors (e.g., 'Kubeflow Pipelines for Kubernetes-native ML workflows', 'Apache Airflow for complex DAG-based ML pipeline orchestration') that restate domain knowledge Claude already has, making it noticeably verbose and padded.	2 / 5
Actionability	No executable code, commands, or concrete steps appear anywhere; the Instructions ('Apply relevant best practices and validate outcomes') and Capabilities sections describe rather than instruct, matching the entirely-vague anchor.	1 / 5
Workflow Clarity	The 8-step Response Approach gives a rough sequence but steps are high-level and abstract ('Design comprehensive architecture', 'Implement infrastructure as code') with no validation checkpoints for risky batch/destructive operations like model deployment or infra provisioning.	2 / 5
Progressive Disclosure	A large inlined capabilities catalog that clearly belongs in separate reference files dominates the body, and the single reference ('open resources/implementation-playbook.md') points to a path that does not exist among the bundle files.	2 / 5
	Total	7 / 20 Passed

Description

66%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 clearly states what the skill does and names specific tools, but omits any explicit 'when to use' trigger clause, which caps completeness and leaves trigger guidance implicit. It is reasonably specific and distinct but reads more as a capability summary than a trigger-optimized description.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when building ML pipelines, setting up experiment tracking, or managing a model registry').

Include natural user-side synonyms and file/context signals (e.g., 'training pipelines', 'model deployment', 'MLflow tracking') to broaden trigger coverage.

Tighten the tool list so the description signals the niche without leaning on a catalog of product names.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Build comprehensive ML pipelines, experiment tracking, and model registries') plus specific tools (MLflow, Kubeflow), but coverage of the full MLOps scope has minor gaps.	4 / 5
Completeness	Has a clear 'what' (build ML pipelines, tracking, registries) but no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('ML pipelines', 'experiment tracking', 'model registries', 'MLflow', 'Kubeflow', 'MLOps') with good keyword coverage, though a few common synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	MLOps is a fairly distinct niche with tool-specific triggers (MLflow, Kubeflow); mostly distinguishable from other skills with only minor overlap risk against general DevOps or data-engineering skills.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/mlops-engineer/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.