Skip to main content
skill CX Codex

rag-architect · vasallo94 — Claude Code skill: what it does, how to install

rag-architect — a skill for editing a LangGraph-based RAG pipeline: its graph nodes, hybrid retrieval, and LLM prompts.

MIT 1 installs ★ 127 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Vasallo94/ObsidianRAG --skill rag-architect -a claude-code
Open on GitHub

What rag-architect does

This skill gives Claude Code and similar tools a map of a RAG agent built on LangGraph. The AgentState graph runs START → retrieve → generate → END. The retrieve node combines an EnsembleRetriever for hybrid search, an optional reranker, and GraphRAG-style expansion: a function called expand_linked_documents follows [[wikilinks]] found in retrieved notes and pulls those linked notes into the context. The generate node then assembles a prompt from that context and queries Ollama through ChatOllama.

For debugging, the skill points to raising the log level to DEBUG in utils/logger.py or inspecting the graph's intermediate state directly. Its guidance on the retrieve node names specific files, obsidianrag/core/qa_agent.py and a possible qa_service.py split, so the advice assumes that project layout rather than a generic RAG setup.

What it helps with

  • swap retrieval logic between BM25, vector search and a reranker
  • add a new node to the LangGraph pipeline
  • wire up GraphRAG-style context expansion through Obsidian wikilinks
  • rewrite the LLM system prompt to require source citations
  • trace which documents a retrieve node pulled in during debugging

Example prompts for the agent

  • Rework the retrieve node so the reranker only kicks in when BM25 returns nothing
  • Add handling for an unanswerable question in the generate node's prompt
  • Extend expand_linked_documents to follow nested wikilinks

How to install rag-architect

1Skills CLI (Vercel)

npx skills add Vasallo94/ObsidianRAG --skill rag-architect -a claude-code

2Manually: put the files in place

~/.claude/skills/rag-architect/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/rag-architect/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about rag-architect

How do I install rag-architect in Claude Code?

Run npx skills add Vasallo94/ObsidianRAG --skill rag-architect -a claude-code; the skill lands at ~/.claude/skills/rag-architect/SKILL.md.

What does rag-architect do?

It documents a LangGraph RAG pipeline's retrieve and generate nodes, hybrid search, wikilink-based context expansion, and the LLM prompts that call Ollama.

What kind of project does rag-architect assume?

It refers to specific files such as obsidianrag/core/qa_agent.py, so it targets a pipeline shaped like ObsidianRAG with LangGraph nodes and ChatOllama rather than a generic RAG setup.

Source text

SKILL.md · MIT
---
name: rag-architect
description: >
  Usa esta skill para diseñar y modificar el pipeline de RAG, incluyendo
  LangGraph, retrieval híbrido, GraphRAG y prompts de LLM.
tools: ['read', 'edit', 'run_command']
---

# RAG & LangGraph Architect

## Cuándo usar esta skill
- Cuando necesites modificar el flujo de preguntas y respuestas.
- Cuando quieras cambiar la lógica de retrieval (BM25, Vector, Reranker).
- Cuando ajustes los prompts del sistema o del LLM.
- Cuando implementes nuevos nodos en el grafo de LangGraph.

## Cómo usar esta skill

### 1. Arquitectura del Grafo
El agente usa `LangGraph` con el estado `AgentState`.
**Flujo**: `START` -> `retrieve` -> `generate` -> `END`

### 2. Implementación de Nodos

#### Retrieve Node
Usa búsqueda híbrida (EnsembleRetriever) + Reranker opcional + Expansión de GraphRAG (wikilinks).
- Ubicación: `obsidianrag/core/qa_agent.py` y `qa_service.py` (si existe split).

#### Generate Node
Construye el prompt con contexto formateado y llama a Ollama via `ChatOllama`.

### 3. GraphRAG Link Expansion
La función clave es `expand_linked_documents`. Busca notas enlazadas mediante `[[wikilinks]]` en los documentos recuperados y las añade al contexto.

### 4. Prompt Engineering
Los prompts están definidos como `ChatPromptTemplate`.
- Sé explícito sobre el rol.
- Pide citas de las notas fuente.
- Maneja el caso "No lo sé".

### 5. Debugging
Para ver qué documentos se recuperan, puedes ajustar el nivel de log a DEBUG en `utils/logger.py` o inspeccionar el estado intermedio del grafo.

© Vasallo94 · MIT · Vasallo94/ObsidianRAG

Similar skills

All skills for AI and ML →

rag-architect by other authors comes first.

rag-architect https://github.com/Jeffallan rag-architect designs production RAG systems: chunks documents, generates embeddings, configures vector stores, builds hybrid search pipelines, and evaluates retrieval quality. CX Codex +1 5,100installs rag-architect Alireza Rezvani rag-architect is a Claude Code skill that designs a RAG pipeline around your documents and measures retrieval quality. It helps compare chunking strategies, embeddings, and vector databases. CX Codex +1 629installs rag-architect borghei rag-architect — a skill for Claude Code and Cursor designs RAG pipelines and tunes chunking configurations. It benchmarks retrieval quality using Recall@K and MRR on real queries. CX Codex +1 137installs veritasgraph bibinprathap veritasgraph — an MCP server for Claude Code and other agent environments that answers questions over a knowledge graph with mandatory source citations. Runs fully offline via Ollama or through cloud APIs. CX Codex +1 ★ 326repo stars rag-implementation Seth Hobson The rag-implementation skill helps build RAG systems with vector search and LLM answers grounded in external documents. Use it for document Q&A and knowledge assistants. CX Codex +1 13,906installs haiku.rag ggozad haiku.rag is an MCP server for Claude Code that indexes documents and answers questions with page and section references. Search your files through an AI agent. CX Codex +1 ★ 665repo stars neo4j-graphrag-skill neo4j-contrib This Claude Code skill builds GraphRAG retrieval pipelines on Neo4j with the neo4j-graphrag Python package. It helps select retrievers and connect them to an LLM. CX Codex +1 1,200installs wiki-query Ar9av wiki-query searches and synthesizes answers from a compiled Obsidian vault using graph indexing without modifying existing notes. CX Codex +1 3,600installs langchain-rag langchain-ai langchain-rag equips coding agents with reference RAG implementations in Python and TypeScript using LangChain loaders, splitters, and vector stores. CX Codex +1 18,600installs

Project sponsors

Companies that keep this analytics open