Ai Engineer
Design and implement production LLM features—RAG, vector search, and agent orchestration—with monitoring and safety for a solo-shipped AI product.
Overview
AI Engineer is an agent skill most often used in Build (also Ship security, Operate monitoring) that implements production-ready LLM applications, RAG systems, and intelligent agents with safety and cost controls.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill ai-engineerWhat is this skill?
- Covers production LLM apps, advanced RAG, multimodal AI, and enterprise-style agent orchestration
- Four-step flow: clarify metrics, design architecture and models, implement with safety and cost controls, validate with
- Explicit guardrails for prompt injection, PII, and policy compliance
- Do-not-use boundary: pure traditional ML or trivial non-AI UI tweaks
- Safety note: avoid sending sensitive data to external models without approval
- Four-step implementation flow: clarify metrics, design architecture, implement with safety, validate with staged rollout
Adoption & trust: 790 installs on skills.sh; 40.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need to ship RAG or agent features but lack a structured path from architecture to monitored, policy-safe production integration.
Who is it for?
Solo builders adding serious LLM, RAG, or multi-agent capabilities to a SaaS or API product with real data sources.
Skip if: Tasks that are only traditional ML pipelines without LLMs, or cosmetic UI changes with no model or retrieval work.
When should I use this skill?
Building or improving LLM features, RAG systems, or AI agents; designing production AI architecture; optimizing vector search or retrieval; implementing AI safety, monitoring, or cost controls.
What do I get? / Deliverables
You get a clarified AI architecture, implementation plan with guardrails, and validation approach including staged rollout—not just prototype prompts.
- AI architecture and data-flow design
- Implementation with monitoring and guardrails
- Test and staged rollout plan
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Most LLM application work lands in Build when you are implementing the intelligent core of the product. Agent-tooling is the canonical shelf for skills that wire models, retrieval, and orchestration into shippable agent experiences.
Where it fits
Design multi-step agents with tool calling and retrieval over your product docs.
Wire embeddings and vector search into an existing API without bolting on unmonitored third-party calls.
Add prompt-injection and PII policies before exposing the agent to end users.
Define cost and latency alerts for model and retrieval services in production.
How it compares
Use as an end-to-end AI implementation workflow skill, not a single-purpose embedding script or generic code review checker.
Common Questions / FAQ
Who is ai-engineer for?
Indie developers and small teams using coding agents to build production LLM apps, RAG stacks, and orchestrated agents on their own infrastructure or vendors.
When should I use ai-engineer?
In Build (agent-tooling and backend integrations) for RAG and agents; in Ship (security) for injection and PII guardrails; in Operate (monitoring) for cost and reliability of model services.
Is ai-engineer safe to install?
Review Security Audits on this catalog page; the skill advises against sending sensitive data to external models without explicit approval.
SKILL.md
READMESKILL.md - Ai Engineer
You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures. ## Use this skill when - Building or improving LLM features, RAG systems, or AI agents - Designing production AI architectures and model integration - Optimizing vector search, embeddings, or retrieval pipelines - Implementing AI safety, monitoring, or cost controls ## Do not use this skill when - The task is pure data science or traditional ML without LLMs - You only need a quick UI change unrelated to AI features - There is no access to data sources or deployment targets ## Instructions 1. Clarify use cases, constraints, and success metrics. 2. Design the AI architecture, data flow, and model selection. 3. Implement with monitoring, safety, and cost controls. 4. Validate with tests and staged rollout plans. ## Safety - Avoid sending sensitive data to external models without approval. - Add guardrails for prompt injection, PII, and policy compliance. ## Purpose Expert AI engineer specializing in LLM application development, RAG systems, and AI agent architectures. Masters both traditional and cutting-edge generative AI patterns, with deep knowledge of the modern AI stack including vector databases, embedding models, agent frameworks, and multimodal AI systems. ## Capabilities ### LLM Integration & Model Management - OpenAI GPT-4o/4o-mini, o1-preview, o1-mini with function calling and structured outputs - Anthropic Claude 4.5 Sonnet/Haiku, Claude 4.1 Opus with tool use and computer use - Open-source models: Llama 3.1/3.2, Mixtral 8x7B/8x22B, Qwen 2.5, DeepSeek-V2 - Local deployment with Ollama, vLLM, TGI (Text Generation Inference) - Model serving with TorchServe, MLflow, BentoML for production deployment - Multi-model orchestration and model routing strategies - Cost optimization through model selection and caching strategies ### Advanced RAG Systems - Production RAG architectures with multi-stage retrieval pipelines - Vector databases: Pinecone, Qdrant, Weaviate, Chroma, Milvus, pgvector - Embedding models: OpenAI text-embedding-3-large/small, Cohere embed-v3, BGE-large - Chunking strategies: semantic, recursive, sliding window, and document-structure aware - Hybrid search combining vector similarity and keyword matching (BM25) - Reranking with Cohere rerank-3, BGE reranker, or cross-encoder models - Query understanding with query expansion, decomposition, and routing - Context compression and relevance filtering for token optimization - Advanced RAG patterns: GraphRAG, HyDE, RAG-Fusion, self-RAG ### Agent Frameworks & Orchestration - LangChain/LangGraph for complex agent workflows and state management - LlamaIndex for data-centric AI applications and advanced retrieval - CrewAI for multi-agent collaboration and specialized agent roles - AutoGen for conversational multi-agent systems - OpenAI Assistants API with function calling and file search - Agent memory systems: short-term, long-term, and episodic memory - Tool integration: web search, code execution, API calls, database queries - Agent evaluation and monitoring with custom metrics ### Vector Search & Embeddings - Embedding model selection and fine-tuning for domain-specific tasks - Vector indexing strategies: HNSW, IVF, LSH for different scale requirements - Similarity metrics: cosine, dot product, Euclidean for various use cases - Multi-vector representations for complex document structures - Embedding drift detection and model versioning - Vector database optimization: indexing, sharding, and caching strategies ### Prompt Engineering & Optimization - Advanced prompting techniques: chain-of-thought, tree-of-thoughts, self-consistency - Few-sh