corpus-rag-setup

Configure and maintain a local semantic search index for project documentation.

6|3|Updated Apr 12, 2026

Search Tags:#documentation #indexing #knowledge management #semantic search #rag #mcp

Ready to run

npx skills add https://github.com/carson-sweet/sweetclaude --skill corpus-rag-setup

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: corpus-rag-setup
Source: https://github.com/carson-sweet/sweetclaude/tree/main/skills/corpus-rag-setup
Command: npx skills add https://github.com/carson-sweet/sweetclaude --skill corpus-rag-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp-local-rag.

What problem does it solve?

This skill solves the challenge of fragmented project knowledge by indexing your local documentation and files, allowing you to query your entire project history and specs using semantic search.

Core Features & Use Cases

Intelligent Indexing: Automatically filters out noise like scratch files, archives, and build artifacts to ensure only relevant content is indexed.
Semantic Search: Enables natural language querying across your project's documentation, strategy files, and canonical records.
Use Case: Quickly find the specific design decision made three months ago by asking the AI to search your project corpus for relevant context.

Quick Start

Run the corpus-rag-setup skill to initialize the local semantic search index for your current project directory.

Frequently Asked Questions about corpus-rag-setup

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

FAQPage Schema

How do I set up local semantic search for my project documentation?▼

To set up local semantic search, run the corpus-rag-setup skill to initialize an index manifest for your project directory using the mcp-local-rag server, filtering out build artifacts and scratch files to index only relevant documentation.

What kind of files does semantic search index from my project directory?▼

Semantic search indexing intelligently filters out noise like scratch files, archives, and build artifacts, ensuring only relevant content such as project documentation, strategy files, and canonical records are indexed for natural language querying.

Do I need npm to configure local semantic search with mcp-local-rag?▼

Yes, you need npm for package management to configure and maintain the local semantic search index, which integrates directly with the Claude Code MCP framework and the mcp-local-rag server.

Can I use natural language to query my project's design decisions?▼

Yes, you can query your project's design decisions using natural language. Semantic search enables you to search your project corpus to find specific context, history, and specs from indexed documentation.

How does the indexing reconciliation process ensure index quality?▼

Index quality is maintained through a structured reconciliation process that scans project directories, manages an index manifest, and ensures the semantic search index accurately reflects relevant documentation while excluding irrelevant noise.

What's the best way to manage fragmented project knowledge for AI queries?▼

To manage fragmented project knowledge, use local semantic search to index your documentation and files, allowing the AI to query your entire project history and canonical records using natural language instead of manual searching.