skills.rest
michelabboud
michelabboudCOMMUNITY
Explore all skills by this author →
GitHub

RAG

Index codebases and manage RAG servers for semantic search in Claude Code.

3|Updated Jan 9, 2026
Search Tags:#codebase#embeddings#rag#mcp#semantic-search#vector-database#claude-code-helper
One-click install
npx skills add https://github.com/michelabboud/claude-code-helper --skill rag-michelabboud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG
Source: https://github.com/michelabboud/claude-code-helper/tree/main/skills/rag
Command: npx skills add https://github.com/michelabboud/claude-code-helper --skill rag-michelabboud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

RAG provides retrieval-augmented code search and centralized management for Claude Code, enabling fast access to relevant code and scalable project governance.

Core Features & Use Cases

  • Index multiple codebases to create per-project collections and enable semantic search across repositories.
  • Perform contextual code retrieval, find similar snippets, and obtain relevant context for tasks.
  • Manage and configure the RAG MCP backend (ChromaDB, Redis, Qdrant) and embedding options, with per-project hints for Claude Code.

Quick Start

Begin by running /rag to start the setup and explore index, search, and config options.

Frequently Asked Questions about RAG

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic code search across multiple project repositories?▼

You can perform semantic code search by indexing multiple codebases to create per-project collections. This enables contextual code retrieval, finding similar snippets, and obtaining relevant context across repositories.

What vector databases can I use for RAG server management with Claude Code?▼

For RAG server management, you can configure ChromaDB, Redis, and Qdrant as vector database backends. These integrate with local or OpenAI embeddings to store and retrieve codebase collections.

How do I configure Claude Code to auto-discover RAG usage in a project?▼

To auto-discover RAG usage, the Skill writes per-project CLAUDE.md hints within your repositories. This requires the rag-mcp integration and backend registration to properly configure Claude Code.

Do I need a specific MCP integration to enable retrieval-augmented code search?▼

Yes, enabling retrieval-augmented code search requires the rag-mcp integration. You must complete backend registration to manage the RAG server and index multiple projects for semantic queries.

Can I use local embeddings instead of OpenAI for indexing my codebase?▼

Yes, you can use local embeddings instead of OpenAI when indexing your codebase. The system supports both local and OpenAI embeddings for generating vector representations across ChromaDB, Redis, and Qdrant.

What is the best way to start setting up semantic code search for a new project?▼

The best way to start is by running the /rag command to initiate setup. This lets you explore indexing, search, and configuration options to establish per-project collections and register backends.

Related Skills

Explore More Software Engineering Skills→
popup-studio-aipopup-studio-ai
589

bkend-data

Configure MCP-based database schemas and CRUD workflows for API backends.

Official
Intermediate
cwenselcwensel
7

arc-search

Search indexed collections with semantic and full-text queries.

Community
Intermediate
christianearle01christianearle01

project-onboarding-assistant

Create a .claude/ directory and CLAUDE.md template for Claude Code projects.

Community
Basic
g-akrpg-akrp
1

ccc

Search local codebases semantically via a CLI vector index.

Community
Intermediate