ai-engineer

Principal AI Architect and Machine Learning Engineer.

Quality

17%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/ai-engineer/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a job title rather than a skill description. It provides no information about what actions the skill performs, when it should be used, or what specific problems it solves. Claude would have no basis for selecting this skill over any other AI/ML-related skill.

Suggestions

Replace the job title with specific actions the skill performs (e.g., 'Designs ML model architectures, reviews training pipelines, optimizes model performance')

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when designing neural networks, selecting model architectures, or optimizing ML systems')

Include specific domains or file types this skill handles to distinguish it from other AI/ML skills (e.g., 'PyTorch models, TensorFlow deployments, MLOps pipelines')

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Principal AI Architect and Machine Learning Engineer' is a job title, not a description of capabilities or actions the skill performs.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It's merely a role title with no explanation of capabilities or usage triggers.	1 / 3
Trigger Term Quality	While 'AI' and 'Machine Learning' are technical terms, they are overly broad and not natural trigger terms users would say when needing a specific skill. No actionable keywords like 'train model', 'deploy', 'analyze data' are present.	1 / 3
Distinctiveness Conflict Risk	Extremely generic - 'AI' and 'Machine Learning' could overlap with countless other skills. There's nothing distinctive about this description that would help Claude select it appropriately.	1 / 3
	Total	4 / 12 Passed

Implementation

35%

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

This skill reads more like a knowledge taxonomy or capability overview than actionable guidance. It catalogs AI engineering concepts comprehensively but fails to provide the concrete, executable instructions Claude needs to actually implement these patterns. The content describes what to do conceptually without showing how to do it.

Suggestions

Add executable code examples for at least 2-3 core patterns (e.g., a complete ReAct loop implementation, a RAG retrieval example with actual code)

Replace vague execution steps like 'Classify AI Intent' with concrete decision criteria or a flowchart/checklist

Include the actual content of referenced scripts inline or provide meaningful summaries of what they do and when to use them

Remove the persona framing ('You are a Principal AI Architect') and marketing language to focus on actionable instructions

Dimension	Reasoning	Score
Conciseness	The content is moderately efficient but includes some unnecessary framing ('You are a Principal AI Architect') and marketing-style language ('Master Kit', emojis). The bullet points are reasonably dense but could be tighter.	2 / 3
Actionability	The skill is almost entirely descriptive rather than instructive. It lists concepts and techniques (ReAct, CoT, RAG) without providing executable code examples, concrete implementations, or copy-paste ready guidance. The execution protocol references scripts that aren't shown.	1 / 3
Workflow Clarity	The Execution Protocol provides a 4-step sequence, but steps are vague ('Classify AI Intent', 'Design Flow') without concrete criteria or validation checkpoints. No feedback loops or error recovery guidance for complex AI system operations.	2 / 3
Progressive Disclosure	Has an internal menu and references sub-skills/scripts, but the main content is a wall of bullet points that could be better organized. The referenced Knowledge Module at the end is incomplete/truncated, and script references point to files without explaining their purpose.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Dokhacgiakhoa/antigravity-ide
Commit: 332e58b

Reviewed: 17 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.