# yugioh-cards-rag

> yugioh-cards-rag — lucasgrecco-yugioh-cards-rag. Use this tool when you need to efficiently search and retrieve Yu-Gi-Oh! card information, leveraging hybrid retrieval methods and dual embeddings for accurate results. It solves problems related to card data management and querying, providing a robust interface for inputs and outputs. Ideal for use cases requiring fast and precise card information retrieval, such as deck building or strategy development.

Canonical page: https://skillsregistry.net/skills/lucasgrecco-yugioh-cards-rag  
JSON: https://api.skillsregistry.net/v1/skills/lucasgrecco-yugioh-cards-rag

## Description

RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/lucasgrecco/yugioh-cards-rag)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "lucasgrecco-yugioh-cards-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lucasgrecco-yugioh-cards-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lucasgrecco-yugioh-cards-rag/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt