How this skill is triggered — by the user, by Claude, or both
Slash command
/nebulaos:nebulaos-ragThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use este guia para configurar e usar conexões RAG para busca semântica.
Use este guia para configurar e usar conexões RAG para busca semântica.
nebulaos rag connections list
nebulaos rag connections list -o json
# OpenAI
nebulaos rag connections create \
--name minha-base \
--type openai \
--api-key sk-... \
--model text-embedding-3-small
# Azure
nebulaos rag connections create \
--name azure-embeddings \
--type azure \
--base-url https://my-resource.openai.azure.com \
--api-key abc123 \
--model text-embedding-ada-002 \
--dimensions 1536
nebulaos rag connections get <connection-id>
nebulaos rag connections test <connection-id>
nebulaos rag connections update <id> --model text-embedding-3-large
nebulaos rag connections delete <id> -y
# Básica
nebulaos rag search \
--connection <connection-id> \
--query "como configurar autenticação?"
# Com limite
nebulaos rag search \
--connection <connection-id> \
--query "processo de onboarding" \
--limit 5
# JSON
nebulaos rag search \
--connection <connection-id> \
--query "política de privacidade" \
-o json
import { RagOpenAISkill } from "@nebulaos/rag-openai-skill";
const ragSkill = new RagOpenAISkill({
connectionId: "<connection-id>",
maxResults: 5
});
const agent = new Agent({
skills: [ragSkill],
// Tool de busca adicionada automaticamente
});
# 1. Criar
nebulaos rag connections create --name docs --type openai --api-key sk-...
# 2. Testar
nebulaos rag connections test <connection-id>
# 3. Buscar
nebulaos rag search --connection <id> --query "teste"
# 4. Usar no código com RagOpenAISkill
nebulaos rag connections get <id> -o json
# Verificar API key e base-url
nebulaos rag search --connection <id> --query "*" --limit 1
# Usar modelo mais leve
# text-embedding-3-small é mais rápido que text-embedding-3-large
npx claudepluginhub starya-nebulaos/nebulaos-claude-skills --plugin nebulaosBuild RAG systems for LLM apps using vector databases, embeddings, and retrieval strategies. Use for document Q&A, grounded chatbots, and semantic search.
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->
Covers RAG architecture including design patterns, chunking strategies, embedding models, retrieval techniques, hybrid search, and context assembly for LLM pipelines.