ai-engineer

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

1.00x

Quality

16%

Does it follow best practices?

Impact

56%

1.00x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

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

Quality

Discovery

32%

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 covers a relevant technical domain with moderate specificity but lacks the critical 'Use when...' clause needed for Claude to know when to select this skill. The trigger terms are somewhat technical and could benefit from more natural language variations that users would actually say. The description would benefit from explicit guidance on when to invoke this skill.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when building chatbots, implementing semantic search, creating AI agents, or setting up retrieval-augmented generation pipelines'

Include more natural language trigger terms users would say: 'chatbot', 'embeddings', 'semantic search', 'retrieval augmented generation', 'langchain', 'AI assistant'

Make actions more concrete: instead of 'implements vector search', specify 'create and query vector embeddings, configure retrieval pipelines, build conversational agents'

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 still somewhat abstract rather than concrete specific actions like 'create embeddings' or 'configure retrieval pipelines'.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this description has no 'when' component at all.	1 / 3
Trigger Term Quality	Includes relevant technical terms like 'RAG', 'vector search', 'agents', 'LLM applications' that users might say, but missing common variations like 'chatbot', 'embeddings', 'retrieval augmented generation', 'AI assistant', 'langchain', or 'semantic search'.	2 / 3
Distinctiveness Conflict Risk	The combination of RAG, vector search, and agent orchestration provides some specificity, but terms like 'LLM applications' and 'enterprise AI integrations' are broad enough to potentially overlap with other AI-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

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 persona description or resume than actionable guidance. It extensively lists technologies and capabilities Claude already knows without providing concrete implementation patterns, executable code, or clear workflows. The content would benefit from dramatic reduction and replacement with specific, actionable examples.

Suggestions

Replace the extensive capability lists with 2-3 concrete, executable code examples for common tasks (e.g., a production RAG implementation with Pinecone, a basic agent workflow with LangGraph)

Add explicit validation checkpoints to the workflow, such as 'Test retrieval quality before deploying' with specific metrics or commands

Move detailed technology lists to a separate REFERENCE.md file and keep SKILL.md focused on actionable patterns

Remove sections like 'Purpose', 'Behavioral Traits', and 'Knowledge Base' which describe Claude's persona rather than providing task guidance

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of technologies, capabilities, and knowledge areas that Claude already knows. The 'Capabilities' section alone spans hundreds of tokens listing tools and frameworks without adding actionable guidance.	1 / 3
Actionability	No executable code, no concrete commands, no specific examples. The 'Instructions' section provides only vague 4-step guidance ('Clarify use cases', 'Design the AI architecture') without any concrete implementation details or copy-paste ready snippets.	1 / 3
Workflow Clarity	The 4-step instructions are abstract and lack validation checkpoints. For complex AI systems involving data pipelines, model deployment, and safety controls, there are no explicit verification steps or feedback loops for error recovery.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline including extensive capability lists, behavioral traits, and knowledge bases that could be split into separate reference documents.	1 / 3
	Total	4 / 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: boisenoise/skills-collections
Commit: 5c5ae21

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.