Rag Implementation
- 499 installs
- 30.1k repo stars
- Updated August 4, 2026
- davila7/claude-code-templates
rag-implementation is an LLM architecture skill that designs retrieval-augmented generation pipelines with chunking, embeddings, vector stores, and grounded answer flows for developers building production RAG application
About
rag-implementation is a Claude Code skill from davila7/claude-code-templates, sourced from vibeship-spawner-skills under Apache 2.0, that guides developers through production-grade retrieval-augmented generation. The skill covers document chunking strategies, embedding selection, vector store configuration, retrieval policies, reranking, and grounded answer flows that keep LLM responses tied to source material. It explicitly addresses failure modes of naive vector-search-only approaches and teaches when RAG helps versus when simpler context injection suffices. Developers reach for rag-implementation when building Q&A bots, internal knowledge assistants, or document search features that must scale beyond prototype quality. The specialist persona reflects experience serving high query volumes over large document sets.
- Chunking and embedding design
- Vector store setup
- Retrieval policy tuning
- Grounded answer flows
- Evaluation-minded architecture
Rag Implementation by the numbers
- 499 all-time installs (skills.sh)
- Ranked #1,776 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill rag-implementationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 499 |
|---|---|
| repo stars | ★ 30.1k |
| Last updated | August 4, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do you implement production RAG with vector retrieval?
Design and implement retrieval-augmented generation with chunking, embeddings, vector stores, retrieval policies, and grounded answer flows for LLM applications.
Who is it for?
Backend and ML engineers implementing retrieval-augmented generation beyond basic chunk-and-embed prototypes.
Skip if: Developers who only need a single-shot LLM prompt with no document corpus to retrieve from.
When should I use this skill?
An LLM application must answer questions grounded in a large document set using embeddings and vector search.
What you get
RAG architecture plans, chunking policies, vector store configs, retrieval pipelines, and grounded answer flows.
- RAG architecture design
- Retrieval pipeline configuration
Files
RAG Implementation
You're a RAG specialist who has built systems serving millions of queries over terabytes of documents. You've seen the naive "chunk and embed" approach fail, and developed sophisticated chunking, retrieval, and reranking strategies.
You understand that RAG is not just vector search—it's about getting the right information to the LLM at the right time. You know when RAG helps and when it's unnecessary overhead.
Your core principles: 1. Chunking is critical—bad chunks mean bad retrieval 2. Hybri
Capabilities
- document-chunking
- embedding-models
- vector-stores
- retrieval-strategies
- hybrid-search
- reranking
Patterns
Semantic Chunking
Chunk by meaning, not arbitrary size
Hybrid Search
Combine dense (vector) and sparse (keyword) search
Contextual Reranking
Rerank retrieved docs with LLM for relevance
Anti-Patterns
❌ Fixed-Size Chunking
❌ No Overlap
❌ Single Retrieval Strategy
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Poor chunking ruins retrieval quality | critical | // Use recursive character text splitter with overlap |
| Query and document embeddings from different models | critical | // Ensure consistent embedding model usage |
| RAG adds significant latency to responses | high | // Optimize RAG latency |
| Documents updated but embeddings not refreshed | medium | // Maintain sync between documents and embeddings |
Related Skills
Works well with: context-window-management, conversation-memory, prompt-caching, data-pipeline
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick rag-implementation for full retrieval pipeline design; use a lighter prompt-engineering skill when no document index is required.
FAQ
What RAG components does rag-implementation cover?
rag-implementation covers chunking strategies, embedding selection, vector store setup, retrieval policies, reranking, and grounded answer flows. The skill targets production pipelines where naive vector search alone fails to deliver accurate, source-attributed LLM responses.
When is rag-implementation the right skill to invoke?
rag-implementation fits when developers build LLM apps that must retrieve relevant documents before generating answers. Trigger on keywords like rag, vector search, embeddings, or semantic search over terabyte-scale or high-query-volume corpora.