rag-implementation

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

2.07x

Quality

56%

Does it follow best practices?

Impact

83%

2.07x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/llm-application-dev/skills/rag-implementation/SKILL.md

Evaluation results

100%

68%

Regulatory Compliance Q&A Assistant

LangGraph RAG pipeline with preferred libraries

Criteria

Without context

With context

LangGraph import

100%

ChatAnthropic client

100%

Correct Claude model

100%

VoyageAI embeddings import

100%

voyage-3-large model

100%

RAGState TypedDict

66%

100%

Retriever k=4

100%

Async invocation

100%

Cannot-answer fallback

100%

63%

35%

Legal Document Search System

Hybrid search with chunking and structured output

Criteria

Without context

With context

EnsembleRetriever

80%

70%

BM25 weight 0.3

100%

Dense weight 0.7

100%

RecursiveCharacterTextSplitter

100%

Chunk size 1000

Chunk overlap 200

Chroma vector store

100%

Chroma persist_directory

Citation format in prompt

Structured output model

30%

100%

Structured model fields

100%

86%

24%

Production RAG System with Cloud Vector Store and Quality Improvements

Production Pinecone setup and reranking configuration

Criteria

Without context

With context

Pinecone dimension=1024

100%

Pinecone metric=cosine

100%

ServerlessSpec aws us-east-1

100%

CrossEncoder model name

100%

MMR fetch_k=20

50%

100%

MMR lambda_mult=0.5

Metadata source field

100%

Metadata category field

100%

Metadata date field

100%

50%

Faithfulness metric

100%

Five eval metrics

37%

100%

Repository: wshobson/agents
Commit: 91fe43e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Regulatory Compliance Q&A Assistant Legal Document Search System Production RAG System with Cloud Vector Store and Quality Improvements

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.