ai-engineer
tessl i github:sickn33/antigravity-awesome-skills --skill ai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
Validation
81%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
Implementation
13%This skill reads like a resume or capability catalog rather than actionable guidance. It extensively lists technologies and frameworks Claude already knows without providing any executable code, concrete examples, or specific implementation patterns. The content would benefit from dramatic reduction and replacement with actual code snippets and specific workflows.
Suggestions
Replace the extensive capability lists with 2-3 concrete, executable code examples for common tasks (e.g., a working RAG implementation, an agent setup)
Move detailed technology lists to a separate REFERENCE.md file and keep only essential quick-start guidance in the main skill
Add validation checkpoints to the workflow, especially for safety-critical operations like prompt injection detection and PII handling
Remove sections that describe what Claude already knows (e.g., what vector databases are, what embedding models exist) and focus on project-specific patterns or constraints
| 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 entire skill describes capabilities and lists technologies but never shows how to actually implement anything. 'Response Approach' is abstract steps, not actionable instructions. | 1 / 3 |
Workflow Clarity | The 'Instructions' section provides a basic 4-step workflow and 'Response Approach' lists 8 steps, but both lack validation checkpoints, concrete verification steps, or feedback loops for error recovery in complex AI operations. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline despite being far too detailed for a skill overview. No navigation structure or links to separate reference materials for the extensive capability lists. | 1 / 3 |
Total | 5 / 12 Passed |
Activation
92%This is a strong skill description that clearly articulates specific capabilities in the LLM/AI application development space and includes explicit trigger guidance. The description uses appropriate third-person voice and covers multiple concrete actions. Minor weakness is potential overlap with other AI-related skills due to some broader terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build production-ready LLM applications', 'advanced RAG systems', 'intelligent agents', 'vector search', 'multimodal AI', 'agent orchestration', and 'enterprise AI integrations'. | 3 / 3 |
Completeness | Clearly answers both what (build LLM apps, RAG systems, agents, vector search, etc.) AND when ('Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'LLM', 'RAG', 'chatbots', 'AI agents', 'AI-powered applications', 'vector search', 'multimodal AI'. These cover common variations of how users describe AI/ML application development. | 3 / 3 |
Distinctiveness Conflict Risk | While specific to AI/LLM domain, terms like 'AI-powered applications' and 'enterprise AI integrations' are broad enough to potentially overlap with other AI-related skills. The RAG, vector search, and agent orchestration terms provide some distinctiveness. | 2 / 3 |
Total | 11 / 12 Passed |
Reviewed
Table of Contents
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.