skills.rest
diegosouzapw
diegosouzapwCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-engineer

Design retrieval-augmented generation pipelines with measurable retrieval quality and grounded citations.

108|27|Updated Mar 26, 2026
Search Tags:#indexing#embeddings#rag#evaluation#retrieval#citations
One-click install
npx skills add https://github.com/diegosouzapw/omni-skills --skill rag-engineer-diegosouzapw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/diegosouzapw/omni-skills/tree/main/skills/rag-engineer
Command: npx skills add https://github.com/diegosouzapw/omni-skills --skill rag-engineer-diegosouzapw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

RAG Engineer helps you design retrieval-augmented generation pipelines that ground AI outputs in verifiable retrieved context, reducing hallucinations and misalignment.

Core Features & Use Cases

  • Define corpus boundaries, chunking metadata, and indexing strategies to improve retrieval precision.
  • Establish citation contracts and evaluation plans to monitor recall, freshness, and answer quality across pipelines.
  • Use cases include knowledge-grounded assistants, internal search systems, and document-heavy workflows.

Quick Start

Outline your knowledge corpus, desired retrieval quality metrics, and required citations to generate a ready-to-use RAG design plan.

Frequently Asked Questions about rag-engineer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a retrieval-augmented generation pipeline with grounded citations?▼

To design a retrieval-augmented generation pipeline, define corpus boundaries, chunking metadata, and indexing strategies to establish citation contracts that ground AI outputs in verifiable retrieved context, reducing hallucinations.

What is the best way to evaluate retrieval quality and recall in a RAG system?▼

Evaluating retrieval quality in a RAG system requires establishing evaluation plans that monitor measurable metrics like recall, freshness, and answer quality across the pipeline to ensure robust document-heavy workflows.

How do I configure chunking and indexing strategies for knowledge-grounded assistants?▼

Configuring chunking and indexing for knowledge-grounded assistants involves defining corpus boundaries and applying specific chunking metadata strategies to improve overall retrieval precision within internal search systems.

Can I build fallback behavior into document-heavy RAG pipelines?▼

Yes, you can build fallback behavior into document-heavy RAG pipelines. The design specifies fallback requirements alongside citation contracts and evaluation metrics to produce a robust, production-ready system.

When do I need to establish citation contracts for internal search systems?▼

You need to establish citation contracts for internal search systems when generating a RAG design that demands verifiable retrieved context, ensuring measurable retrieval quality and grounded answers for document-heavy workflows.

Related Skills

Explore More Software Engineering Skills→
sayalinvidiasayalinvidia

rag-eval

Run filesystem-based RAG benchmarks and output NVSkills metrics.

Community
Advanced
JCETools-PetraJCETools-Petra
16

ai-llm-engineering

Design RAG pipelines with chunking, embedding, retrieval, and evaluation metrics.

Community
Advanced
salmanparachasalmanparacha

building-rag-systems

Build RAG systems with semantic chunking, incremental indexing, and Qdrant vector search.

Community
Advanced
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate