Does this skill require a local database setup?

Yes, it requires the FAISS index files and the rag_query.py interface located in your local D:\AutoRegMonkey\database directory.

What is the primary source of the knowledge base?

The skill queries a RAG database specifically built from the contents of Bruce Hansen's 'Econometrics' textbook, a standard reference in the field.

Which Python environment is used for the queries?

The skill is configured to use the user's Anaconda Python environment for consistent library management and UTF-8 encoding support.

How do I trigger a RAG query in Claude Code?

Simply start your prompt with the 'rag:' prefix (e.g., 'rag: What is heteroskedasticity?') to trigger the Python-based retrieval script.

Can the RAG results be used in automated scripts?

Absolutely. The skill includes a get_context() method that allows Claude to programmatically pull theoretical context into broader data analysis workflows.

Econometrics RAG Assistant

Name: Econometrics RAG Assistant
Author: rukikotoo

byrukikotoo

•

Data Science & ML

Queries a specialized vector database of Bruce Hansen's econometrics textbook to provide accurate academic references and theoretical context.

This skill integrates a Retrieval-Augmented Generation (RAG) system based on Bruce Hansen's authoritative econometrics textbook into Claude's workflow. It allows users to instantly retrieve specific theoretical definitions, formulas, and page-referenced content using a simple 'rag:' prefix. By leveraging a FAISS vector database and Python-based querying, it ensures that statistical analyses and econometric modeling tasks are supported by rigorous academic literature, reducing hallucinations in specialized technical domains and providing precise citations.

Key Features

01Precise page-number referencing for verified academic citations

02Support for both English and Chinese query processing

036 GitHub stars

04Semantic search across Bruce Hansen's Econometrics textbook

05Adjustable similarity scoring and n_results parameters

06Seamless integration with local FAISS vector databases

Use Cases

01Verifying OLS regression assumptions and theoretical proofs during analysis

02Retrieving specific econometric formulas and theorems for implementation

03Cross-referencing statistical model results with textbook-standard methodology

Key Features

01Precise page-number referencing for verified academic citations

02Support for both English and Chinese query processing

036 GitHub stars

04Semantic search across Bruce Hansen's Econometrics textbook

05Adjustable similarity scoring and n_results parameters

06Seamless integration with local FAISS vector databases

Use Cases

01Verifying OLS regression assumptions and theoretical proofs during analysis

02Retrieving specific econometric formulas and theorems for implementation

03Cross-referencing statistical model results with textbook-standard methodology