ml-engineer

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

Quality

48%

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/ml-engineer/SKILL.md

Quality

Content

20%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is an extensive catalog of ML tools and capabilities that adds little beyond common knowledge, with no concrete code or validation-gated workflows and no progressive disclosure into reference files.

Suggestions

Replace the long capability/tool catalogs with lean, actionable guidance (concrete code snippets or commands) for the tasks Claude would actually perform.

Add explicit validation checkpoints in the 'Response Approach' workflow for deployment and batch operations (e.g., validate model, verify serving endpoint, monitor drift).

Move detailed tool lists and reference material into separate reference files and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is a long enumeration of framework names and capability bullets that largely restates domain knowledge Claude already has; it is padded and verbose rather than lean.	1 / 3
Actionability	It describes capabilities ('Model serving platforms: TensorFlow Serving, TorchServe...') without any executable code, concrete commands, or copy-paste-ready guidance, so it instructs only abstractly.	1 / 3
Workflow Clarity	The 'Response Approach' section lists a numbered sequence, but steps are abstract and lack validation checkpoints despite covering deployment and batch operations where feedback loops are required.	2 / 3
Progressive Disclosure	Sections are well-organized, but all content is inline in a monolithic SKILL.md with no external references or bundle files, so material that should be split out is not separated.	2 / 3
	Total	6 / 12 Passed

Description

77%Weight 40%Scale 1-3

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 specific and covers both capabilities and explicit use-when triggers, but its trigger terms lean technical and the broad ML domain creates some overlap risk with related skills.

Suggestions

Add more natural-language trigger phrases a user would actually say (e.g., 'deploy a model', 'serve predictions', 'set up ML monitoring') rather than only technical terms.

Sharpen the niche by scoping triggers to production-serving scenarios to reduce overlap with general data-science or DevOps skills.

Drop the meta-directive 'PROACTIVELY' from user-facing trigger wording in favor of plain 'Use when...' phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'model serving, feature engineering, A/B testing, and monitoring', matching the top anchor for specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Build production ML systems... Implements model serving...') and when ('Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes relevant terms like 'ML model deployment' and 'inference optimization', but these read as technical jargon rather than natural user phrasing and lack common variations; the meta-directive 'PROACTIVELY' is not a natural trigger.	2 / 3
Distinctiveness Conflict Risk	The 'production ML infrastructure' framing gives a niche, but the broad ML scope could still overlap with adjacent data-science or DevOps skills, so it is only somewhat specific.	2 / 3
	Total	10 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/ml-engineer/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.