skills.rest
DucCuong159
DucCuong159COMMUNITY
Explore all skills by this author →
GitHub

rag-implementation

Implements RAG systems covering embedding selection, vector databases, chunking, and retrieval optimization.

Updated Aug 11, 2026
Search Tags:#semantic search#embeddings#llm#rag#vector database#chunking#retrieval-augmented generation
One-click install
npx skills add https://github.com/DucCuong159/Realtime-chatapp --skill rag-implementation-duccuong159
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-implementation
Source: https://github.com/DucCuong159/Realtime-chatapp/tree/main/.agent/skills/rag-implementation
Command: npx skills add https://github.com/DucCuong159/Realtime-chatapp --skill rag-implementation-duccuong159

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building a Retrieval-Augmented Generation system involves many interdependent decisions—embedding models, vector databases, chunking strategies, retrieval methods, and evaluation—and this Skill provides a structured eight-phase workflow that guides you through each one. ## Core Features & Use Cases - Phased RAG Workflow: Eight phases from requirements analysis through embedding selection, vector database setup, chunking, retrieval, LLM integration, caching, and evaluation. - Skill Orchestration: Each phase references specialized skills (e.g., embedding-strategies, vector-database-engineer, hybrid-search-implementation) with copy-paste prompts. - Quality Gates: Checklists verify that embeddings, vector DB, chunking, retrieval, LLM integration, and evaluation are complete. - Use Case: When building a document Q&A system, follow the phases to select an embedding model, configure a vector database, implement hybrid search with reranking, and evaluate retrieval accuracy before launch. ## Quick Start Use the rag-implementation skill to plan and build a RAG pipeline for my document question-answering application.

Frequently Asked Questions about rag-implementation

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

FAQPage Schema
How do I implement a RAG system from scratch?▼

Follow the eight-phase workflow: define requirements, select an embedding model, set up a vector database, implement chunking with overlap, build retrieval with hybrid search and reranking, integrate the LLM, add caching, and evaluate retrieval and generation quality.

How do I choose an embedding model for RAG?▼

Evaluate candidate embedding models for domain relevance, measure embedding quality on your data, and weigh cost and latency trade-offs before selecting one. The workflow's Phase 2 covers this evaluation process.

What chunking strategy should I use for RAG?▼

Choose a chunk size appropriate to your documents, implement chunking with overlap handling, attach metadata to each chunk, and test retrieval quality. The workflow's Phase 4 guides chunk size selection and overlap configuration.

Does RAG retrieval support hybrid search?▼

Yes, the workflow includes combining vector search with keyword search into hybrid retrieval, plus reranking configuration and latency optimization in Phase 5.

How do I evaluate RAG retrieval accuracy?▼

Define evaluation metrics, create a test dataset, measure retrieval accuracy, and evaluate generation quality, then iterate on improvements. Phase 8 of the workflow covers this evaluation process.

When should I not use this RAG workflow?▼

Avoid it when the task does not clearly match RAG implementation scope, and do not treat its output as a substitute for environment-specific validation, testing, or expert review. Stop and clarify if inputs, permissions, or success criteria are missing.

Related Skills

Explore More Software Engineering Skills→
sergiomvjsergiomvj

rag-engineer

Design retrieval pipelines with embeddings, chunking, and hybrid search.

Community
Advanced
davicqueirozdavicqueiroz

RAG Evaluation Skill

Evaluate RAG retrieval, generation, and latency metrics against defined targets.

Community
Advanced
DhumitechDhumitech

prompt-caching

Cache prompts and responses in LLM workflows to reduce latency and API costs.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced