Tessl • The package manager for agent skills

SkillPublic

mlops-engineer

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

Quality

62%

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 ./skills/mlops-engineer/SKILL.md

Quality

Content

25%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 a persona/knowledge dump: an extensive catalog of MLOps tools and capabilities with no executable guidance, no validation checkpoints, and no progressive disclosure into reference files. It largely restates knowledge Claude already has rather than adding skill-specific procedure.

Suggestions

Replace the tool catalog with concise, executable guidance (commands, IaC snippets, MLflow/Kubeflow code examples) for the most common MLOps tasks instead of enumerating every tool.

Move the per-cloud and per-category tool inventories into reference files (e.g. references/cloud-stacks.md, references/tooling.md) and link to them from a lean SKILL.md overview.

Add an explicit multi-step workflow with validation checkpoints (e.g. validate IaC plan -> deploy -> verify endpoint -> monitor drift) including rollback/feedback loops for deployment operations.

Dimension	Reasoning	Score
Conciseness	The ~210-line body is a verbose enumeration of dozens of tools (Kubernetes, Terraform, Prometheus, etc.) that Claude already knows, padded with capability catalogs rather than lean, value-add guidance.	2 / 5
Actionability	It names relevant tools and patterns but provides no executable code, commands, or concrete steps; the 'Response Approach' is abstract direction ('Design comprehensive architecture', 'Implement infrastructure as code') rather than instruction.	2 / 5
Workflow Clarity	The 8-step 'Response Approach' is a rough, abstract sequence with no validation checkpoints, and destructive/batch operations like deployments lack the feedback loops the rubric requires.	2 / 5
Progressive Disclosure	It is a monolithic single-file wall where large tool catalogs that clearly belong in separate reference files are fully inlined, and no external references or bundle files exist to offload detail.	2 / 5
	Total	8 / 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, names specific tools, and provides an explicit trigger clause covering both what and when. Minor weakness is generic padding ('comprehensive', 'modern MLOps tools') and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (build pipelines, experiment tracking, model registries, automated training/deployment/monitoring) and names specific tools (MLflow, Kubeflow), but generic phrasing like 'comprehensive', 'modern MLOps tools', and 'across cloud platforms' leaves minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (build/tracking/registries/training/deployment/monitoring) and 'when' ('Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural keywords users would say ('ML pipelines', 'experiment tracking', 'model registries', 'ML infrastructure', 'pipeline automation', 'MLOps'), but misses some common synonyms and variations.	4 / 5
Distinctiveness Conflict Risk	MLOps is a fairly distinct niche with specific triggers, but it has some overlap risk with general cloud and DevOps skills.	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: rmyndharis/antigravity-skills
Path: skills/mlops-engineer/SKILL.md
Revision: 364ea63

Reviewed: 21 days ago

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.

mlops-engineer

Table of Contents

Is this your skill?