Agent Systems & LLM Workflows

RAG Retrieval Quality Engineer

Design and evaluate RAG retrieval with chunking, metadata, hybrid search, reranking, citations, freshness, and failure analysis.

Last updated Jul 11, 2026
FreeClaudeChatGPTCursor
TL;DR

RAG Retrieval Quality Engineer is a free AI skill for agent systems & llm workflows. Design and evaluate RAG retrieval with chunking, metadata, hybrid search, reranking, citations, freshness, and failure analysis. It works with Claude, ChatGPT, Cursor and is ready to use out of the box.

Download Skill.md Package

About this skill

RAG Retrieval Quality Engineer helps teams build retrieval-augmented generation systems that find the right evidence before generation. It defines ingestion, chunking, metadata, embeddings, hybrid search, filters, reranking, freshness, citations, evaluation, observability, and fallback behavior.

What it does

The skill analyzes documents, user questions, permissions, language, scale, and latency; designs the retrieval pipeline; creates evaluation datasets and metrics; identifies failure modes; and produces implementation and tuning guidance.

What is included

  • Document and query analysis
  • Chunking strategy
  • Metadata and permission design
  • Embedding and hybrid retrieval
  • Reranking and context selection
  • Citation and freshness rules
  • Evaluation framework
  • Monitoring and tuning plan

How to use it

1. Download the rag-retrieval-quality-engineer-SKILL.md file
2. Upload it to your AI or search workspace
3. Provide sample documents, queries, users, permissions, and current retrieval behavior
4. Add latency and freshness requirements
5. Use the design to implement and evaluate RAG

Examples

Example input
Design retrieval for an internal engineering assistant using architecture docs, runbooks, tickets, API docs, and code references.
Example output
A complete RAG retrieval plan with ingestion, chunking, metadata, tenant and role filters, embeddings, BM25 hybrid search, reranking, citation rules, evaluation queries, metrics, and failure analysis.

FAQ

What is this skill for?
It designs and evaluates the retrieval layer of RAG systems.
Does it choose chunk size?
Yes. It evaluates document structure, query types, context limits, and retrieval behavior.
Can it use hybrid search?
Yes. It can combine keyword, vector, metadata, and reranking methods.
How are permissions enforced?
Through retrieval-time identity and metadata filters outside the language model.
Does it measure answer quality?
It focuses on retrieval quality and also links retrieval evidence to answer-grounding checks.
How is this different from general RAG architecture?
It focuses deeply on evidence selection, evaluation, failure analysis, and tuning.

Related Skills

Agent Systems & LLM WorkflowsFree

AI Evaluation Benchmark Designer

Design practical evaluation benchmarks for AI assistants and agents using test sets, scoring rubrics, failure categories, and release thresholds.

ClaudeChatGPTCursor
#ai evaluation#llm benchmark#agent testing
Agent Systems & LLM WorkflowsFree

Agent Memory and Context Governance Architect

Design agent memory governance with memory types, relevance, consent, retention, editing, deletion, isolation, retrieval, and safety.

ClaudeChatGPT
#agent memory#context governance#LLM architecture
Agent Systems & LLM WorkflowsFree

Agent Tool Failure and Recovery Orchestrator

Design agent recovery for unavailable tools, bad responses, timeouts, partial actions, duplicates, permission errors, and human escalation.

ClaudeChatGPT
#agent recovery#tool failure#LLM orchestration

Related Prompts

Free

Agent Retrieval Strategy Designer

Design how an agent finds, verifies, ranks, and cites external knowledge across structured and unstructured sources.

ClaudeChatGPT
#agent-retrieval#rag-design#knowledge-grounding