mcpField
S
skool-rag

skool-rag

github.com/aiagentwithdhruvProductivity2037 installsUpdated 15w ago
Repository

About skool-rag

skool-rag is a RAG pipeline for searching Skool community content. It prepares and indexes posts, then returns answers with source references using vector search and reranking.

Key features

  1. 01Scrapes and chunks community content
  2. 02Indexes content in Pinecone
  3. 03Searches with vector retrieval and reranking
  4. 04Generates answers with source references

Use cases

  1. 01Find answers in a Skool community
  2. 02Query indexed community discussions
  3. 03Prepare community content for search

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/aiagentwithdhruv/skills --skill skool-rag

After installing, type/skool-ragin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

scripts/
skool_rag_index.py
skool_rag_prepare.py
skool_rag_query.py

Details

From the project README

Skool RAG Pipeline

Goal

Query Skool community content using a RAG (Retrieval-Augmented Generation) pipeline with vector search and reranking.

Scripts

  • ./scripts/skool_rag_prepare.py - Prepare content for indexing
  • ./scripts/skool_rag_index.py - Index content in Pinecone
  • ./scripts/skool_rag_query.py - Query the knowledge base

Pipeline

1. Prepare Content
python3 ./scripts/skool_rag_prepare.py --community makerschool

Scrapes and chunks community content.

2. Index in Pinecone
python3 ./scripts/skool_rag_index.py --input .tmp/skool_chunks.json

Creates OpenAI embeddings and stores in Pinecone.

3. Query
python3 ./scripts/skool_rag_query.py --query "How do I get my first client?"

Pipeline:

  1. OpenAI embeddings for query
  2. Pinecone vector search
  3. Cohere reranking
  4. Claude response generation

Environment

PINECONE_API_KEY=your_key
OPENAI_API_KEY=your_key
COHERE_API_KEY=your_key
ANTHROPIC_API_KEY=your_key

Schema

Inputs
NameTypeRequiredDescription
querystringYesNatural language question to search for
communitystringNoCommunity slug to index (default: makerschool)
Outputs
NameTypeDescription
answerstringAI-generated answer with source references
Credentials
NameSource
PINECONE_API_KEY.env
OPENAI_API_KEY.env
COHERE_API_KEY.env
ANTHROPIC_API_KEY.env
Composable With

Skills that chain well with this one: skool-monitor

Cost

Pinecone + OpenAI embeddings + Cohere reranking + Claude

Comments

Markdown supported