ai-engineer

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Quality

12%

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/ai-engineer/SKILL.md

Quality

Content

0%Scale 1-3

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

This skill reads as a persona/role description rather than an actionable skill document. It is essentially a long enumeration of AI technologies, frameworks, and abstract behavioral guidelines with no executable code, no concrete workflows, and no practical guidance. The content would need a fundamental restructuring to become useful—replacing technology catalogs with specific, executable patterns and splitting detailed topics into referenced sub-files.

Suggestions

Replace the technology enumeration lists with 2-3 concrete, executable code examples for the most common tasks (e.g., a production RAG pipeline setup, an agent workflow with LangGraph) with copy-paste ready code.

Rewrite the 'Instructions' section as a detailed multi-step workflow with explicit validation checkpoints, especially for complex operations like RAG system setup or agent deployment.

Remove or drastically condense the 'Capabilities', 'Behavioral Traits', 'Knowledge Base', 'Purpose', and 'Example Interactions' sections—these describe what Claude already knows and consume tokens without adding actionable value.

Split detailed guidance for major topics (RAG systems, agent frameworks, production deployment) into separate referenced files to enable progressive disclosure and reduce the main file to a concise overview.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded with information Claude already knows. The massive capability lists (model names, framework names, database names) are essentially catalogs that don't teach Claude anything new. Sections like 'Behavioral Traits', 'Knowledge Base', 'Example Interactions', and 'Purpose' are redundant persona descriptions that waste tokens without adding actionable value.	1 / 3
Actionability	Contains zero executable code, no concrete commands, no specific examples with inputs/outputs. The entire skill is abstract description and enumeration of technologies. The 'Instructions' section is four vague bullet points ('Clarify use cases', 'Design the AI architecture') that provide no concrete guidance on how to actually perform any task.	1 / 3
Workflow Clarity	The four-step 'Instructions' workflow is extremely vague with no validation checkpoints, no error recovery, and no concrete sequencing. For a skill covering complex operations like RAG pipelines, agent orchestration, and production deployments, the absence of any detailed workflow with verification steps is a critical gap.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle files to support the breadth of topics covered. All content is inline in a single massive document. The content would benefit enormously from splitting detailed capability areas into separate reference files, but instead everything is dumped into one flat structure.	1 / 3
	Total	4 / 12 Passed

Description

25%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 reads like a marketing pitch rather than a functional skill selector, relying heavily on buzzwords like 'production-ready', 'advanced', 'intelligent', and 'enterprise' without specifying concrete actions. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill. The extremely broad scope covering nearly all AI application development creates high conflict risk with more specialized skills.

Suggestions

Add an explicit 'Use when...' clause with specific trigger scenarios, e.g., 'Use when the user asks to build RAG pipelines, configure vector databases, create LLM-powered agents, or integrate AI APIs into applications.'

Narrow the scope or clearly delineate sub-capabilities to reduce conflict risk — currently it covers too many distinct domains (RAG, agents, multimodal, enterprise integrations) that could each be separate skills.

Replace vague buzzwords ('production-ready', 'advanced', 'intelligent', 'enterprise') with concrete actions like 'configures embedding pipelines', 'implements document chunking strategies', 'sets up tool-calling agent loops'.

Dimension	Reasoning	Score
Specificity	Names the domain (LLM applications, RAG systems, agents) and lists some actions (vector search, multimodal AI, agent orchestration, enterprise AI integrations), but these are more like buzzword categories than concrete specific actions. It doesn't describe what it actually does with these things (e.g., 'configures vector databases', 'implements retrieval pipelines').	2 / 3
Completeness	Describes 'what' at a high level but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent statement telling Claude when to select this skill, which per the rubric should cap completeness at 2, and since the 'what' is also somewhat vague/buzzwordy, this falls to 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'RAG', 'LLM', 'vector search', 'agents', and 'multimodal AI' that users might mention. However, it misses common variations and natural phrasings users would say like 'chatbot', 'embeddings', 'retrieval augmented generation', 'AI pipeline', 'langchain', 'llamaindex', or specific framework names.	2 / 3
Distinctiveness Conflict Risk	The description is extremely broad, covering LLM applications, RAG, agents, vector search, multimodal AI, and enterprise integrations — essentially the entire AI/ML application space. This would easily conflict with more specific skills for any of these individual areas and provides no clear niche.	1 / 3
	Total	6 / 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: popey/claude-code-skills
Path: skills/ai-engineer/SKILL.md
Commit: a5a6601

Reviewed: 5 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.